modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-06-28 06:27:35
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 500
values | tags
sequencelengths 1
4.05k
| pipeline_tag
stringclasses 54
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-06-28 06:24:42
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
Klevin/Emo-AI-3B | Klevin | 2024-06-22T03:52:47Z | 5 | 1 | transformers | [
"transformers",
"pytorch",
"gemma",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"en",
"base_model:unsloth/gemma-2b-bnb-4bit",
"base_model:finetune:unsloth/gemma-2b-bnb-4bit",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-06-22T03:47:09Z | ---
base_model: unsloth/gemma-2b-bnb-4bit
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- gemma
- trl
- sft
---
# Uploaded model
- **Developed by:** Klevin
- **License:** apache-2.0
- **Finetuned from model :** unsloth/gemma-2b-bnb-4bit
This gemma model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
mzbac/nougat-base-8bit-mlx | mzbac | 2024-06-22T03:46:07Z | 15 | 0 | transformers | [
"transformers",
"safetensors",
"vision-encoder-decoder",
"image-text-to-text",
"vision",
"nougat",
"image-to-text",
"arxiv:2308.13418",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"region:us"
] | image-to-text | 2024-06-22T03:43:24Z | ---
license: cc-by-nc-4.0
tags:
- vision
- nougat
pipeline_tag: image-to-text
---
# Nougat model, base-sized version
Nougat model trained on PDF-to-markdown. It was introduced in the paper [Nougat: Neural Optical Understanding for Academic Documents](https://arxiv.org/abs/2308.13418) by Blecher et al. and first released in [this repository](https://github.com/facebookresearch/nougat/tree/main).
Disclaimer: The team releasing Nougat did not write a model card for this model so this model card has been written by the Hugging Face team.
Note: this model corresponds to the "0.1.0-base" version of the original repository.
## Model description
Nougat is a [Donut](https://huggingface.co/docs/transformers/model_doc/donut) model trained to transcribe scientific PDFs into an easy-to-use markdown format. The model consists of a Swin Transformer as vision encoder, and an mBART model as text decoder.
The model is trained to autoregressively predict the markdown given only the pixels of the PDF image as input.
<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/nougat_architecture.jpg"
alt="drawing" width="600"/>
<small> Nougat high-level overview. Taken from the <a href="https://arxiv.org/abs/2308.13418">original paper</a>. </small>
## Intended uses & limitations
You can use the raw model for transcribing a PDF into Markdown. See the [model hub](https://huggingface.co/models?search=nougat) to look for other
fine-tuned versions that may interest you.
### How to use
We refer to the [docs](https://huggingface.co/docs/transformers/main/en/model_doc/nougat).
### BibTeX entry and citation info
```bibtex
@misc{blecher2023nougat,
title={Nougat: Neural Optical Understanding for Academic Documents},
author={Lukas Blecher and Guillem Cucurull and Thomas Scialom and Robert Stojnic},
year={2023},
eprint={2308.13418},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
``` |
chickenrice0721/whisper-large-v3-translate-zh-v0.1-lt | chickenrice0721 | 2024-06-22T03:22:37Z | 19 | 5 | transformers | [
"transformers",
"safetensors",
"whisper",
"automatic-speech-recognition",
"audio",
"translate",
"generated_from_trainer",
"zh",
"base_model:openai/whisper-large-v3",
"base_model:finetune:openai/whisper-large-v3",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | automatic-speech-recognition | 2024-06-22T01:30:40Z | ---
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
- audio
- automatic-speech-recognition
- translate
- generated_from_trainer
language:
- zh
metrics:
- cer
- wer
model-index:
- name: whisper-large-v3-translate-zh-v0.1-lt
results: []
pipeline_tag: automatic-speech-recognition
---
# whisper-large-v3-translate-zh-v0.1-lt
This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3).
## Model description
3500小时 (日语音频,中文字幕) 数据微调, 翻译模式直出中文
## Usage
task='translate', language='ja'
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 4000
- dropout: 0.1
- mask_time_prob: 0.05
- mask_feature_prob: 0.2
- condition_on_previous_text_rate: 0.5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Cer | Wer |
|:-------------:|:------:|:-----:|:---------------:|:------:|:------:|
| 2.1282 | 0.0739 | 1000 | 2.1852 | 1.9014 | 4.4904 |
| 1.8567 | 0.1478 | 2000 | 1.8366 | 1.7295 | 3.8716 |
| 1.6968 | 0.2217 | 3000 | 1.2615 | 1.6279 | 2.4825 |
| 1.6264 | 0.2956 | 4000 | 1.0536 | 1.5625 | 1.8101 |
| 1.5687 | 0.3695 | 5000 | 1.0932 | 1.5410 | 2.1218 |
| 1.531 | 0.4433 | 6000 | 1.5156 | 1.2533 | 2.3689 |
| 1.4875 | 0.5172 | 7000 | 1.4697 | 0.9560 | 1.5588 |
| 1.4518 | 0.5911 | 8000 | 1.4521 | 1.0170 | 1.6392 |
| 1.4472 | 0.6650 | 9000 | 1.4463 | 1.0084 | 1.6420 |
| 1.3991 | 0.7389 | 10000 | 1.4238 | 0.9266 | 1.6992 |
| 1.4266 | 0.8128 | 11000 | 1.4141 | 0.8365 | 1.3056 |
| 1.3755 | 0.8867 | 12000 | 1.4033 | 0.7904 | 1.3119 |
| 1.3833 | 0.9606 | 13000 | 1.4004 | 0.8600 | 1.3333 |
| 1.3224 | 1.0345 | 14000 | 1.3770 | 0.8243 | 1.4560 |
| 1.3295 | 1.1084 | 15000 | 1.3770 | 0.7852 | 1.4298 |
| 1.3136 | 1.1823 | 16000 | 1.3564 | 0.7176 | 1.1826 |
| 1.2832 | 1.2561 | 17000 | 1.3535 | 0.6767 | 1.1781 |
| 1.2917 | 1.3300 | 18000 | 1.3584 | 0.7255 | 1.1218 |
| 1.27 | 1.4039 | 19000 | 1.3330 | 0.6590 | 1.1242 |
| 1.2704 | 1.4778 | 20000 | 1.3379 | 0.6934 | 1.1944 |
| 1.2614 | 1.5517 | 21000 | 1.3330 | 0.6949 | 1.1820 |
| 1.2455 | 1.6256 | 22000 | 1.3350 | 0.6931 | 1.0892 |
| 1.2475 | 1.6995 | 23000 | 1.3154 | 0.6662 | 1.1576 |
| 1.2583 | 1.7734 | 24000 | 1.3164 | 0.6490 | 1.0705 |
| 1.2333 | 1.8473 | 25000 | 1.3184 | 0.6833 | 1.1480 |
| 1.2462 | 1.9212 | 26000 | 1.3125 | 0.6672 | 1.1612 |
| 1.2279 | 1.9950 | 27000 | 1.3047 | 0.6644 | 1.2179 |
| 1.1908 | 2.0689 | 28000 | 1.3047 | 0.6938 | 1.2221 |
| 1.1831 | 2.1428 | 29000 | 1.2998 | 0.6316 | 1.0717 |
| 1.1705 | 2.2167 | 30000 | 1.3018 | 0.6165 | 1.0958 |
| 1.171 | 2.2906 | 31000 | 1.3027 | 0.6109 | 1.0868 |
| 1.1567 | 2.3645 | 32000 | 1.3037 | 0.6485 | 1.1736 |
| 1.1705 | 2.4384 | 33000 | 1.2969 | 0.6078 | 1.0515 |
| 1.1819 | 2.5123 | 34000 | 1.2949 | 0.6158 | 1.0362 |
| 1.1447 | 2.5862 | 35000 | 1.2920 | 0.6365 | 1.0558 |
| 1.17 | 2.6601 | 36000 | 1.2881 | 0.6339 | 1.0868 |
| 1.1495 | 2.7340 | 37000 | 1.2949 | 0.6297 | 1.0437 |
| 1.1395 | 2.8078 | 38000 | 1.2900 | 0.6285 | 1.1221 |
| 1.15 | 2.8817 | 39000 | 1.2891 | 0.5997 | 1.0217 |
| 1.1623 | 2.9556 | 40000 | 1.2881 | 0.6085 | 1.0395 |
### Framework versions
- Transformers 4.41.1
- Pytorch 2.3.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
tjake/llama2-7b-chat-hf-jlama-Q4 | tjake | 2024-06-22T03:22:27Z | 22 | 1 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"facebook",
"meta",
"pytorch",
"llama-2",
"conversational",
"en",
"arxiv:2307.09288",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2023-11-06T04:52:53Z | ---
extra_gated_heading: Access Llama 2 on Hugging Face
extra_gated_description: >-
This is a form to enable access to Llama 2 on Hugging Face after you have been
granted access from Meta. Please visit the [Meta website](https://ai.meta.com/resources/models-and-libraries/llama-downloads) and accept our
license terms and acceptable use policy before submitting this form. Requests
will be processed in 1-2 days.
extra_gated_prompt: "**Your Hugging Face account email address MUST match the email you provide on the Meta website, or your request will not be approved.**"
extra_gated_button_content: Submit
extra_gated_fields:
I agree to share my name, email address and username with Meta and confirm that I have already been granted download access on the Meta website: checkbox
language:
- en
pipeline_tag: text-generation
inference: false
tags:
- facebook
- meta
- pytorch
- llama
- llama-2
---
# **Llama 2**
Llama 2 is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the repository for the 7B pretrained model, converted for the Hugging Face Transformers format. Links to other models can be found in the index at the bottom.
## Model Details
*Note: Use of this model is governed by the Meta license. In order to download the model weights and tokenizer, please visit the [website](https://ai.meta.com/resources/models-and-libraries/llama-downloads/) and accept our License before requesting access here.*
Meta developed and publicly released the Llama 2 family of large language models (LLMs), a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. Our fine-tuned LLMs, called Llama-2-Chat, are optimized for dialogue use cases. Llama-2-Chat models outperform open-source chat models on most benchmarks we tested, and in our human evaluations for helpfulness and safety, are on par with some popular closed-source models like ChatGPT and PaLM.
**Model Developers** Meta
**Variations** Llama 2 comes in a range of parameter sizes — 7B, 13B, and 70B — as well as pretrained and fine-tuned variations.
**Input** Models input text only.
**Output** Models generate text only.
**Model Architecture** Llama 2 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align to human preferences for helpfulness and safety.
||Training Data|Params|Content Length|GQA|Tokens|LR|
|---|---|---|---|---|---|---|
|Llama 2|*A new mix of publicly available online data*|7B|4k|✗|2.0T|3.0 x 10<sup>-4</sup>|
|Llama 2|*A new mix of publicly available online data*|13B|4k|✗|2.0T|3.0 x 10<sup>-4</sup>|
|Llama 2|*A new mix of publicly available online data*|70B|4k|✔|2.0T|1.5 x 10<sup>-4</sup>|
*Llama 2 family of models.* Token counts refer to pretraining data only. All models are trained with a global batch-size of 4M tokens. Bigger models - 70B -- use Grouped-Query Attention (GQA) for improved inference scalability.
**Model Dates** Llama 2 was trained between January 2023 and July 2023.
**Status** This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.
**License** A custom commercial license is available at: [https://ai.meta.com/resources/models-and-libraries/llama-downloads/](https://ai.meta.com/resources/models-and-libraries/llama-downloads/)
**Research Paper** ["Llama-2: Open Foundation and Fine-tuned Chat Models"](arxiv.org/abs/2307.09288)
## Intended Use
**Intended Use Cases** Llama 2 is intended for commercial and research use in English. Tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.
To get the expected features and performance for the chat versions, a specific formatting needs to be followed, including the `INST` and `<<SYS>>` tags, `BOS` and `EOS` tokens, and the whitespaces and breaklines in between (we recommend calling `strip()` on inputs to avoid double-spaces). See our reference code in github for details: [`chat_completion`](https://github.com/facebookresearch/llama/blob/main/llama/generation.py#L212).
**Out-of-scope Uses** Use in any manner that violates applicable laws or regulations (including trade compliance laws).Use in languages other than English. Use in any other way that is prohibited by the Acceptable Use Policy and Licensing Agreement for Llama 2.
## Hardware and Software
**Training Factors** We used custom training libraries, Meta's Research Super Cluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.
**Carbon Footprint** Pretraining utilized a cumulative 3.3M GPU hours of computation on hardware of type A100-80GB (TDP of 350-400W). Estimated total emissions were 539 tCO2eq, 100% of which were offset by Meta’s sustainability program.
||Time (GPU hours)|Power Consumption (W)|Carbon Emitted(tCO<sub>2</sub>eq)|
|---|---|---|---|
|Llama 2 7B|184320|400|31.22|
|Llama 2 13B|368640|400|62.44|
|Llama 2 70B|1720320|400|291.42|
|Total|3311616||539.00|
**CO<sub>2</sub> emissions during pretraining.** Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.
## Training Data
**Overview** Llama 2 was pretrained on 2 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over one million new human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.
**Data Freshness** The pretraining data has a cutoff of September 2022, but some tuning data is more recent, up to July 2023.
## Evaluation Results
In this section, we report the results for the Llama 1 and Llama 2 models on standard academic benchmarks.For all the evaluations, we use our internal evaluations library.
|Model|Size|Code|Commonsense Reasoning|World Knowledge|Reading Comprehension|Math|MMLU|BBH|AGI Eval|
|---|---|---|---|---|---|---|---|---|---|
|Llama 1|7B|14.1|60.8|46.2|58.5|6.95|35.1|30.3|23.9|
|Llama 1|13B|18.9|66.1|52.6|62.3|10.9|46.9|37.0|33.9|
|Llama 1|33B|26.0|70.0|58.4|67.6|21.4|57.8|39.8|41.7|
|Llama 1|65B|30.7|70.7|60.5|68.6|30.8|63.4|43.5|47.6|
|Llama 2|7B|16.8|63.9|48.9|61.3|14.6|45.3|32.6|29.3|
|Llama 2|13B|24.5|66.9|55.4|65.8|28.7|54.8|39.4|39.1|
|Llama 2|70B|**37.5**|**71.9**|**63.6**|**69.4**|**35.2**|**68.9**|**51.2**|**54.2**|
**Overall performance on grouped academic benchmarks.** *Code:* We report the average pass@1 scores of our models on HumanEval and MBPP. *Commonsense Reasoning:* We report the average of PIQA, SIQA, HellaSwag, WinoGrande, ARC easy and challenge, OpenBookQA, and CommonsenseQA. We report 7-shot results for CommonSenseQA and 0-shot results for all other benchmarks. *World Knowledge:* We evaluate the 5-shot performance on NaturalQuestions and TriviaQA and report the average. *Reading Comprehension:* For reading comprehension, we report the 0-shot average on SQuAD, QuAC, and BoolQ. *MATH:* We report the average of the GSM8K (8 shot) and MATH (4 shot) benchmarks at top 1.
|||TruthfulQA|Toxigen|
|---|---|---|---|
|Llama 1|7B|27.42|23.00|
|Llama 1|13B|41.74|23.08|
|Llama 1|33B|44.19|22.57|
|Llama 1|65B|48.71|21.77|
|Llama 2|7B|33.29|**21.25**|
|Llama 2|13B|41.86|26.10|
|Llama 2|70B|**50.18**|24.60|
**Evaluation of pretrained LLMs on automatic safety benchmarks.** For TruthfulQA, we present the percentage of generations that are both truthful and informative (the higher the better). For ToxiGen, we present the percentage of toxic generations (the smaller the better).
|||TruthfulQA|Toxigen|
|---|---|---|---|
|Llama-2-Chat|7B|57.04|**0.00**|
|Llama-2-Chat|13B|62.18|**0.00**|
|Llama-2-Chat|70B|**64.14**|0.01|
**Evaluation of fine-tuned LLMs on different safety datasets.** Same metric definitions as above.
## Ethical Considerations and Limitations
Llama 2 is a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Llama 2’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 2, developers should perform safety testing and tuning tailored to their specific applications of the model.
Please see the Responsible Use Guide available at [https://ai.meta.com/llama/responsible-use-guide/](https://ai.meta.com/llama/responsible-use-guide)
## Reporting Issues
Please report any software “bug,” or other problems with the models through one of the following means:
- Reporting issues with the model: [github.com/facebookresearch/llama](http://github.com/facebookresearch/llama)
- Reporting problematic content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)
- Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)
## Llama Model Index
|Model|Llama2|Llama2-hf|Llama2-chat|Llama2-chat-hf|
|---|---|---|---|---|
|7B| [Link](https://huggingface.co/llamaste/Llama-2-7b) | [Link](https://huggingface.co/llamaste/Llama-2-7b-hf) | [Link](https://huggingface.co/llamaste/Llama-2-7b-chat) | [Link](https://huggingface.co/llamaste/Llama-2-7b-chat-hf)|
|13B| [Link](https://huggingface.co/llamaste/Llama-2-13b) | [Link](https://huggingface.co/llamaste/Llama-2-13b-hf) | [Link](https://huggingface.co/llamaste/Llama-2-13b-chat) | [Link](https://huggingface.co/llamaste/Llama-2-13b-hf)|
|70B| [Link](https://huggingface.co/llamaste/Llama-2-70b) | [Link](https://huggingface.co/llamaste/Llama-2-70b-hf) | [Link](https://huggingface.co/llamaste/Llama-2-70b-chat) | [Link](https://huggingface.co/llamaste/Llama-2-70b-hf)| |
Somnuk/distilbert-base-uncased-finetuned-imdb | Somnuk | 2024-06-22T03:07:48Z | 6 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"distilbert",
"fill-mask",
"generated_from_trainer",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | 2024-06-01T10:21:03Z | ---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
model-index:
- name: distilbert-base-uncased-finetuned-imdb
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilbert-base-uncased-finetuned-imdb
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.4891
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.6823 | 1.0 | 157 | 2.5090 |
| 2.5864 | 2.0 | 314 | 2.4501 |
| 2.528 | 3.0 | 471 | 2.4828 |
### Framework versions
- Transformers 4.39.3
- Pytorch 2.3.0
- Datasets 2.19.1
- Tokenizers 0.15.1
|
Rickliou/gemma-medical_qa-Finetune | Rickliou | 2024-06-22T02:55:53Z | 6 | 0 | transformers | [
"transformers",
"safetensors",
"gemma",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-06-22T02:53:18Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
ymoslem/whisper-medium-ga2en-v1.3.1-4k-r | ymoslem | 2024-06-22T02:45:53Z | 28 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"ga",
"en",
"dataset:ymoslem/IWSLT2023-GA-EN",
"dataset:ymoslem/FLEURS-GA-EN",
"dataset:ymoslem/BitesizeIrish-GA-EN",
"dataset:ymoslem/SpokenWords-GA-EN-MTed",
"base_model:openai/whisper-medium",
"base_model:finetune:openai/whisper-medium",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] | automatic-speech-recognition | 2024-06-21T23:50:45Z | ---
language:
- ga
- en
license: apache-2.0
base_model: openai/whisper-medium
tags:
- generated_from_trainer
datasets:
- ymoslem/IWSLT2023-GA-EN
- ymoslem/FLEURS-GA-EN
- ymoslem/BitesizeIrish-GA-EN
- ymoslem/SpokenWords-GA-EN-MTed
metrics:
- bleu
- wer
model-index:
- name: Whisper Medium GA-EN Speech Translation Raw
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: IWSLT-2023, FLEURS, BiteSize, and SpokenWords
type: ymoslem/IWSLT2023-GA-EN
metrics:
- name: Bleu
type: bleu
value: 26.56
- name: Wer
type: wer
value: 76.67717244484467
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Whisper Medium GA-EN Speech Translation Raw
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the IWSLT-2023, FLEURS, BiteSize, and SpokenWords dataset.
It achieves the following results on the evaluation set:
- Loss: 1.5187
- Bleu: 26.56
- Chrf: 46.91
- Wer: 76.6772
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.03
- training_steps: 4000
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Bleu | Chrf | Validation Loss | Wer |
|:-------------:|:------:|:----:|:-----:|:-----:|:---------------:|:--------:|
| 2.5874 | 0.0539 | 100 | 4.9 | 19.49 | 2.1785 | 114.0027 |
| 2.3237 | 0.1079 | 200 | 6.48 | 22.77 | 2.1129 | 151.8235 |
| 2.192 | 0.1618 | 300 | 7.92 | 25.9 | 2.0182 | 148.6718 |
| 1.9861 | 0.2157 | 400 | 10.55 | 28.55 | 1.8607 | 121.0266 |
| 1.8893 | 0.2697 | 500 | 16.68 | 33.64 | 1.8560 | 89.7794 |
| 1.8526 | 0.3236 | 600 | 8.83 | 30.12 | 1.7738 | 166.9968 |
| 1.6537 | 0.3776 | 700 | 10.94 | 33.83 | 1.6781 | 152.2287 |
| 1.7103 | 0.4315 | 800 | 16.9 | 36.4 | 1.6389 | 92.2557 |
| 1.4837 | 0.4854 | 900 | 13.81 | 34.5 | 1.6077 | 124.2233 |
| 1.2784 | 0.5394 | 1000 | 14.79 | 37.53 | 1.6103 | 116.3440 |
| 1.111 | 0.5933 | 1100 | 19.31 | 39.0 | 1.5579 | 93.6965 |
| 1.167 | 0.6472 | 1200 | 20.88 | 41.7 | 1.5210 | 91.6704 |
| 1.2217 | 0.7012 | 1300 | 21.29 | 41.72 | 1.4719 | 84.9167 |
| 1.0613 | 0.7551 | 1400 | 28.3 | 44.37 | 1.4663 | 67.1319 |
| 0.9256 | 0.8091 | 1500 | 27.5 | 45.59 | 1.4258 | 68.7078 |
| 0.8023 | 0.8630 | 1600 | 27.1 | 46.27 | 1.4027 | 72.7600 |
| 0.8327 | 0.9169 | 1700 | 27.03 | 46.19 | 1.3784 | 73.0302 |
| 0.7019 | 0.9709 | 1800 | 28.91 | 46.34 | 1.4127 | 67.4921 |
| 0.2681 | 1.0248 | 1900 | 28.53 | 47.12 | 1.3955 | 68.3026 |
| 0.2659 | 1.0787 | 2000 | 28.37 | 45.85 | 1.4194 | 68.1225 |
| 0.4202 | 1.1327 | 2100 | 1.5449| 27.53 | 44.0 | 69.8784 |
| 0.4212 | 1.1866 | 2200 | 1.6060| 25.89 | 43.05 | 70.1036 |
| 0.4124 | 1.2406 | 2300 | 1.6167| 24.31 | 41.55 | 75.8217 |
| 0.4696 | 1.2945 | 2400 | 1.5904| 21.79 | 41.86 | 85.0968 |
| 0.4018 | 1.3484 | 2500 | 1.6300| 25.36 | 43.45 | 76.4070 |
| 0.4549 | 1.4024 | 2600 | 1.5540| 26.06 | 44.27 | 71.9946 |
| 0.4018 | 1.4563 | 2700 | 1.5721| 26.22 | 45.42 | 72.9851 |
| 0.3534 | 1.5102 | 2800 | 1.5488| 23.65 | 44.43 | 80.0090 |
| 0.2907 | 1.5642 | 2900 | 1.5494| 24.04 | 42.57 | 75.3715 |
| 0.3117 | 1.6181 | 3000 | 1.5691| 28.27 | 45.06 | 67.2670 |
| 0.3379 | 1.6721 | 3100 | 1.4951| 30.52 | 47.42 | 65.5561 |
| 0.3686 | 1.7260 | 3200 | 1.5010| 30.7 | 48.13 | 64.8357 |
| 0.2855 | 1.7799 | 3300 | 1.5197| 27.19 | 46.47 | 74.5610 |
| 0.2919 | 1.8339 | 3400 | 1.4974| 31.39 | 48.56 | 63.5299 |
| 0.2582 | 1.8878 | 3500 | 1.4779| 30.18 | 48.54 | 64.9257 |
| 0.2523 | 1.9417 | 3600 | 1.4835| 30.29 | 47.07 | 66.6367 |
| 0.2005 | 1.9957 | 3700 | 1.4682| 29.89 | 47.95 | 68.2125 |
| 0.0617 | 2.0496 | 3800 | 1.5221| 29.49 | 47.1 | 67.6272 |
| 0.0661 | 2.1036 | 3900 | 1.5142| 26.93 | 46.91 | 75.8217 |
| 0.0609 | 2.1575 | 4000 | 1.5187| 26.56 | 46.91 | 76.6772 |
### Framework versions
- Transformers 4.41.2
- Pytorch 2.2.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
|
ZainabNac/Translation-Darija-to-English | ZainabNac | 2024-06-22T02:26:51Z | 1 | 0 | null | [
"license:apache-2.0",
"region:us"
] | null | 2024-06-18T17:54:14Z | ---
license: apache-2.0
---
Ce modèle est pré-entraîné pour effectuer la traduction automatique neuronale entre le dialecte marocain et l'anglais.
Il intégre les embeddings d'un modèle de langue (BERT) dans une architecture d'encodeur-décodeur pour améliorer la qualité de la traduction entre ces deux langues.
L'entraînement de ce modèle est inspiré par cet article :
Dans cet entraînement, nous avons utilisé différentes versions de BERT pour l'anglais et DarijaBERT pour le dialecte marocain |
magnifi/parser_user_v8-0621-epoch8-0.002_nosystemprompt | magnifi | 2024-06-22T02:17:01Z | 6 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"conversational",
"en",
"base_model:unsloth/Phi-3-mini-4k-instruct-bnb-4bit",
"base_model:finetune:unsloth/Phi-3-mini-4k-instruct-bnb-4bit",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-06-22T02:15:00Z | ---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- trl
base_model: unsloth/Phi-3-mini-4k-instruct-bnb-4bit
---
# Uploaded model
- **Developed by:** magnifi
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Phi-3-mini-4k-instruct-bnb-4bit
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
M2LabOrg/whisper-small-lv | M2LabOrg | 2024-06-22T02:08:16Z | 13 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"lv",
"dataset:mozilla-foundation/common_voice_11_0",
"base_model:openai/whisper-small",
"base_model:finetune:openai/whisper-small",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] | automatic-speech-recognition | 2024-06-21T07:58:20Z | ---
language:
- lv
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
model-index:
- name: Whisper small lv - Michel Mesquita
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 11.0
type: mozilla-foundation/common_voice_11_0
config: lv
split: None
args: 'config: lv, split: test'
metrics:
- name: Wer
type: wer
value: 35.363774156877604
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Whisper small lv - Michel Mesquita
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5957
- Wer: 35.3638
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-------:|:----:|:---------------:|:-------:|
| 0.0043 | 12.9870 | 1000 | 0.4936 | 36.7753 |
| 0.0005 | 25.9740 | 2000 | 0.5587 | 35.4585 |
| 0.0003 | 38.9610 | 3000 | 0.5855 | 35.3448 |
| 0.0002 | 51.9481 | 4000 | 0.5957 | 35.3638 |
### Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
|
Local-Novel-LLM-project/Yosegi-2 | Local-Novel-LLM-project | 2024-06-22T02:02:57Z | 38 | 2 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"mergekit",
"merge",
"arxiv:2306.01708",
"base_model:meta-math/MetaMath-Mistral-7B",
"base_model:merge:meta-math/MetaMath-Mistral-7B",
"base_model:mistralai/Mistral-7B-v0.3",
"base_model:merge:mistralai/Mistral-7B-v0.3",
"base_model:uukuguy/speechless-zephyr-code-functionary-7b",
"base_model:merge:uukuguy/speechless-zephyr-code-functionary-7b",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-06-22T01:59:07Z | ---
base_model:
- mistralai/Mistral-7B-v0.3
- meta-math/MetaMath-Mistral-7B
- uukuguy/speechless-zephyr-code-functionary-7b
library_name: transformers
tags:
- mergekit
- merge
---
# Yosegi-2
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using ./Yosegi-0601 as a base.
### Models Merged
The following models were included in the merge:
* [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3)
* [meta-math/MetaMath-Mistral-7B](https://huggingface.co/meta-math/MetaMath-Mistral-7B)
* ./Ninja-v1-RP-expressive-v2-LoRA
* [uukuguy/speechless-zephyr-code-functionary-7b](https://huggingface.co/uukuguy/speechless-zephyr-code-functionary-7b)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
base_model: ./Yosegi-0601
dtype: bfloat16
merge_method: ties
parameters:
int8_mask: 1.0
normalize: 0.0
slices:
- sources:
- layer_range: [0, 2]
model: mistralai/Mistral-7B-v0.3
parameters:
density:
- filter: self_attn
value: 1.0
- filter: mlp
value: 0.9895701336232673
- value: 1.0
weight:
- filter: self_attn
value: 0.5057237984975562
- filter: mlp
value: 0.36247235528151495
- value: 0.0076810835717692014
- layer_range: [0, 2]
model: meta-math/MetaMath-Mistral-7B
parameters:
density:
- filter: self_attn
value: 1.0
- filter: mlp
value: 1.0
- value: 0.8239779346577963
weight:
- filter: self_attn
value: 0.27499287617186813
- filter: mlp
value: 0.10579959634086915
- value: 0.14502290477239704
- layer_range: [0, 2]
model: uukuguy/speechless-zephyr-code-functionary-7b
parameters:
density:
- filter: self_attn
value: 1.0
- filter: mlp
value: 0.9654867628269999
- value: 0.9584724004158125
weight:
- filter: self_attn
value: 0.059719404899177556
- filter: mlp
value: 0.1299695859327612
- value: 0.18821871354400985
- layer_range: [0, 2]
model: ./Ninja-v1-RP-expressive-v2-LoRA
parameters:
density:
- filter: self_attn
value: 0.9322987005873715
- filter: mlp
value: 0.8119693860979944
- value: 0.7800996941956229
weight:
- filter: self_attn
value: 0.14989333734000856
- filter: mlp
value: 0.20525182711733667
- value: 0.0743540962371737
- layer_range: [0, 2]
model: ./Yosegi-0601
- sources:
- layer_range: [2, 4]
model: mistralai/Mistral-7B-v0.3
parameters:
density:
- filter: self_attn
value: 0.6361163471256639
- filter: mlp
value: 0.9983948965135213
- value: 1.0
weight:
- filter: self_attn
value: 0.2433049522842103
- filter: mlp
value: 0.11537153133586801
- value: 0.11236945502439658
- layer_range: [2, 4]
model: meta-math/MetaMath-Mistral-7B
parameters:
density:
- filter: self_attn
value: 1.0
- filter: mlp
value: 1.0
- value: 1.0
weight:
- filter: self_attn
value: 0.13087986863180992
- filter: mlp
value: 0.05060452788200992
- value: 0.029882383396623725
- layer_range: [2, 4]
model: uukuguy/speechless-zephyr-code-functionary-7b
parameters:
density:
- filter: self_attn
value: 0.9938109261305853
- filter: mlp
value: 0.709432587913349
- value: 1.0
weight:
- filter: self_attn
value: 0.15343343058938377
- filter: mlp
value: 0.4105917936868785
- value: 0.6078632204623161
- layer_range: [2, 4]
model: ./Ninja-v1-RP-expressive-v2-LoRA
parameters:
density:
- filter: self_attn
value: 1.0
- filter: mlp
value: 1.0
- value: 0.9634269234020544
weight:
- filter: self_attn
value: 0.03750763360681478
- filter: mlp
value: 0.29089122858987404
- value: 0.3408085857388722
- layer_range: [2, 4]
model: ./Yosegi-0601
- sources:
- layer_range: [4, 6]
model: mistralai/Mistral-7B-v0.3
parameters:
density:
- filter: self_attn
value: 0.8057109303418598
- filter: mlp
value: 0.9954520808628292
- value: 1.0
weight:
- filter: self_attn
value: 0.02598285706585618
- filter: mlp
value: 0.06661629726622949
- value: 0.1285191000066376
- layer_range: [4, 6]
model: meta-math/MetaMath-Mistral-7B
parameters:
density:
- filter: self_attn
value: 0.9112825916608848
- filter: mlp
value: 0.9322557507910056
- value: 1.0
weight:
- filter: self_attn
value: 0.18823564379986454
- filter: mlp
value: 0.4552822441636322
- value: 0.5120525709221785
- layer_range: [4, 6]
model: uukuguy/speechless-zephyr-code-functionary-7b
parameters:
density:
- filter: self_attn
value: 0.9869122169774399
- filter: mlp
value: 1.0
- value: 0.9751291459565757
weight:
- filter: self_attn
value: 0.00493134813843582
- filter: mlp
value: 0.3008979965262413
- value: 0.2528466849993097
- layer_range: [4, 6]
model: ./Ninja-v1-RP-expressive-v2-LoRA
parameters:
density:
- filter: self_attn
value: 1.0
- filter: mlp
value: 0.8956512783019246
- value: 1.0
weight:
- filter: self_attn
value: 0.4197408619693966
- filter: mlp
value: 0.1448902874618845
- value: 0.5196932662212128
- layer_range: [4, 6]
model: ./Yosegi-0601
- sources:
- layer_range: [6, 8]
model: mistralai/Mistral-7B-v0.3
parameters:
density:
- filter: self_attn
value: 1.0
- filter: mlp
value: 1.0
- value: 1.0
weight:
- filter: self_attn
value: 0.05321377226808306
- filter: mlp
value: 0.0482589904702303
- value: 0.433407006546336
- layer_range: [6, 8]
model: meta-math/MetaMath-Mistral-7B
parameters:
density:
- filter: self_attn
value: 0.8300482882633113
- filter: mlp
value: 0.8951636861593875
- value: 1.0
weight:
- filter: self_attn
value: 0.35952608658046414
- filter: mlp
value: 0.17385333183950857
- value: 0.6366514725970246
- layer_range: [6, 8]
model: uukuguy/speechless-zephyr-code-functionary-7b
parameters:
density:
- filter: self_attn
value: 0.7848308077099464
- filter: mlp
value: 0.869549457974157
- value: 1.0
weight:
- filter: self_attn
value: 0.12433943050311849
- filter: mlp
value: 0.3065832590226165
- value: 0.33138948726149514
- layer_range: [6, 8]
model: ./Ninja-v1-RP-expressive-v2-LoRA
parameters:
density:
- filter: self_attn
value: 1.0
- filter: mlp
value: 1.0
- value: 1.0
weight:
- filter: self_attn
value: 0.11885967308786714
- filter: mlp
value: 0.29125668567121127
- value: 0.19251901269486088
- layer_range: [6, 8]
model: ./Yosegi-0601
- sources:
- layer_range: [8, 10]
model: mistralai/Mistral-7B-v0.3
parameters:
density:
- filter: self_attn
value: 1.0
- filter: mlp
value: 0.9429625513013793
- value: 1.0
weight:
- filter: self_attn
value: 0.4085396076816443
- filter: mlp
value: 0.038473657720644636
- value: 0.35014489493395495
- layer_range: [8, 10]
model: meta-math/MetaMath-Mistral-7B
parameters:
density:
- filter: self_attn
value: 1.0
- filter: mlp
value: 1.0
- value: 1.0
weight:
- filter: self_attn
value: 0.26957216810533163
- filter: mlp
value: 0.2393300696241166
- value: 0.4735322427351712
- layer_range: [8, 10]
model: uukuguy/speechless-zephyr-code-functionary-7b
parameters:
density:
- filter: self_attn
value: 0.8594757954447017
- filter: mlp
value: 1.0
- value: 1.0
weight:
- filter: self_attn
value: 0.26101395702355007
- filter: mlp
value: 0.3147672140145126
- value: 0.11658182776184756
- layer_range: [8, 10]
model: ./Ninja-v1-RP-expressive-v2-LoRA
parameters:
density:
- filter: self_attn
value: 1.0
- filter: mlp
value: 0.6948062341711919
- value: 0.9312401427737346
weight:
- filter: self_attn
value: 0.1987774487170517
- filter: mlp
value: 0.5628384475763534
- value: 0.2765378221890683
- layer_range: [8, 10]
model: ./Yosegi-0601
- sources:
- layer_range: [10, 12]
model: mistralai/Mistral-7B-v0.3
parameters:
density:
- filter: self_attn
value: 1.0
- filter: mlp
value: 0.8230035654228713
- value: 1.0
weight:
- filter: self_attn
value: 0.1741591536775035
- filter: mlp
value: 0.30563583223301516
- value: 0.2060419023239155
- layer_range: [10, 12]
model: meta-math/MetaMath-Mistral-7B
parameters:
density:
- filter: self_attn
value: 1.0
- filter: mlp
value: 0.9991063013557119
- value: 1.0
weight:
- filter: self_attn
value: 0.1470996125766866
- filter: mlp
value: 0.06646481892400827
- value: 0.2645489609472036
- layer_range: [10, 12]
model: uukuguy/speechless-zephyr-code-functionary-7b
parameters:
density:
- filter: self_attn
value: 0.6812899560643833
- filter: mlp
value: 0.9083104648631823
- value: 0.9730062683598184
weight:
- filter: self_attn
value: 0.14278507832578724
- filter: mlp
value: 0.3475945971407978
- value: 0.40266546962595284
- layer_range: [10, 12]
model: ./Ninja-v1-RP-expressive-v2-LoRA
parameters:
density:
- filter: self_attn
value: 0.7047231879232164
- filter: mlp
value: 0.9148432633716144
- value: 1.0
weight:
- filter: self_attn
value: 0.15341559366405985
- filter: mlp
value: 0.20047704006010095
- value: 0.17364445581398172
- layer_range: [10, 12]
model: ./Yosegi-0601
- sources:
- layer_range: [12, 14]
model: mistralai/Mistral-7B-v0.3
parameters:
density:
- filter: self_attn
value: 0.6974090973508299
- filter: mlp
value: 1.0
- value: 0.9553573565285324
weight:
- filter: self_attn
value: 0.03614401712451334
- filter: mlp
value: 0.1287785039219736
- value: 0.3780545754310749
- layer_range: [12, 14]
model: meta-math/MetaMath-Mistral-7B
parameters:
density:
- filter: self_attn
value: 0.7857328784783159
- filter: mlp
value: 1.0
- value: 0.6631303877423032
weight:
- filter: self_attn
value: 0.21728574423632604
- filter: mlp
value: 0.22813107248290188
- value: 0.1435266378249425
- layer_range: [12, 14]
model: uukuguy/speechless-zephyr-code-functionary-7b
parameters:
density:
- filter: self_attn
value: 0.7579910864422339
- filter: mlp
value: 1.0
- value: 1.0
weight:
- filter: self_attn
value: 0.21526786827735228
- filter: mlp
value: 0.19769619474642783
- value: 0.49420458585638627
- layer_range: [12, 14]
model: ./Ninja-v1-RP-expressive-v2-LoRA
parameters:
density:
- filter: self_attn
value: 0.8379590665264793
- filter: mlp
value: 1.0
- value: 0.6778673543559375
weight:
- filter: self_attn
value: 0.060679858649663874
- filter: mlp
value: 0.17248738428562518
- value: 0.05145640258269078
- layer_range: [12, 14]
model: ./Yosegi-0601
- sources:
- layer_range: [14, 16]
model: mistralai/Mistral-7B-v0.3
parameters:
density:
- filter: self_attn
value: 1.0
- filter: mlp
value: 0.8193296716327286
- value: 0.709644132681917
weight:
- filter: self_attn
value: 0.09821428505487592
- filter: mlp
value: 0.0039875777021436964
- value: 0.27550746634944184
- layer_range: [14, 16]
model: meta-math/MetaMath-Mistral-7B
parameters:
density:
- filter: self_attn
value: 0.9420135087156387
- filter: mlp
value: 1.0
- value: 0.9478569230341948
weight:
- filter: self_attn
value: 0.32640822225239857
- filter: mlp
value: 0.28189746971019747
- value: 0.09777040841174603
- layer_range: [14, 16]
model: uukuguy/speechless-zephyr-code-functionary-7b
parameters:
density:
- filter: self_attn
value: 0.9811539353914964
- filter: mlp
value: 1.0
- value: 0.9947034500579488
weight:
- filter: self_attn
value: 0.015308461456516246
- filter: mlp
value: 0.0018966958379955934
- value: 0.24275389952300747
- layer_range: [14, 16]
model: ./Ninja-v1-RP-expressive-v2-LoRA
parameters:
density:
- filter: self_attn
value: 0.9022355771447704
- filter: mlp
value: 1.0
- value: 1.0
weight:
- filter: self_attn
value: 0.03331841447575224
- filter: mlp
value: 0.03561712850019841
- value: 0.16096143804589919
- layer_range: [14, 16]
model: ./Yosegi-0601
- sources:
- layer_range: [16, 18]
model: mistralai/Mistral-7B-v0.3
parameters:
density:
- filter: self_attn
value: 0.8813466618200871
- filter: mlp
value: 1.0
- value: 1.0
weight:
- filter: self_attn
value: 0.20435001101909528
- filter: mlp
value: 0.1516594727144469
- value: 0.2269819409999868
- layer_range: [16, 18]
model: meta-math/MetaMath-Mistral-7B
parameters:
density:
- filter: self_attn
value: 1.0
- filter: mlp
value: 1.0
- value: 0.8113796412034742
weight:
- filter: self_attn
value: 0.23760349395229585
- filter: mlp
value: 0.1725436279774783
- value: 0.5818814139457673
- layer_range: [16, 18]
model: uukuguy/speechless-zephyr-code-functionary-7b
parameters:
density:
- filter: self_attn
value: 1.0
- filter: mlp
value: 0.9307369835995082
- value: 1.0
weight:
- filter: self_attn
value: 0.0673898519051937
- filter: mlp
value: 0.049368399457210624
- value: 0.2621269048339309
- layer_range: [16, 18]
model: ./Ninja-v1-RP-expressive-v2-LoRA
parameters:
density:
- filter: self_attn
value: 0.8219541044757637
- filter: mlp
value: 1.0
- value: 1.0
weight:
- filter: self_attn
value: 0.21320061393511042
- filter: mlp
value: 0.09188781867337345
- value: 0.27266490524762327
- layer_range: [16, 18]
model: ./Yosegi-0601
- sources:
- layer_range: [18, 20]
model: mistralai/Mistral-7B-v0.3
parameters:
density:
- filter: self_attn
value: 1.0
- filter: mlp
value: 0.7993530327131696
- value: 1.0
weight:
- filter: self_attn
value: 0.20420262433348008
- filter: mlp
value: 0.43400570066910155
- value: 0.13720822682656159
- layer_range: [18, 20]
model: meta-math/MetaMath-Mistral-7B
parameters:
density:
- filter: self_attn
value: 1.0
- filter: mlp
value: 1.0
- value: 0.7035563346885239
weight:
- filter: self_attn
value: 0.3313523263002212
- filter: mlp
value: 0.356035051194268
- value: 0.4742357680522683
- layer_range: [18, 20]
model: uukuguy/speechless-zephyr-code-functionary-7b
parameters:
density:
- filter: self_attn
value: 1.0
- filter: mlp
value: 1.0
- value: 1.0
weight:
- filter: self_attn
value: 0.2475654838180605
- filter: mlp
value: 0.35095371882044646
- value: 0.18536862919946695
- layer_range: [18, 20]
model: ./Ninja-v1-RP-expressive-v2-LoRA
parameters:
density:
- filter: self_attn
value: 1.0
- filter: mlp
value: 1.0
- value: 1.0
weight:
- filter: self_attn
value: 0.02997204931537696
- filter: mlp
value: 0.4103581291392323
- value: 0.19313933251158066
- layer_range: [18, 20]
model: ./Yosegi-0601
- sources:
- layer_range: [20, 22]
model: mistralai/Mistral-7B-v0.3
parameters:
density:
- filter: self_attn
value: 1.0
- filter: mlp
value: 1.0
- value: 0.5321196166337413
weight:
- filter: self_attn
value: 0.17930537920958298
- filter: mlp
value: 0.07662274511683252
- value: 0.1354315278471591
- layer_range: [20, 22]
model: meta-math/MetaMath-Mistral-7B
parameters:
density:
- filter: self_attn
value: 1.0
- filter: mlp
value: 0.3768803907042144
- value: 1.0
weight:
- filter: self_attn
value: 0.1592147705254305
- filter: mlp
value: 0.18410207999201075
- value: 0.4928015910047033
- layer_range: [20, 22]
model: uukuguy/speechless-zephyr-code-functionary-7b
parameters:
density:
- filter: self_attn
value: 1.0
- filter: mlp
value: 1.0
- value: 1.0
weight:
- filter: self_attn
value: 0.37897278298418885
- filter: mlp
value: 0.0952591073533606
- value: 0.03551732810121447
- layer_range: [20, 22]
model: ./Ninja-v1-RP-expressive-v2-LoRA
parameters:
density:
- filter: self_attn
value: 1.0
- filter: mlp
value: 1.0
- value: 1.0
weight:
- filter: self_attn
value: 0.2682334102128691
- filter: mlp
value: 0.33485781481395227
- value: 0.3395139468281392
- layer_range: [20, 22]
model: ./Yosegi-0601
- sources:
- layer_range: [22, 24]
model: mistralai/Mistral-7B-v0.3
parameters:
density:
- filter: self_attn
value: 1.0
- filter: mlp
value: 0.8002588203446623
- value: 1.0
weight:
- filter: self_attn
value: 0.2549204541625693
- filter: mlp
value: 0.3722418477156178
- value: 0.2410463731352089
- layer_range: [22, 24]
model: meta-math/MetaMath-Mistral-7B
parameters:
density:
- filter: self_attn
value: 0.9220873255898425
- filter: mlp
value: 1.0
- value: 1.0
weight:
- filter: self_attn
value: 0.487455295718532
- filter: mlp
value: 0.40022413917173594
- value: 0.17846009757502157
- layer_range: [22, 24]
model: uukuguy/speechless-zephyr-code-functionary-7b
parameters:
density:
- filter: self_attn
value: 0.7696341317318985
- filter: mlp
value: 1.0
- value: 1.0
weight:
- filter: self_attn
value: 0.011267799816515114
- filter: mlp
value: 0.5320959832591042
- value: 0.17095406531325266
- layer_range: [22, 24]
model: ./Ninja-v1-RP-expressive-v2-LoRA
parameters:
density:
- filter: self_attn
value: 1.0
- filter: mlp
value: 1.0
- value: 1.0
weight:
- filter: self_attn
value: 0.556101646343872
- filter: mlp
value: 0.5470253909079791
- value: 0.13241555469863223
- layer_range: [22, 24]
model: ./Yosegi-0601
- sources:
- layer_range: [24, 26]
model: mistralai/Mistral-7B-v0.3
parameters:
density:
- filter: self_attn
value: 0.8667033674916582
- filter: mlp
value: 1.0
- value: 0.9446091486920749
weight:
- filter: self_attn
value: 0.4134110775513897
- filter: mlp
value: 0.0181822765943834
- value: 0.22797659617038232
- layer_range: [24, 26]
model: meta-math/MetaMath-Mistral-7B
parameters:
density:
- filter: self_attn
value: 1.0
- filter: mlp
value: 0.9839865829690491
- value: 0.8252981103449059
weight:
- filter: self_attn
value: 0.3310295320944009
- filter: mlp
value: 0.05341478458353629
- value: 0.3588847186159219
- layer_range: [24, 26]
model: uukuguy/speechless-zephyr-code-functionary-7b
parameters:
density:
- filter: self_attn
value: 1.0
- filter: mlp
value: 0.8834823812212265
- value: 0.8195593509048733
weight:
- filter: self_attn
value: 0.3778012590489552
- filter: mlp
value: 0.2553204906819882
- value: 0.23250565137970108
- layer_range: [24, 26]
model: ./Ninja-v1-RP-expressive-v2-LoRA
parameters:
density:
- filter: self_attn
value: 1.0
- filter: mlp
value: 0.7731602497153744
- value: 0.8647152680789973
weight:
- filter: self_attn
value: 0.1101209698118704
- filter: mlp
value: 0.2399169741437055
- value: 0.32311925187355206
- layer_range: [24, 26]
model: ./Yosegi-0601
- sources:
- layer_range: [26, 28]
model: mistralai/Mistral-7B-v0.3
parameters:
density:
- filter: self_attn
value: 1.0
- filter: mlp
value: 0.9508674341172941
- value: 1.0
weight:
- filter: self_attn
value: 0.4312865186270921
- filter: mlp
value: 0.28336325917543326
- value: 0.051826325177477234
- layer_range: [26, 28]
model: meta-math/MetaMath-Mistral-7B
parameters:
density:
- filter: self_attn
value: 1.0
- filter: mlp
value: 0.8945725432745376
- value: 1.0
weight:
- filter: self_attn
value: 0.03524133636598346
- filter: mlp
value: 0.21426126710725438
- value: 0.31724116335002545
- layer_range: [26, 28]
model: uukuguy/speechless-zephyr-code-functionary-7b
parameters:
density:
- filter: self_attn
value: 1.0
- filter: mlp
value: 0.7138130384877139
- value: 1.0
weight:
- filter: self_attn
value: 0.04890129864608137
- filter: mlp
value: 0.3324333287494201
- value: 0.11533647335498036
- layer_range: [26, 28]
model: ./Ninja-v1-RP-expressive-v2-LoRA
parameters:
density:
- filter: self_attn
value: 1.0
- filter: mlp
value: 1.0
- value: 0.9200281327001997
weight:
- filter: self_attn
value: 0.300842776105564
- filter: mlp
value: 0.08363140003203932
- value: 0.2538677006866867
- layer_range: [26, 28]
model: ./Yosegi-0601
- sources:
- layer_range: [28, 30]
model: mistralai/Mistral-7B-v0.3
parameters:
density:
- filter: self_attn
value: 1.0
- filter: mlp
value: 0.7116000185808022
- value: 1.0
weight:
- filter: self_attn
value: 0.10977758983122704
- filter: mlp
value: 0.1839207861311269
- value: 0.5426174846632369
- layer_range: [28, 30]
model: meta-math/MetaMath-Mistral-7B
parameters:
density:
- filter: self_attn
value: 1.0
- filter: mlp
value: 0.8412049419861911
- value: 1.0
weight:
- filter: self_attn
value: 0.3517232690814979
- filter: mlp
value: 0.11878679655495025
- value: 0.432611353923264
- layer_range: [28, 30]
model: uukuguy/speechless-zephyr-code-functionary-7b
parameters:
density:
- filter: self_attn
value: 1.0
- filter: mlp
value: 0.7196182744068202
- value: 1.0
weight:
- filter: self_attn
value: 0.29848623969081
- filter: mlp
value: 0.034661358236493495
- value: 0.3438376072572394
- layer_range: [28, 30]
model: ./Ninja-v1-RP-expressive-v2-LoRA
parameters:
density:
- filter: self_attn
value: 1.0
- filter: mlp
value: 1.0
- value: 1.0
weight:
- filter: self_attn
value: 0.051511204430449285
- filter: mlp
value: 0.3617968383178797
- value: 0.2578690795635758
- layer_range: [28, 30]
model: ./Yosegi-0601
- sources:
- layer_range: [30, 32]
model: mistralai/Mistral-7B-v0.3
parameters:
density:
- filter: self_attn
value: 0.7971002248466003
- filter: mlp
value: 0.8931695149333363
- value: 1.0
weight:
- filter: self_attn
value: 0.07401430804790136
- filter: mlp
value: 0.00696466997386886
- value: 0.08295038526296711
- layer_range: [30, 32]
model: meta-math/MetaMath-Mistral-7B
parameters:
density:
- filter: self_attn
value: 1.0
- filter: mlp
value: 0.8158777337631619
- value: 0.8348784699583887
weight:
- filter: self_attn
value: 0.26799125918248423
- filter: mlp
value: 0.08176923813129498
- value: 0.030317330226146508
- layer_range: [30, 32]
model: uukuguy/speechless-zephyr-code-functionary-7b
parameters:
density:
- filter: self_attn
value: 0.8188850632365792
- filter: mlp
value: 0.7463831519693573
- value: 0.6515317051533988
weight:
- filter: self_attn
value: 0.21122007850953434
- filter: mlp
value: 0.1463362342258229
- value: 0.09176704194956312
- layer_range: [30, 32]
model: ./Ninja-v1-RP-expressive-v2-LoRA
parameters:
density:
- filter: self_attn
value: 0.9313941807354906
- filter: mlp
value: 1.0
- value: 1.0
weight:
- filter: self_attn
value: 0.1443680121177074
- filter: mlp
value: 0.08309606396368145
- value: 0.37059044424517035
- layer_range: [30, 32]
model: ./Yosegi-0601
```
|
ctrlg/tulu2-7b_writing-prompts | ctrlg | 2024-06-22T02:02:08Z | 40 | 2 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-06-22T01:54:05Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
powermove72/SharkOgno-7b-Task | powermove72 | 2024-06-22T01:42:34Z | 8 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"powermove72/Shark-1",
"eren23/OGNO-7b-dpo-truthful",
"base_model:eren23/OGNO-7b-dpo-truthful",
"base_model:merge:eren23/OGNO-7b-dpo-truthful",
"base_model:powermove72/Shark-1",
"base_model:merge:powermove72/Shark-1",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-06-22T01:38:27Z | ---
base_model:
- powermove72/Shark-1
- eren23/OGNO-7b-dpo-truthful
tags:
- merge
- mergekit
- lazymergekit
- powermove72/Shark-1
- eren23/OGNO-7b-dpo-truthful
---
# SharkOgno-7b-Task
SharkOgno-7b-Task is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [powermove72/Shark-1](https://huggingface.co/powermove72/Shark-1)
* [eren23/OGNO-7b-dpo-truthful](https://huggingface.co/eren23/OGNO-7b-dpo-truthful)
## 🧩 Configuration
```yaml
models:
- model: powermove72/Shark-1
parameters:
weight: 0.4
- model: eren23/OGNO-7b-dpo-truthful
parameters:
weight: 0.6
merge_method: task_arithmetic
base_model: eren23/OGNO-7b-dpo-truthful
parameters:
normalize: true
tokenizer_source: union
dtype: float16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "powermove72/SharkOgno-7b-Task"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
``` |
MrezaPRZ/codestral_high_quality_sft_bigquery | MrezaPRZ | 2024-06-22T01:38:17Z | 8 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-06-22T01:30:02Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
davidyu2023/Qwen-Qwen1.5-7B-1719020015 | davidyu2023 | 2024-06-22T01:33:43Z | 5 | 0 | peft | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:Qwen/Qwen1.5-7B",
"base_model:adapter:Qwen/Qwen1.5-7B",
"region:us"
] | null | 2024-06-22T01:33:35Z | ---
base_model: Qwen/Qwen1.5-7B
library_name: peft
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.11.1 |
magnifi/parser_user_v8-0621-epoch6-0.002_nosystemprompt | magnifi | 2024-06-22T01:27:39Z | 6 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"conversational",
"en",
"base_model:unsloth/Phi-3-mini-4k-instruct-bnb-4bit",
"base_model:finetune:unsloth/Phi-3-mini-4k-instruct-bnb-4bit",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-06-22T01:25:43Z | ---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- trl
base_model: unsloth/Phi-3-mini-4k-instruct-bnb-4bit
---
# Uploaded model
- **Developed by:** magnifi
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Phi-3-mini-4k-instruct-bnb-4bit
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
EleutherAI/Meta-Llama-3-8B-population-random-standardized-many-random-names | EleutherAI | 2024-06-22T01:11:08Z | 12 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"trl",
"sft",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-06-21T21:16:25Z | ---
library_name: transformers
tags:
- trl
- sft
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
Yuxuan-Qiao/PrismCaptioner-2B | Yuxuan-Qiao | 2024-06-22T00:58:46Z | 0 | 2 | prismcaptioner | [
"prismcaptioner",
"safetensors",
"image-text-to-text",
"dataset:FreedomIntelligence/ALLaVA-4V",
"arxiv:2406.14544",
"license:cc-by-4.0",
"region:us"
] | image-text-to-text | 2024-05-29T06:00:57Z | ---
license: cc-by-4.0
datasets:
- FreedomIntelligence/ALLaVA-4V
pipeline_tag: image-text-to-text
library_name: prismcaptioner
---
<br>
# PrismCaptioner Model Card
**Model details**
PrismCaptioners are open-source captioners with LLaVA architecture finetuned on GPT4V-assisted dataset [ALLaVA](https://huggingface.co/datasets/FreedomIntelligence/ALLaVA-4V). We have released [PrismCaptioner-7B](https://huggingface.co/Yuxuan-Qiao/PrismCaptioner-7B) and [PrismCaptioner-2B](https://huggingface.co/Yuxuan-Qiao/PrismCaptioner-7B).
PrismCaptioner-2B details
- **Vision Backbone:** google/siglip-so400m-patch14-384
- **Language Backbone:** internlm/internlm2-1_8b
- **Dataset:** 1x ALLaVA-Caption-[LAION/VFLAN], 2x Evol-Instruct-GPT4-Turbo-143K
**Paper and codebase for more information:**
[[Paper](https://arxiv.org/abs/2406.14544)] [[Code](https://github.com/SparksJoe/Prism)]
**Intended uses**
- **Perception Module:** The model can be integrated into [Prism](https://github.com/SparksJoe/Prism) as a perception module to solve vision-language task by utilizing an external LLM.
- **Effective Captioner:** The model can produce high-quality captions for given images.
**Model usage**
Clone the [Prism](https://github.com/SparksJoe/Prism) repo and complete the [preparation](https://github.com/SparksJoe/Prism/tree/main?tab=readme-ov-file#preparation). You can use PrismCaptioners following [usage](https://github.com/SparksJoe/Prism/blob/main/README.md#usage) or demo below.
```python
# In the Prism repo folder
from decouple import supported_VLM
model = supported_VLM['prismcaptioner-2b']()
res = model.generate(['assets/case1.png', 'Given the image below, please provide a detailed description of what you see.'])
``` |
PhillipGuo/hp-lat-llama-PCA-epsilon6.0-pgd_layer8-def_layer8_9_10_11_12_13_14-wikitext-fullrank-71 | PhillipGuo | 2024-06-22T00:58:32Z | 8 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-06-22T00:56:03Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
bobbyw/deberta-v3-large_v3_relationships | bobbyw | 2024-06-22T00:51:36Z | 16 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"deberta-v2",
"text-classification",
"generated_from_trainer",
"base_model:bobbyw/deberta-v3-large_v3_relationships",
"base_model:finetune:bobbyw/deberta-v3-large_v3_relationships",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2024-06-13T19:19:11Z | ---
license: mit
base_model: bobbyw/deberta-v3-large_v3_relationships
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: deberta-v3-large_v3_relationships
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# deberta-v3-large_v3_relationships
This model is a fine-tuned version of [bobbyw/deberta-v3-large_v3_relationships](https://huggingface.co/bobbyw/deberta-v3-large_v3_relationships) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0124
- Accuracy: 0.0038
- F1: 0.0038
- Precision: 0.0019
- Recall: 0.4242
- Learning Rate: 0.002
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-06
- train_batch_size: 3
- eval_batch_size: 3
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- num_epochs: 8
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Rate |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|:-----:|
| No log | 1.0 | 382 | 0.0109 | 0.0027 | 0.0046 | 0.0023 | 0.5152 | 0.002 |
| 0.0043 | 2.0 | 764 | 0.0106 | 0.0026 | 0.0046 | 0.0023 | 0.5152 | 0.002 |
| 0.0041 | 3.0 | 1146 | 0.0115 | 0.0028 | 0.0051 | 0.0026 | 0.5758 | 0.002 |
| 0.004 | 4.0 | 1528 | 0.0132 | 0.0031 | 0.0048 | 0.0024 | 0.5455 | 0.002 |
| 0.004 | 5.0 | 1910 | 0.0140 | 0.0032 | 0.0046 | 0.0023 | 0.5152 | 0.002 |
| 0.0043 | 6.0 | 2292 | 0.0116 | 0.0032 | 0.0046 | 0.0023 | 0.5152 | 0.002 |
| 0.0044 | 7.0 | 2674 | 0.0129 | 0.0027 | 0.0043 | 0.0022 | 0.4848 | 0.002 |
| 0.0038 | 8.0 | 3056 | 0.0124 | 0.0038 | 0.0038 | 0.0019 | 0.4242 | 0.002 |
### Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
|
mlx-community/instruction-pretrain-finance-Llama3-8B-4bit | mlx-community | 2024-06-22T00:40:24Z | 14 | 2 | mlx | [
"mlx",
"safetensors",
"llama",
"finance",
"en",
"dataset:Open-Orca/OpenOrca",
"dataset:GAIR/lima",
"dataset:WizardLM/WizardLM_evol_instruct_V2_196k",
"arxiv:2406.14491",
"license:llama3",
"region:us"
] | null | 2024-06-21T13:21:15Z | ---
language:
- en
license: llama3
tags:
- finance
- mlx
datasets:
- Open-Orca/OpenOrca
- GAIR/lima
- WizardLM/WizardLM_evol_instruct_V2_196k
---
# mlx-community/instruction-pretrain-finance-Llama3-8B-4bit
The Model [mlx-community/instruction-pretrain-finance-Llama3-8B-4bit](https://huggingface.co/mlx-community/instruction-pretrain-finance-Llama3-8B-4bit) was converted to MLX format from [instruction-pretrain/finance-Llama3-8B](https://huggingface.co/instruction-pretrain/finance-Llama3-8B) using mlx-lm version **0.14.3**. Original paper: [Instruction Pre-Training: Language Models are Supervised Multitask Learners](https://huggingface.co/papers/2406.14491)
## Use with mlx
```bash
pip install mlx-lm
```
```python
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/instruction-pretrain-finance-Llama3-8B-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```
|
mlx-community/instruction-pretrain-instruction-synthesizer | mlx-community | 2024-06-22T00:39:50Z | 7 | 4 | mlx | [
"mlx",
"safetensors",
"mistral",
"en",
"dataset:instruction-pretrain/ft-instruction-synthesizer-collection",
"arxiv:2406.14491",
"license:apache-2.0",
"region:us"
] | null | 2024-06-21T16:32:58Z | ---
datasets:
- instruction-pretrain/ft-instruction-synthesizer-collection
language:
- en
license: apache-2.0
tags:
- mlx
---
# mlx-community/instruction-pretrain-instruction-synthesizer
The Model [mlx-community/instruction-pretrain-instruction-synthesizer](https://huggingface.co/mlx-community/instruction-pretrain-instruction-synthesizer) was converted to MLX format from [instruction-pretrain/instruction-synthesizer](https://huggingface.co/instruction-pretrain/instruction-synthesizer) using mlx-lm version **0.14.3**. Original paper: [Instruction Pre-Training: Language Models are Supervised Multitask Learners](https://huggingface.co/papers/2406.14491)
## Use with mlx
```bash
pip install mlx-lm
```
```python
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/instruction-pretrain-instruction-synthesizer")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```
|
bartowski/tabula-8b-GGUF | bartowski | 2024-06-22T00:25:14Z | 184 | 2 | null | [
"gguf",
"text-generation",
"en",
"dataset:jpgard/t4-full",
"license:llama3",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-06-21T23:55:45Z | ---
license: llama3
datasets:
- jpgard/t4-full
language:
- en
quantized_by: bartowski
pipeline_tag: text-generation
---
## Llamacpp imatrix Quantizations of tabula-8b
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b3197">b3197</a> for quantization.
Original model: https://huggingface.co/mlfoundations/tabula-8b
All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
## Prompt format
No chat template specified so default is used. This may be incorrect, check original model card for details.
```
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Description |
| -------- | ---------- | --------- | ----------- |
| [tabula-8b-Q8_0_L.gguf](https://huggingface.co/bartowski/tabula-8b-GGUF/blob/main/tabula-8b-Q8_1.gguf) | Q8_0_L | 9.52GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. Extremely high quality, generally unneeded but max available quant. |
| [tabula-8b-Q8_0.gguf](https://huggingface.co/bartowski/tabula-8b-GGUF/blob/main/tabula-8b-Q8_0.gguf) | Q8_0 | 8.54GB | Extremely high quality, generally unneeded but max available quant. |
| [tabula-8b-Q6_K_L.gguf](https://huggingface.co/bartowski/tabula-8b-GGUF/blob/main/tabula-8b-Q6_K_L.gguf) | Q6_K_L | 7.83GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. Very high quality, near perfect, *recommended*. |
| [tabula-8b-Q6_K.gguf](https://huggingface.co/bartowski/tabula-8b-GGUF/blob/main/tabula-8b-Q6_K.gguf) | Q6_K | 6.59GB | Very high quality, near perfect, *recommended*. |
| [tabula-8b-Q5_K_L.gguf](https://huggingface.co/bartowski/tabula-8b-GGUF/blob/main/tabula-8b-Q5_K_L.gguf) | Q5_K_L | 7.04GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. High quality, *recommended*. |
| [tabula-8b-Q5_K_M.gguf](https://huggingface.co/bartowski/tabula-8b-GGUF/blob/main/tabula-8b-Q5_K_M.gguf) | Q5_K_M | 5.73GB | High quality, *recommended*. |
| [tabula-8b-Q5_K_S.gguf](https://huggingface.co/bartowski/tabula-8b-GGUF/blob/main/tabula-8b-Q5_K_S.gguf) | Q5_K_S | 5.59GB | High quality, *recommended*. |
| [tabula-8b-Q4_K_L.gguf](https://huggingface.co/bartowski/tabula-8b-GGUF/blob/main/tabula-8b-Q4_K_L.gguf) | Q4_K_L | 6.29GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. Good quality, uses about 4.83 bits per weight, *recommended*. |
| [tabula-8b-Q4_K_M.gguf](https://huggingface.co/bartowski/tabula-8b-GGUF/blob/main/tabula-8b-Q4_K_M.gguf) | Q4_K_M | 4.92GB | Good quality, uses about 4.83 bits per weight, *recommended*. |
| [tabula-8b-Q4_K_S.gguf](https://huggingface.co/bartowski/tabula-8b-GGUF/blob/main/tabula-8b-Q4_K_S.gguf) | Q4_K_S | 4.69GB | Slightly lower quality with more space savings, *recommended*. |
| [tabula-8b-IQ4_XS.gguf](https://huggingface.co/bartowski/tabula-8b-GGUF/blob/main/tabula-8b-IQ4_XS.gguf) | IQ4_XS | 4.44GB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [tabula-8b-Q3_K_XL.gguf](https://huggingface.co/bartowski/tabula-8b-GGUF//main/tabula-8b-Q3_K_XL.gguf) | Q3_K_XL | | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. Lower quality but usable, good for low RAM availability. |
| [tabula-8b-Q3_K_L.gguf](https://huggingface.co/bartowski/tabula-8b-GGUF/blob/main/tabula-8b-Q3_K_L.gguf) | Q3_K_L | 4.32GB | Lower quality but usable, good for low RAM availability. |
| [tabula-8b-Q3_K_M.gguf](https://huggingface.co/bartowski/tabula-8b-GGUF/blob/main/tabula-8b-Q3_K_M.gguf) | Q3_K_M | 4.01GB | Even lower quality. |
| [tabula-8b-IQ3_M.gguf](https://huggingface.co/bartowski/tabula-8b-GGUF/blob/main/tabula-8b-IQ3_M.gguf) | IQ3_M | 3.78GB | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [tabula-8b-Q3_K_S.gguf](https://huggingface.co/bartowski/tabula-8b-GGUF/blob/main/tabula-8b-Q3_K_S.gguf) | Q3_K_S | 3.66GB | Low quality, not recommended. |
| [tabula-8b-IQ3_XS.gguf](https://huggingface.co/bartowski/tabula-8b-GGUF/blob/main/tabula-8b-IQ3_XS.gguf) | IQ3_XS | 3.51GB | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [tabula-8b-IQ3_XXS.gguf](https://huggingface.co/bartowski/tabula-8b-GGUF/blob/main/tabula-8b-IQ3_XXS.gguf) | IQ3_XXS | 3.27GB | Lower quality, new method with decent performance, comparable to Q3 quants. |
| [tabula-8b-Q2_K.gguf](https://huggingface.co/bartowski/tabula-8b-GGUF/blob/main/tabula-8b-Q2_K.gguf) | Q2_K | 3.17GB | Very low quality but surprisingly usable. |
| [tabula-8b-IQ2_M.gguf](https://huggingface.co/bartowski/tabula-8b-GGUF/blob/main/tabula-8b-IQ2_M.gguf) | IQ2_M | 2.94GB | Very low quality, uses SOTA techniques to also be surprisingly usable. |
| [tabula-8b-IQ2_S.gguf](https://huggingface.co/bartowski/tabula-8b-GGUF/blob/main/tabula-8b-IQ2_S.gguf) | IQ2_S | 2.75GB | Very low quality, uses SOTA techniques to be usable. |
| [tabula-8b-IQ2_XS.gguf](https://huggingface.co/bartowski/tabula-8b-GGUF/blob/main/tabula-8b-IQ2_XS.gguf) | IQ2_XS | 2.60GB | Very low quality, uses SOTA techniques to be usable. |
## Downloading using huggingface-cli
First, make sure you have hugginface-cli installed:
```
pip install -U "huggingface_hub[cli]"
```
Then, you can target the specific file you want:
```
huggingface-cli download bartowski/tabula-8b-GGUF --include "tabula-8b-Q4_K_M.gguf" --local-dir ./
```
If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
```
huggingface-cli download bartowski/tabula-8b-GGUF --include "tabula-8b-Q8_0.gguf/*" --local-dir tabula-8b-Q8_0
```
You can either specify a new local-dir (tabula-8b-Q8_0) or download them all in place (./)
## Which file should I choose?
A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9)
The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.
If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.
If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.
Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.
If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.
If you want to get more into the weeds, you can check out this extremely useful feature chart:
[llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix)
But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.
These I-quants can also be used on CPU and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
The I-quants are *not* compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm.
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
|
bendavis78/dolphin-2.7-mixtral-8x7b-3.5bpw-h6-exl2-Q8_0-GGUF | bendavis78 | 2024-06-22T00:22:55Z | 11 | 0 | null | [
"gguf",
"llama-cpp",
"gguf-my-repo",
"en",
"dataset:ehartford/dolphin",
"dataset:jondurbin/airoboros-2.2.1",
"dataset:ehartford/dolphin-coder",
"dataset:teknium/openhermes",
"dataset:ise-uiuc/Magicoder-OSS-Instruct-75K",
"dataset:ise-uiuc/Magicoder-Evol-Instruct-110K",
"dataset:LDJnr/Capybara",
"base_model:LoneStriker/dolphin-2.7-mixtral-8x7b-3.5bpw-h6-exl2",
"base_model:quantized:LoneStriker/dolphin-2.7-mixtral-8x7b-3.5bpw-h6-exl2",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2024-06-22T00:22:53Z | ---
base_model: LoneStriker/dolphin-2.7-mixtral-8x7b-3.5bpw-h6-exl2
datasets:
- ehartford/dolphin
- jondurbin/airoboros-2.2.1
- ehartford/dolphin-coder
- teknium/openhermes
- ise-uiuc/Magicoder-OSS-Instruct-75K
- ise-uiuc/Magicoder-Evol-Instruct-110K
- LDJnr/Capybara
language:
- en
license: apache-2.0
tags:
- llama-cpp
- gguf-my-repo
---
# bendavis78/dolphin-2.7-mixtral-8x7b-3.5bpw-h6-exl2-Q8_0-GGUF
This model was converted to GGUF format from [`LoneStriker/dolphin-2.7-mixtral-8x7b-3.5bpw-h6-exl2`](https://huggingface.co/LoneStriker/dolphin-2.7-mixtral-8x7b-3.5bpw-h6-exl2) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/LoneStriker/dolphin-2.7-mixtral-8x7b-3.5bpw-h6-exl2) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo bendavis78/dolphin-2.7-mixtral-8x7b-3.5bpw-h6-exl2-Q8_0-GGUF --hf-file dolphin-2.7-mixtral-8x7b-3.5bpw-h6-exl2-q8_0.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo bendavis78/dolphin-2.7-mixtral-8x7b-3.5bpw-h6-exl2-Q8_0-GGUF --hf-file dolphin-2.7-mixtral-8x7b-3.5bpw-h6-exl2-q8_0.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo bendavis78/dolphin-2.7-mixtral-8x7b-3.5bpw-h6-exl2-Q8_0-GGUF --hf-file dolphin-2.7-mixtral-8x7b-3.5bpw-h6-exl2-q8_0.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo bendavis78/dolphin-2.7-mixtral-8x7b-3.5bpw-h6-exl2-Q8_0-GGUF --hf-file dolphin-2.7-mixtral-8x7b-3.5bpw-h6-exl2-q8_0.gguf -c 2048
```
|
ymoslem/whisper-medium-ga2en-v1.3.0-2k-r | ymoslem | 2024-06-21T23:56:08Z | 5 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"ga",
"en",
"dataset:ymoslem/IWSLT2023-GA-EN",
"dataset:ymoslem/FLEURS-GA-EN",
"dataset:ymoslem/BitesizeIrish-GA-EN",
"dataset:ymoslem/SpokenWords-GA-EN-MTed",
"base_model:openai/whisper-medium",
"base_model:finetune:openai/whisper-medium",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] | automatic-speech-recognition | 2024-06-21T18:59:23Z | ---
language:
- ga
- en
license: apache-2.0
base_model: openai/whisper-medium
tags:
- generated_from_trainer
datasets:
- ymoslem/IWSLT2023-GA-EN
- ymoslem/FLEURS-GA-EN
- ymoslem/BitesizeIrish-GA-EN
- ymoslem/SpokenWords-GA-EN-MTed
metrics:
- bleu
- wer
model-index:
- name: Whisper Medium GA-EN Speech Translation Raw
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: IWSLT-2023, FLEURS, BiteSize, and SpokenWords
type: ymoslem/IWSLT2023-GA-EN
metrics:
- name: Bleu
type: bleu
value: 28.37
- name: Wer
type: wer
value: 68.12246735704638
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Whisper Medium GA-EN Speech Translation Raw
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the IWSLT-2023, FLEURS, BiteSize, and SpokenWords dataset.
It achieves the following results on the evaluation set:
- Bleu: 28.37
- Chrf: 45.85
- Loss: 1.4194
- Wer: 68.1225
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.03
- training_steps: 2000
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Bleu | Chrf | Validation Loss | Wer |
|:-------------:|:------:|:----:|:-----:|:-----:|:---------------:|:--------:|
| 2.5874 | 0.0539 | 100 | 4.9 | 19.49 | 2.1785 | 114.0027 |
| 2.3237 | 0.1079 | 200 | 6.48 | 22.77 | 2.1129 | 151.8235 |
| 2.192 | 0.1618 | 300 | 7.92 | 25.9 | 2.0182 | 148.6718 |
| 1.9861 | 0.2157 | 400 | 10.55 | 28.55 | 1.8607 | 121.0266 |
| 1.8893 | 0.2697 | 500 | 16.68 | 33.64 | 1.8560 | 89.7794 |
| 1.8526 | 0.3236 | 600 | 8.83 | 30.12 | 1.7738 | 166.9968 |
| 1.6537 | 0.3776 | 700 | 10.94 | 33.83 | 1.6781 | 152.2287 |
| 1.7103 | 0.4315 | 800 | 16.9 | 36.4 | 1.6389 | 92.2557 |
| 1.4837 | 0.4854 | 900 | 13.81 | 34.5 | 1.6077 | 124.2233 |
| 1.2784 | 0.5394 | 1000 | 14.79 | 37.53 | 1.6103 | 116.3440 |
| 1.111 | 0.5933 | 1100 | 19.31 | 39.0 | 1.5579 | 93.6965 |
| 1.167 | 0.6472 | 1200 | 20.88 | 41.7 | 1.5210 | 91.6704 |
| 1.2217 | 0.7012 | 1300 | 21.29 | 41.72 | 1.4719 | 84.9167 |
| 1.0613 | 0.7551 | 1400 | 28.3 | 44.37 | 1.4663 | 67.1319 |
| 0.9256 | 0.8091 | 1500 | 27.5 | 45.59 | 1.4258 | 68.7078 |
| 0.8023 | 0.8630 | 1600 | 27.1 | 46.27 | 1.4027 | 72.7600 |
| 0.8327 | 0.9169 | 1700 | 27.03 | 46.19 | 1.3784 | 73.0302 |
| 0.7019 | 0.9709 | 1800 | 28.91 | 46.34 | 1.4127 | 67.4921 |
| 0.2681 | 1.0248 | 1900 | 28.53 | 47.12 | 1.3955 | 68.3026 |
| 0.2659 | 1.0787 | 2000 | 28.37 | 45.85 | 1.4194 | 68.1225 |
### Framework versions
- Transformers 4.41.2
- Pytorch 2.2.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
|
tsavage68/Summary_L3_1000steps_1e5rate_01beta_CSFTDPO | tsavage68 | 2024-06-21T23:21:55Z | 7 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"trl",
"dpo",
"generated_from_trainer",
"conversational",
"base_model:tsavage68/Summary_L3_1000steps_1e7rate_SFT2",
"base_model:finetune:tsavage68/Summary_L3_1000steps_1e7rate_SFT2",
"license:llama3",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-06-21T21:22:16Z | ---
license: llama3
base_model: tsavage68/Summary_L3_1000steps_1e7rate_SFT2
tags:
- trl
- dpo
- generated_from_trainer
model-index:
- name: Summary_L3_1000steps_1e5rate_01beta_CSFTDPO
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Summary_L3_1000steps_1e5rate_01beta_CSFTDPO
This model is a fine-tuned version of [tsavage68/Summary_L3_1000steps_1e7rate_SFT2](https://huggingface.co/tsavage68/Summary_L3_1000steps_1e7rate_SFT2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5961
- Rewards/chosen: -0.8715
- Rewards/rejected: -3.9531
- Rewards/accuracies: 0.1400
- Rewards/margins: 3.0816
- Logps/rejected: -54.7948
- Logps/chosen: -18.0977
- Logits/rejected: -1.3576
- Logits/chosen: -1.3527
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- training_steps: 1000
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
| 0.5546 | 0.2004 | 50 | 0.5961 | -0.8720 | -3.9451 | 0.1400 | 3.0730 | -54.7146 | -18.1031 | -1.3571 | -1.3522 |
| 0.6585 | 0.4008 | 100 | 0.5961 | -0.8712 | -3.9495 | 0.1400 | 3.0783 | -54.7588 | -18.0949 | -1.3575 | -1.3526 |
| 0.6238 | 0.6012 | 150 | 0.5961 | -0.8681 | -3.9389 | 0.1400 | 3.0707 | -54.6525 | -18.0641 | -1.3563 | -1.3514 |
| 0.6065 | 0.8016 | 200 | 0.5961 | -0.8725 | -3.9499 | 0.1400 | 3.0774 | -54.7626 | -18.1074 | -1.3568 | -1.3519 |
| 0.6238 | 1.0020 | 250 | 0.5961 | -0.8717 | -3.9513 | 0.1400 | 3.0796 | -54.7771 | -18.1000 | -1.3576 | -1.3527 |
| 0.6238 | 1.2024 | 300 | 0.5961 | -0.8725 | -3.9481 | 0.1400 | 3.0756 | -54.7450 | -18.1078 | -1.3571 | -1.3522 |
| 0.6238 | 1.4028 | 350 | 0.5961 | -0.8727 | -3.9498 | 0.1400 | 3.0771 | -54.7614 | -18.1094 | -1.3572 | -1.3523 |
| 0.5718 | 1.6032 | 400 | 0.5961 | -0.8724 | -3.9505 | 0.1400 | 3.0781 | -54.7691 | -18.1072 | -1.3573 | -1.3524 |
| 0.5892 | 1.8036 | 450 | 0.5961 | -0.8726 | -3.9502 | 0.1400 | 3.0776 | -54.7655 | -18.1083 | -1.3573 | -1.3523 |
| 0.5718 | 2.0040 | 500 | 0.5961 | -0.8717 | -3.9446 | 0.1400 | 3.0728 | -54.7095 | -18.1001 | -1.3575 | -1.3526 |
| 0.5718 | 2.2044 | 550 | 0.5961 | -0.8733 | -3.9538 | 0.1400 | 3.0805 | -54.8019 | -18.1157 | -1.3569 | -1.3521 |
| 0.5545 | 2.4048 | 600 | 0.5961 | -0.8691 | -3.9509 | 0.1400 | 3.0818 | -54.7729 | -18.0740 | -1.3573 | -1.3524 |
| 0.5199 | 2.6052 | 650 | 0.5961 | -0.8731 | -3.9531 | 0.1400 | 3.0800 | -54.7946 | -18.1135 | -1.3573 | -1.3524 |
| 0.6238 | 2.8056 | 700 | 0.5961 | -0.8719 | -3.9544 | 0.1400 | 3.0826 | -54.8080 | -18.1013 | -1.3581 | -1.3532 |
| 0.6065 | 3.0060 | 750 | 0.5961 | -0.8719 | -3.9517 | 0.1400 | 3.0798 | -54.7812 | -18.1017 | -1.3575 | -1.3526 |
| 0.6412 | 3.2064 | 800 | 0.5961 | -0.8706 | -3.9530 | 0.1400 | 3.0824 | -54.7941 | -18.0886 | -1.3574 | -1.3525 |
| 0.6585 | 3.4068 | 850 | 0.5961 | -0.8715 | -3.9512 | 0.1400 | 3.0798 | -54.7760 | -18.0975 | -1.3577 | -1.3529 |
| 0.6238 | 3.6072 | 900 | 0.5961 | -0.8715 | -3.9512 | 0.1400 | 3.0798 | -54.7760 | -18.0975 | -1.3577 | -1.3529 |
| 0.5372 | 3.8076 | 950 | 0.5961 | -0.8715 | -3.9531 | 0.1400 | 3.0816 | -54.7948 | -18.0977 | -1.3576 | -1.3527 |
| 0.6238 | 4.0080 | 1000 | 0.5961 | -0.8715 | -3.9531 | 0.1400 | 3.0816 | -54.7948 | -18.0977 | -1.3576 | -1.3527 |
### Framework versions
- Transformers 4.41.2
- Pytorch 2.0.0+cu117
- Datasets 2.20.0
- Tokenizers 0.19.1
|
zhaorui-nb/Yi-1.5-6B-Chat._.lora_ft._.Setting1 | zhaorui-nb | 2024-06-21T23:06:59Z | 6 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-06-21T22:48:00Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
SiMajid/xlm-roberta-base | SiMajid | 2024-06-21T23:05:26Z | 6 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"xlm-roberta",
"text-classification",
"trl",
"reward-trainer",
"generated_from_trainer",
"base_model:FacebookAI/xlm-roberta-base",
"base_model:finetune:FacebookAI/xlm-roberta-base",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2024-06-21T23:04:52Z | ---
license: mit
base_model: FacebookAI/xlm-roberta-base
tags:
- trl
- reward-trainer
- generated_from_trainer
model-index:
- name: xlm-roberta-base
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# xlm-roberta-base
This model is a fine-tuned version of [FacebookAI/xlm-roberta-base](https://huggingface.co/FacebookAI/xlm-roberta-base) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1.41e-05
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 25.0
### Training results
### Framework versions
- Transformers 4.41.2
- Pytorch 2.1.2
- Datasets 2.19.2
- Tokenizers 0.19.1
|
CMoiNoah/Livai_40kHz | CMoiNoah | 2024-06-21T23:02:13Z | 0 | 0 | null | [
"license:openrail",
"region:us"
] | null | 2024-01-22T08:26:38Z | ---
license: openrail
---
Model Name : Livaï (french singer)
rvc : v2
extraction : rmvpe
epochs : 600
Steps : 28k |
Areeb-02/mpnet-base-GISTEmbedLoss-MSEE_Evaluator-salestax-docs | Areeb-02 | 2024-06-21T22:47:54Z | 10 | 0 | sentence-transformers | [
"sentence-transformers",
"safetensors",
"mpnet",
"sentence-similarity",
"feature-extraction",
"generated_from_trainer",
"dataset_size:238",
"loss:GISTEmbedLoss",
"arxiv:1908.10084",
"arxiv:2402.16829",
"base_model:microsoft/mpnet-base",
"base_model:finetune:microsoft/mpnet-base",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | sentence-similarity | 2024-06-21T22:47:22Z | ---
base_model: microsoft/mpnet-base
datasets: []
language: []
library_name: sentence-transformers
metrics:
- negative_mse
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:238
- loss:GISTEmbedLoss
widget:
- source_sentence: What is the timeframe for opening a physical location in the Designated
Areas to be eligible for the credit under Section 960.1?
sentences:
- '(a) A person or combined group that opens a physical location in the Designated
Areas on or after January 1, 2023 through and including December 31, 2027, shall
be allowed
a credit against that person or combined group''s Gross Receipts Tax if the person
or
74SAN FIAT CU
2024 11AY 10 PM 1331
combined group did not have a physical location in the City for at least three
years prior to
DEPARTMENT OF ELECTIONS
opening the physical location. The credit under this Section 960.1 shall be an
annual credit
for each of up to three tax years immediately following the tax year in which
the person or
combined group opened the physical location in the Designated Areas, provided
the person or
combined group maintains a physical location in the Designated Areas in the tax
year that the
credit is taken. To be eligible for the credit, the person or combined group must
take the
credit for each tax year on an original Gross Receipts Tax return filed with the
Tax Collector.'
- '5222 (Nondepository Credit Intermediation), 5223 (Activities Related
to Credit Intermediation)), 533 (Lessors of Nonfinancial Intangible Assets (except
Copyrighted
Works)), 54 (Professional, Scientific, and Technical Services) but not including
541714 (Research and
Development in Biotechnology (except Nanobiotechnology)), 55 (Management of Companies
and
63SA
CL
2024 LAY 10 PA (30
Enterprises), 562 (Waste Management and Remediation Services), 61 (Educational
Services),
DEPARTMENT OF ELECTI
62 (Health Care and Social Assistance), and all business activities not otherwise
exempt and not
elsewhere subjected to a gross receipts tax rate by Sections 953.20 through 953.26
or an administrative
office tax under Section 953.8.
(c) The amount of taxable gross receipts from Category 5 Business Activities subject
to the
gross receipts tax shall be three-quarters of the amount determined under Section
956.1 plus
one-quarter of the amount determined under Section 956.2.
SEC. 953.25. GROSS RECEIPTS TAX APPLICABLE TO CATEGORY 6 BUSINESS
ACTIVITIES.
(a) The gross receipts tax rates applicable to Category 6 Business Activities
are:
(1) For tax years 2025 and 2026:
1.5% for taxable gross receipts between $0 and $1,000,000
1.5% for taxable gross receipts between $1,000,000.01 and $2,500,000
3% for taxable gross receipts between $2,500,000.01 and $25,000,000
2.352% for taxable gross receipts between $25,000,000.01 and $50,000,000
3.024% for taxable gross receipts between $50,000,000.01 and $75,000,000
3.024% for taxable gross receipts between $75,000,000.01 and $100,000,000
3.36% for taxable gross receipts between $100,000,000.01 and $150,000,000
3.36% for taxable gross receipts between $150,000,000.01 and $250,000,000
3.36% for taxable gross receipts between $250,000,000.01 and $500,000,000
3.'
- 'Except as otherwise provided in this Section 855
and Section 856 of this Article 12, and Section 76.3 of Article 2 of this Business
and Tax Regulations
Code, the annual fee for obtaining a registration certificate for the 2025-2026
registration year,
payable in advance, shall be as follows:
San Francisco Gross Receipts for the
Immediately Preceding Tax Year
$0 to $100,000
$100,000.01 to $250,000
Annual Registration Fee
$41
$71
$250,000.01 to $500,000
$120
$500,000.01 to $750,000
$240
$750,000.01 to $1,000,000
$330
$1,000,000.01 to $1,500,000
$469
$1,500,000.01 to $2,000,000
$656
$2,000,000.01 to $2,500,000
$848
$2,500,000.01 to $5,000,000
$1,414
$5,000,000.01 to $7,500,000
$600
$7,500,000.01 to $15,000,000
$1,500
$15,000,000.01 to $25,000,000
$4,875
25$25,000,000.01 to $50,000,000
$50,000,000.01 to $100,000,000
$100,000,000.01 to $200,000,000
$200,000,000.01 and over
SAN KAL CO
2724 11 10 11 129
$15,000
DEPARTMENT
$30,000
$37,500
$45,000
(d) Fee for Registration Years Beginning On or After April 1, 2026. Except as
otherwise
provided in this Section 855 and Section 856 of this Article 12, and Section 76.3
of Article 2 of this
Business and Tax Regulations Code, the annual fee for obtaining a registration
certificate for
registration years beginning on or after April 1, 2026, payable in advance, shall
be as follows:
San Francisco Gross Receipts for the
Immediately Preceding Tax Year
$0 to $100,'
- source_sentence: How is the overpaid executive administrative office tax measured
for individuals or combined groups, and what other administrative office taxes
might they also be liable for?
sentences:
- '(b) Combined gross receipts are the total worldwide gross receipts of the person
and
all related entities to the person, unless the election provided for in California
Revenue and
Taxation Code Section 25110 is in effect for the person, in which case combined
gross
receipts shall be computed consistently with the water''s edge election, as set
forth therein.
(c) Combined payroll is the total worldwide compensation paid by the person and
all
related entities to the person, unless the election provided for in California
Revenue and
Taxation Code Section 25110 is in effect for the person, in which case combined
payroll shall
be computed consistently with the water''s edge election, as set forth therein.
A person who
72SALA 50
has no combined payroll in a tax year shall have no gross receipts under this
Section for that
DEPARTMENT OF LECT
tax year.
(d) Payroll in the City is the total amount paid for compensation in the City
by the
person and by all related entities to the person.
(e) Compensation paid in the City shall be determined as follows:set forth in
Section 953.8)(4).
(1) Where compensation is paid by reason of work performed or services rendered
by
an individual wholly within the City, all of the compensation for such individual
shall be attributable to
the City.
(2) Where compensation is paid by reason of work performed or services rendered
by
an individual partly within and partly without the City, the portion of such compensation
attributable to
the City shall be determined as follows:
(A) Except as otherwise provided in this Section 956.2(e), the portion of such
compensation attributable to the City shall be the portion of such compensation
which the total number
of working hours employed within the City bears to the total number of working
hours within and
without the City.
(B) If the amount of such compensation depends on the volume of business
transacted by such individual, then the portion of such compensation attributable
to the City shall be
the portion of such compensation which the volume of business transacted by such
individual in the
City bears to the volume of business transacted by such individual within and
without the City.'
- 'If the person or combined group did not file a
7SANT
V
772 MAY 10 TH 1:28
return for the preceding tax year and did not request an extension under Section
6.9-4 to file that
return, the person or combined group shall be deemed to have filed a return showing
no
liability for purposes of this Section 6.9-Isubsection (c)(3)(C)(ii), and no estimated
tax payments
of that tax shall be due for the current tax year.
(D) Lessor of Residential Real Estate Exemption. Notwithstanding
any other provision in this Section 6.9-1(c)(3), a lessor of residential real
estate, as defined in
Section 954.1 of Article 12-A-1, shall not be required to make estimated tax payments
under
this Section 6.9-1(c)(3), but shall pay its full Gross Receipts Tax liability,
Homelessness Gross
Receipts Tax liability, and Overpaid Executive Gross Receipts Tax liability on
or before the
last day of February of the succeeding year, or the extended deadline in Section
6.9-4, if the
lessor''s gross receipts within the City shown on the lessor''s return for either
the current tax
year or the preceding tax year did not exceed the threshold in Section 954.1(b)
of
Article 12-A-1.
*
*
(g) Business Registration Certificate; Annual Due Date.
(1) For registration years ending on or before June 30, 2025 and the
2025-2026 registration year, eExcept for any extensions granted under Section
6.9-4 or as
otherwise provided in this Business and Tax Regulations Code, returns and payments
of the
Business Registration Fee (Article 12) shall be filed annually and are due and
payable, and
shall be delinquent if not submitted and paid to the Tax Collector, on or before
the last day of
May preceding the registration year commencing July 1 of that year.'
- 'DEPARTMENT OF ELECTION
Article 12-A-1, shall pay an annual overpaid executive administrative office tax
if the Executive
Pay Ratio for the tax year of that person or the combined group of which it is
a part
exceeds 100:1. This overpaid executive administrative office tax shall be measured
by the
person''s total payroll expense, as defined in Section 953.8(f) of Article 12-A-1,
that is
attributable to the City. If a person is a member of a combined group, then its
tax shall be
measured by the total payroll expense of the combined group attributable to the
City. Such
person or combined group shall pay only the overpaid executive administrative
office tax, and
not the tax imposed under other subsections of this Section 3303, but a person
or combined
group may be liable for the administrative office tax imposed by Section 953.8
of
Article 12-A-1 and the homelessness administrative office tax imposed by Section
2804(d) or
Section 2804.9 of Article 28 in addition to the overpaid executive administrative
office tax
imposed by this subsection (dg). Unless specified otherwise, this overpaid executive
administrative office tax shall be considered part of the Overpaid Executive Gross
Receipts
Tax for all purposes.'
- source_sentence: What are the homelessness gross receipts tax rates applicable to
Category 1 Business Activities for tax years beginning on or after January 1,
2025, as outlined in Section 2804.3 of the same code?
sentences:
- 'For purposes
of serving a notice of a deficiency determination under this Section 6.11-2, the
date that a return was
due shall be:
(1) For tax years and tax periods ending on or before December 31, 2021, and
registration years ending on or before June 30, 2023, the due date of the return
without regard to any
extensions under Section 6.9-4;
(2) For tax years and tax periods beginning on or after January 1, 2022, and
registration years beginning on or after July 1, 2023 and ending on or before
March 31, 2026, except
for the taxes for the years and periods subject to subsection (a)(3) of this Section
6.11-2, the due date of
the return including any extensions; or
(3) For the Gross Receipts Tax (Article 12-A-1) (including the tax on administrative
office business activities in Section 953.8 of Article 12-A-1), the Early Care
and Education Commercial
Rents Tax (Article 21), the Homelessness Gross Receipts Tax (Article 28) (including
the tax on
administrative office business activities in Section 2804(d) or Section 2804.9
of Article 28), the
Cannabis Business Tax (Article 30), and the Overpaid Executive Gross Receipts
Tax (Article 33)
(including the tax on administrative office business activities in Section 3303(g))
for tax years
beginning on or after January 1, 2025, and for the Business Registration Fee (Article
12) for
registration years beginning on or after April 1, 2026, November 30 of the calendar
year in which the
return for such respective tax was originally due.
13SAN
CO
22 MAY (b) The notice of any determination under this Section 6.11-2 may be served
upon the
DEMANTHER OF CLIENT OFF
taxpayer or other affected person personally or by mail; if by mail, service shall
be:
(1) to the last known address that appears in the Tax Collector''s records,
provided there is such an address in the Tax Collector''s records, or
(2) to an address that the Tax Collector concludes, in the Tax Collector''s
discretion, is the last known address of the person(s).'
- 'If the person or combined group did not file a
7SANT
V
772 MAY 10 TH 1:28
return for the preceding tax year and did not request an extension under Section
6.9-4 to file that
return, the person or combined group shall be deemed to have filed a return showing
no
liability for purposes of this Section 6.9-Isubsection (c)(3)(C)(ii), and no estimated
tax payments
of that tax shall be due for the current tax year.
(D) Lessor of Residential Real Estate Exemption. Notwithstanding
any other provision in this Section 6.9-1(c)(3), a lessor of residential real
estate, as defined in
Section 954.1 of Article 12-A-1, shall not be required to make estimated tax payments
under
this Section 6.9-1(c)(3), but shall pay its full Gross Receipts Tax liability,
Homelessness Gross
Receipts Tax liability, and Overpaid Executive Gross Receipts Tax liability on
or before the
last day of February of the succeeding year, or the extended deadline in Section
6.9-4, if the
lessor''s gross receipts within the City shown on the lessor''s return for either
the current tax
year or the preceding tax year did not exceed the threshold in Section 954.1(b)
of
Article 12-A-1.
*
*
(g) Business Registration Certificate; Annual Due Date.
(1) For registration years ending on or before June 30, 2025 and the
2025-2026 registration year, eExcept for any extensions granted under Section
6.9-4 or as
otherwise provided in this Business and Tax Regulations Code, returns and payments
of the
Business Registration Fee (Article 12) shall be filed annually and are due and
payable, and
shall be delinquent if not submitted and paid to the Tax Collector, on or before
the last day of
May preceding the registration year commencing July 1 of that year.'
- '(a) The homelessness gross receipts tax rates applicable to Category 1 Business
Activities for
tax years beginning on or after January 1, 2025 are:
0% for taxable gross receipts between $0 and $1,000,000
0% for taxable gross receipts between $1,000,000.01 and $2,500,000
0% for taxable gross receipts between $2,500,000.01 and $25,000,000
0.164% for taxable gross receipts between $25,000,000.01 and $50,000,000
0.164% for taxable gross receipts between $50,000,000.01 and $75,000,000
0.164% for taxable gross receipts between $75,000,000.01 and $100,000,000
0.164% for taxable gross receipts between $100,000,000.01 and $150,000,000
0.246% for taxable gross receipts between $150,000,000.01 and $250,000,000
0.328% for taxable gross receipts between $250,000,000.01 and $500,000,000
0.41% for taxable gross receipts between $500,000,000.01 and $1,000,000,000
0.492% for taxable gross receipts over $1,000,000,000
(b) "Category 1 Business Activities" has the same meaning as in Section 953.20(b)
of
Article 12-A-1 of this Business and Tax Regulations Code.
(c) The amount of taxable gross receipts from Category 1 Business Activities subject
to the
homelessness gross receipts tax shall be three-quarters of the amount determined
under Section 956.1
of Article 12-A-1 plus one-quarter of the amount determined under Section 956.2
of Article 12-A-1.
84SAL
SEC. 2804.3. HOMELESSNESS GROSS RECEIPTS TAX APPLICABLE TO CATEGORY 2
BUSINESS ACTIVITIES.'
- source_sentence: What are the different gross receipts tax rates applicable to private
education and health services, administrative and support services, and miscellaneous
business activities as outlined in Section 953.4?
sentences:
- '(b) For only so long as and to the extent that the City is prohibited from imposing
the
Homelessness Gross Receipts Tax, any person upon whom the City is prohibited under
the
Constitution or laws of the State of California or the Constitution or laws of
the United States
from imposing the Homelessness Gross Receipts Tax shall be exempt from the
Homelessness Gross Receipts Tax.
(c) For purposes of this Article 28, gross receipts shall not include receipts
that are
excluded from gross receipts for purposes of the gross receipts tax imposed by
Article 12-A-1,
and also shall not include receipts subject to a gross receipts tax on commercial
rents
imposed as a result of a measure adopted by the voters of San Francisco in the
June 5, 2018
election.
(d) This Section 2805 shall apply to tax years ending on or before December 31,
2024.
SEC. 2805.3. EXEMPTIONS AND EXCLUSIONS.
(a) An organization that is exempt from income taxation by Chapter 4 (commencing
with
Section 23701) of Part 11 of Division 2 of the California Revenue and Taxation
Code or Subchapter F
(commencing with Section 501) of Chapter 1 of Subtitle A of the Internal Revenue
Code of 1986, as
amended, as qualified by Sections 502, 503, 504, and 508 of the Internal Revenue
Code of 1986, as
amended, shall be exempt from taxation under this Article 28, only so long as
those exemptions
continue to exist under state or federal law.
(b) For purposes of this Article 28, gross receipts as defined in Section 952.3
shall not include
receipts from business activities if, and only so long as and to the extent that,
the City is prohibited
93SA
01:32
from taxing such receipts under the Constitution or laws of the United States
or under the Constitution
or laws of the State of California.
(c) Rent Controlled Buildings Exclusion. A person subject to the homelessness
gross receipts
tax may exclude from gross receipts in any tax year 50% of the total amount received
from the rental of
real property to tenants in occupancy at any location in the City, which is subject
to limits on rent
increases pursuant to the Residential Rent Stabilization and Arbitration Ordinance,
Administrative
Code, Chapter 37, Section 37.1 et seq.'
- '10 that the
90% gross receipts threshold has been met for tax year 2023, and for tax year
2024 if the Controller
does not certify under Section 953.10 that the 95% gross receipts threshold has
been met for tax
year 2024:
42SAN LANCI Co
FILED
2024 MAY 10 PH 1:29
0.45% (e.g. $4.50 per $1,000) for taxable gross receipts between $0 and $1,000,000
DEPARTMENT OF ELECTIONS
0.488% (e.g. $4.88 per $1,000) for taxable gross receipts between $1,000,000.01
and
$2,500,000
0.488% (e.g. $4.88 per $1,000) for taxable gross receipts between $2,500,000.01
and
$25,000,000
0.6% (e.g. $6 per $1,000) for taxable gross receipts over $25,000,000
(D) For tax year 2024 if the Controller certifies under Section 953.10 that the
95% gross receipts threshold has been met for tax year 2024, and for tax years
beginning on or after
January 1, 2025:
0.465% (e.g. $4.65 per $1,000) for taxable gross receipts between $0 and $1,000,000
0.504% (e.g. $5.04 per $1,000) for taxable gross receipts between $1,000,000.01
and
$2,500,000
0.504% (e.g. $5.04 per $1,000) for taxable gross receipts between $2,500,000.01
and
$25,000,000
0.62% (e.g. $6.20 per $1,000) for taxable gross receipts over $25,000,000
SEC. 953.4. GROSS RECEIPTS TAX APPLICABLE TO PRIVATE EDUCATION AND
HEALTH SERVICES; ADMINISTRATIVE AND SUPPORT SERVICES; AND
MISCELLANEOUS BUSINESS ACTIVITIES.
(a) The gross receipts tax rates applicable to the business activities of private
education and health services, administrative and support services,'
- 'SARI
до
202 BAY 10 FA 1:32
year by 52, and dividing the result by the number of weeks that the employee was
employed by that
person or combined group during the tax year.
"Highest-Paid Managerial Employee" means the individual employee or officer of
a
person or combined group with managerial responsibility in a business function
who received the most
Compensation for a tax year. For purposes of determining the Highest-Paid Managerial
Employee and
the Compensation of such employee, Compensation shall not be annualized or converted
to a full-time
equivalency.
SEC. 3303. IMPOSITION OF TAX.
(a) Except as otherwise provided in this Article 33, commencing with tax years
beginning on or after January 1, 2022, for the privilege of engaging in business
in the City, the
City imposes an annual Overpaid Executive Gross Receipts Tax on each person engaging
in
business within the City where the Executive Pay Ratio for the tax year of that
person or the
combined group of which it is a part exceeds 100:1.'
- source_sentence: Based on the context information provided, what are the different
gross receipts tax rates for businesses in San Francisco for tax years 2022, 2023,
and 2024?
sentences:
- '$9.75 per $1,000) for taxable gross receipts over $25,000,000
44SANCO
2024 NAY LO
(D) For tax year 2024 if the Controller certifies under Section 953.10 that the
DEPARTMENT OF
95% gross receipts threshold has been met for tax year 2024, and for tax years
beginning on or after
January 1, 2025:
0.814% (e.g. $8.14 per $1,000) for taxable gross receipts between $0 and $1,000,000
0.853% (e.g. $8.53 per $1,000) for taxable gross receipts between $1,000,000.01
and
$2,500,000
0.93% (e.g. $9.30 per $1,000) for taxable gross receipts between $2,500,000.01
and
$25,000,000
1.008% (e.g. $10.08 per $1,000) for taxable gross receipts over $25,000,000
(3) For all business activities not otherwise exempt and not elsewhere
subjected to a gross receipts tax rate or an administrative office tax by this
Article 12-A-1:
(B) For tax years 2022 and, if the Controller does not certify under
Section 953.10 that the 90% gross receipts threshold has been met for tax year
2023, for tax
year 2023:
0.788% (e.g. $7.88 per $1,000) for taxable gross receipts between $0 and $1,000,000
0.825% (e.g. $8.25 per $1,000) for taxable gross receipts between $1,000,000.01
and
$2,500,000
0.9% (e.g. $9 per $1,000) for taxable gross receipts between $2,500,000.01 and
$25,000,000
0.975% (e.g. $9.75 per $1,000) for taxable gross receipts over $25,000,000
(C) For tax year 2023 if the Controller certifies under Section 953.10 that the
90% gross receipts threshold has been met for tax year 2023,'
- '(d) In no event shall the credit under this Section 960.4 reduce a person or
combined group''s
Gross Receipts Tax liability to less than $0 for any tax year. The credit under
this Section shall not be
refundable and may not be carried forward to a subsequent year.
SEC. 966. CONTROLLER REPORTS.
The Controller shall prepare reports by September 1, 2026, and September 1, 2027,
respectively, that discuss current economic conditions in the City and the performance
of the tax system
revised by the voters in the ordinance adding this Section 966.
Section 6. Article 21 of the Business and Tax Regulations Code is hereby amended
by
revising Section 2106 to read as follows:
SEC. 2106. SMALL BUSINESS EXEMPTION.
(a) For tax years ending on or before December 31, 2024, nNotwithstanding any
other
provision of this Article 21, a person or combined group exempt from payment of
the gross
receipts tax under Section 954.1 of Article 12-A-1, as amended from time to time,
shall also
be exempt from payment of the Early Care and Education Commercial Rents Tax.
79SAN
DL W(b) For tax years beginning on or after January 1, 2025, notwithstanding any
other provision
of this Article 21, a "small business enterprise" shall be exempt from payment
of the Early Care and
Education Commercial Rents Tax. For purposes of this subsection (b), the term
"small business
enterprise" shall mean any person or combined group whose gross receipts within
the City, determined
under Article 12-A-1, did not exceed $2,325,000, adjusted annually in accordance
with the increase in
the Consumer Price Index: All Urban Consumers for the San Francisco/Oakland/Hayward
Area for All
Items as reported by the United States Bureau of Labor Statistics, or any successor
to that index, as of
December 31 of the calendar year two years prior to the tax year, beginning with
tax year 2026, and
rounded to the nearest $10,000. This subsection (b) shall not apply to a person
or combined group
subject to a tax on administrative office business activities in Section 953.8
of Article 12-A-1.
Section 7.'
- '(1) For tax years ending on or before December 31, 2024, the overpaid executive
administrative office tax shall be calculated as follows:
(+4) 0.4% of the person or combined group''s total payroll expense
attributable to the City for a tax year if the person or combined group has an
Executive Pay
Ratio for that tax year of greater than 100:1, but less than or equal to 200:1;
(2B) 0.8% of the person or combined group''s total payroll expense
attributable to the City for a tax year if the person or combined group has an
Executive Pay
Ratio for that tax year of greater than 200:1, but less than or equal to 300:1;
(3C) 1.2% of the person or combined group''s total payroll expense
attributable to the City for a tax year if the person or combined group has an
Executive Pay
Ratio for that tax year of greater than 300:1, but less than or equal to 400:1;
103SAULAMIC 50
10 PM 1:32
(4D) 1.6% of the person or combined group''s total payroll expense
DEPARTMENT OF ELECTIONS
attributable to the City for a tax year if the person or combined group has an
Executive Pay
Ratio for that tax year of greater than 400:1, but less than or equal to 500:1;
(5E) 2% of the person or combined group''s total payroll expense
attributable to the City for a tax year if the person or combined group has an
Executive Pay
Ratio for that tax year of greater than 500:1, but less than or equal to 600:1;
or
(6F) 2.4% of the person or combined group''s total payroll expense
attributable to the City for a tax year if the person or combined group has an
Executive Pay
Ratio for that tax year of greater than 600:1.'
model-index:
- name: SentenceTransformer based on microsoft/mpnet-base
results:
- task:
type: knowledge-distillation
name: Knowledge Distillation
dataset:
name: stsb dev
type: stsb-dev
metrics:
- type: negative_mse
value: -2.4281997233629227
name: Negative Mse
---
# SentenceTransformer based on microsoft/mpnet-base
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [microsoft/mpnet-base](https://huggingface.co/microsoft/mpnet-base). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
## Model Details
### Model Description
- **Model Type:** Sentence Transformer
- **Base model:** [microsoft/mpnet-base](https://huggingface.co/microsoft/mpnet-base) <!-- at revision 6996ce1e91bd2a9c7d7f61daec37463394f73f09 -->
- **Maximum Sequence Length:** 512 tokens
- **Output Dimensionality:** 768 tokens
- **Similarity Function:** Cosine Similarity
<!-- - **Training Dataset:** Unknown -->
<!-- - **Language:** Unknown -->
<!-- - **License:** Unknown -->
### Model Sources
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
### Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: MPNetModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)
```
## Usage
### Direct Usage (Sentence Transformers)
First install the Sentence Transformers library:
```bash
pip install -U sentence-transformers
```
Then you can load this model and run inference.
```python
from sentence_transformers import SentenceTransformer
# Download from the 🤗 Hub
model = SentenceTransformer("Areeb-02/mpnet-base-GISTEmbedLoss-MSEE_Evaluator-salestax-docs")
# Run inference
sentences = [
'Based on the context information provided, what are the different gross receipts tax rates for businesses in San Francisco for tax years 2022, 2023, and 2024?',
'$9.75 per $1,000) for taxable gross receipts over $25,000,000\n44SANCO\n2024 NAY LO\n(D) For tax year 2024 if the Controller certifies under Section 953.10 that the\nDEPARTMENT OF\n95% gross receipts threshold has been met for tax year 2024, and for tax years beginning on or after\nJanuary 1, 2025:\n0.814% (e.g. $8.14 per $1,000) for taxable gross receipts between $0 and $1,000,000\n0.853% (e.g. $8.53 per $1,000) for taxable gross receipts between $1,000,000.01 and\n$2,500,000\n0.93% (e.g. $9.30 per $1,000) for taxable gross receipts between $2,500,000.01 and\n$25,000,000\n1.008% (e.g. $10.08 per $1,000) for taxable gross receipts over $25,000,000\n(3) For all business activities not otherwise exempt and not elsewhere\nsubjected to a gross receipts tax rate or an administrative office tax by this Article 12-A-1:\n(B) For tax years 2022 and, if the Controller does not certify under\nSection 953.10 that the 90% gross receipts threshold has been met for tax year 2023, for tax\nyear 2023:\n0.788% (e.g. $7.88 per $1,000) for taxable gross receipts between $0 and $1,000,000\n0.825% (e.g. $8.25 per $1,000) for taxable gross receipts between $1,000,000.01 and\n$2,500,000\n0.9% (e.g. $9 per $1,000) for taxable gross receipts between $2,500,000.01 and\n$25,000,000\n0.975% (e.g. $9.75 per $1,000) for taxable gross receipts over $25,000,000\n(C) For tax year 2023 if the Controller certifies under Section 953.10 that the\n90% gross receipts threshold has been met for tax year 2023,',
'(d) In no event shall the credit under this Section 960.4 reduce a person or combined group\'s\nGross Receipts Tax liability to less than $0 for any tax year. The credit under this Section shall not be\nrefundable and may not be carried forward to a subsequent year.\nSEC. 966. CONTROLLER REPORTS.\nThe Controller shall prepare reports by September 1, 2026, and September 1, 2027,\nrespectively, that discuss current economic conditions in the City and the performance of the tax system\nrevised by the voters in the ordinance adding this Section 966.\nSection 6. Article 21 of the Business and Tax Regulations Code is hereby amended by\nrevising Section 2106 to read as follows:\nSEC. 2106. SMALL BUSINESS EXEMPTION.\n(a) For tax years ending on or before December 31, 2024, nNotwithstanding any other\nprovision of this Article 21, a person or combined group exempt from payment of the gross\nreceipts tax under Section 954.1 of Article 12-A-1, as amended from time to time, shall also\nbe exempt from payment of the Early Care and Education Commercial Rents Tax.\n79SAN\nDL W(b) For tax years beginning on or after January 1, 2025, notwithstanding any other provision\nof this Article 21, a "small business enterprise" shall be exempt from payment of the Early Care and\nEducation Commercial Rents Tax. For purposes of this subsection (b), the term "small business\nenterprise" shall mean any person or combined group whose gross receipts within the City, determined\nunder Article 12-A-1, did not exceed $2,325,000, adjusted annually in accordance with the increase in\nthe Consumer Price Index: All Urban Consumers for the San Francisco/Oakland/Hayward Area for All\nItems as reported by the United States Bureau of Labor Statistics, or any successor to that index, as of\nDecember 31 of the calendar year two years prior to the tax year, beginning with tax year 2026, and\nrounded to the nearest $10,000. This subsection (b) shall not apply to a person or combined group\nsubject to a tax on administrative office business activities in Section 953.8 of Article 12-A-1.\nSection 7.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]
# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]
```
<!--
### Direct Usage (Transformers)
<details><summary>Click to see the direct usage in Transformers</summary>
</details>
-->
<!--
### Downstream Usage (Sentence Transformers)
You can finetune this model on your own dataset.
<details><summary>Click to expand</summary>
</details>
-->
<!--
### Out-of-Scope Use
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
-->
## Evaluation
### Metrics
#### Knowledge Distillation
* Dataset: `stsb-dev`
* Evaluated with [<code>MSEEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.MSEEvaluator)
| Metric | Value |
|:-----------------|:------------|
| **negative_mse** | **-2.4282** |
<!--
## Bias, Risks and Limitations
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
-->
<!--
### Recommendations
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
-->
## Training Details
### Training Dataset
#### Unnamed Dataset
* Size: 238 training samples
* Columns: <code>sentence1</code> and <code>sentence2</code>
* Approximate statistics based on the first 1000 samples:
| | sentence1 | sentence2 |
|:--------|:-----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
| type | string | string |
| details | <ul><li>min: 5 tokens</li><li>mean: 41.95 tokens</li><li>max: 219 tokens</li></ul> | <ul><li>min: 63 tokens</li><li>mean: 426.3 tokens</li><li>max: 512 tokens</li></ul> |
* Samples:
| sentence1 | sentence2 |
|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| <code>What types of businesses are subject to the gross receipts tax in San Francisco, and how is their San Francisco gross receipts calculated? What are the current rates for this tax, and are there any exemptions or scheduled increases?</code> | <code>The Way It Is Now<br>CHANGES TO BUSINESS TAXES<br>The City collects various business taxes on an annual basis including:<br>O<br>•<br>SAN FRANCISCO<br>FILED<br>2024 MAY 15 PM 3:10<br>DEPARTMENT OF ELECTIONS<br>A gross receipts tax that is a percentage of a business's San Francisco gross receipts.<br>Depending on business type, the City determines a business's San Francisco gross<br>receipts based on sales in San Francisco, payroll expenses for employees working there,<br>or both. Rates range from 0.053% to 1.008% and are scheduled to increase in coming<br>years. Rates depend on business type, and higher rates apply as a business generates<br>more gross receipts. For 2023, most businesses with gross receipts up to $2.19 million<br>are exempt.<br>A homelessness gross receipts tax that is an additional tax on businesses with San<br>Francisco gross receipts over $50 million. Rates range from 0.175% to 0.69%.<br>An overpaid executive gross receipts tax that is an additional tax on businesses that pay<br>their highest-paid managerial employee much higher than the median compensation they<br>pay their San Francisco employees. Rates are between 0.1% and 0.6%.<br>A business registration fee that is an additional tax. For most businesses the fee is<br>currently between $47 and $45,150, based on business type and amount of gross receipts.<br>• An administrative office tax on payroll expenses that certain large businesses pay instead<br>of these other business taxes. The combined rates in 2024 range from 3.04% to 5.44%,<br>and in 2025 are scheduled to range from 3.11% to 5.51%. Business registration fees for<br>these businesses currently range from $19,682 to $45,928.<br>State law limits the total revenue, including tax revenue, the City may spend each year. The<br>voters may approve increases to this limit for up to four years.</code> |
| <code>What is the homelessness gross receipts tax, and which businesses are required to pay it? What are the current rates for this tax, and how do they vary based on the amount of San Francisco gross receipts? Are there any exemptions or scheduled increases for this tax?</code> | <code>The Way It Is Now<br>CHANGES TO BUSINESS TAXES<br>The City collects various business taxes on an annual basis including:<br>O<br>•<br>SAN FRANCISCO<br>FILED<br>2024 MAY 15 PM 3:10<br>DEPARTMENT OF ELECTIONS<br>A gross receipts tax that is a percentage of a business's San Francisco gross receipts.<br>Depending on business type, the City determines a business's San Francisco gross<br>receipts based on sales in San Francisco, payroll expenses for employees working there,<br>or both. Rates range from 0.053% to 1.008% and are scheduled to increase in coming<br>years. Rates depend on business type, and higher rates apply as a business generates<br>more gross receipts. For 2023, most businesses with gross receipts up to $2.19 million<br>are exempt.<br>A homelessness gross receipts tax that is an additional tax on businesses with San<br>Francisco gross receipts over $50 million. Rates range from 0.175% to 0.69%.<br>An overpaid executive gross receipts tax that is an additional tax on businesses that pay<br>their highest-paid managerial employee much higher than the median compensation they<br>pay their San Francisco employees. Rates are between 0.1% and 0.6%.<br>A business registration fee that is an additional tax. For most businesses the fee is<br>currently between $47 and $45,150, based on business type and amount of gross receipts.<br>• An administrative office tax on payroll expenses that certain large businesses pay instead<br>of these other business taxes. The combined rates in 2024 range from 3.04% to 5.44%,<br>and in 2025 are scheduled to range from 3.11% to 5.51%. Business registration fees for<br>these businesses currently range from $19,682 to $45,928.<br>State law limits the total revenue, including tax revenue, the City may spend each year. The<br>voters may approve increases to this limit for up to four years.</code> |
| <code>What is the proposed measure that voters may approve to change the City's business taxes in San Francisco?</code> | <code>The<br>voters may approve increases to this limit for up to four years.<br>The Proposal<br>The proposed measure would change the City's business taxes to:<br>•<br>For the gross receipts tax:<br>○ recategorize business types, reducing the number from 14 to seven;<br>determine San Francisco gross receipts for some businesses based less on payroll<br>expenses and more on sales;<br>o change rates to between 0.1% and 3.716%; and<br>exempt most businesses with gross receipts up to $5 million (increased by<br>inflation).<br>Apply the homelessness gross receipts tax on business activities with San Francisco gross<br>receipts over $25 million, at rates between 0.162% and 1.64%.<br>Modify how the City calculates the overpaid executive gross receipts tax and who pays<br>that tax, and set rates between 0.02% and 0.129%.<br>Adjust business registration fees to between $55 and $60,000 (increased by inflation).Adjust the administrative office tax rates for certain large businesses to range from 2.97%<br>to 3.694%, and the business registration fees for these taxpayers to between $500 and<br>$35,000 (increased by inflation).<br>Make administrative and other changes to the City's business taxes.<br>The homelessness gross receipts tax would continue to fund services for people experiencing<br>homelessness and homelessness prevention. The City would use the other taxes for general<br>government purposes.<br>All these taxes would apply indefinitely until repealed.<br>This proposal would increase the City's spending limit for four years.SALITA CO<br>2024 MAY 10 PH 1:27<br>DEPARTMENT OF ELECTI<br>"Local Small Business Tax Cut Ordinance"<br>Be it ordained by the People of the City and County of San Francisco:<br>NOTE:<br>Unchanged Code text and uncodified text are in plain font.<br>Additions to Codes are in single-underline italics Times New Roman font.<br>Deletions to Codes are in strikethrough italics Times New Roman font.<br>Asterisks (* * * *) indicate the omission of unchanged Code<br>subsections or parts of tables.<br>Section 1. Title. This initiative is known and may be referred to as the "Local Small<br>Business Tax Cut Ordinance."<br>Section 2. Article 2 of the Business and Tax Regulations Code is hereby amended by<br>revising Section 76.3 to read as follows:<br>SEC. 76.3.</code> |
* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
```json
{'guide': SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
(2): Normalize()
), 'temperature': 0.01}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `eval_strategy`: steps
- `per_device_train_batch_size`: 16
- `per_device_eval_batch_size`: 16
- `num_train_epochs`: 1
- `warmup_ratio`: 0.1
#### All Hyperparameters
<details><summary>Click to expand</summary>
- `overwrite_output_dir`: False
- `do_predict`: False
- `eval_strategy`: steps
- `prediction_loss_only`: True
- `per_device_train_batch_size`: 16
- `per_device_eval_batch_size`: 16
- `per_gpu_train_batch_size`: None
- `per_gpu_eval_batch_size`: None
- `gradient_accumulation_steps`: 1
- `eval_accumulation_steps`: None
- `learning_rate`: 5e-05
- `weight_decay`: 0.0
- `adam_beta1`: 0.9
- `adam_beta2`: 0.999
- `adam_epsilon`: 1e-08
- `max_grad_norm`: 1.0
- `num_train_epochs`: 1
- `max_steps`: -1
- `lr_scheduler_type`: linear
- `lr_scheduler_kwargs`: {}
- `warmup_ratio`: 0.1
- `warmup_steps`: 0
- `log_level`: passive
- `log_level_replica`: warning
- `log_on_each_node`: True
- `logging_nan_inf_filter`: True
- `save_safetensors`: True
- `save_on_each_node`: False
- `save_only_model`: False
- `restore_callback_states_from_checkpoint`: False
- `no_cuda`: False
- `use_cpu`: False
- `use_mps_device`: False
- `seed`: 42
- `data_seed`: None
- `jit_mode_eval`: False
- `use_ipex`: False
- `bf16`: False
- `fp16`: False
- `fp16_opt_level`: O1
- `half_precision_backend`: auto
- `bf16_full_eval`: False
- `fp16_full_eval`: False
- `tf32`: None
- `local_rank`: 0
- `ddp_backend`: None
- `tpu_num_cores`: None
- `tpu_metrics_debug`: False
- `debug`: []
- `dataloader_drop_last`: False
- `dataloader_num_workers`: 0
- `dataloader_prefetch_factor`: None
- `past_index`: -1
- `disable_tqdm`: False
- `remove_unused_columns`: True
- `label_names`: None
- `load_best_model_at_end`: False
- `ignore_data_skip`: False
- `fsdp`: []
- `fsdp_min_num_params`: 0
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
- `fsdp_transformer_layer_cls_to_wrap`: None
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
- `deepspeed`: None
- `label_smoothing_factor`: 0.0
- `optim`: adamw_torch
- `optim_args`: None
- `adafactor`: False
- `group_by_length`: False
- `length_column_name`: length
- `ddp_find_unused_parameters`: None
- `ddp_bucket_cap_mb`: None
- `ddp_broadcast_buffers`: False
- `dataloader_pin_memory`: True
- `dataloader_persistent_workers`: False
- `skip_memory_metrics`: True
- `use_legacy_prediction_loop`: False
- `push_to_hub`: False
- `resume_from_checkpoint`: None
- `hub_model_id`: None
- `hub_strategy`: every_save
- `hub_private_repo`: False
- `hub_always_push`: False
- `gradient_checkpointing`: False
- `gradient_checkpointing_kwargs`: None
- `include_inputs_for_metrics`: False
- `eval_do_concat_batches`: True
- `fp16_backend`: auto
- `push_to_hub_model_id`: None
- `push_to_hub_organization`: None
- `mp_parameters`:
- `auto_find_batch_size`: False
- `full_determinism`: False
- `torchdynamo`: None
- `ray_scope`: last
- `ddp_timeout`: 1800
- `torch_compile`: False
- `torch_compile_backend`: None
- `torch_compile_mode`: None
- `dispatch_batches`: None
- `split_batches`: None
- `include_tokens_per_second`: False
- `include_num_input_tokens_seen`: False
- `neftune_noise_alpha`: None
- `optim_target_modules`: None
- `batch_eval_metrics`: False
- `batch_sampler`: batch_sampler
- `multi_dataset_batch_sampler`: proportional
</details>
### Training Logs
| Epoch | Step | stsb-dev_negative_mse |
|:-----:|:----:|:---------------------:|
| 0 | 0 | -2.4282 |
### Framework Versions
- Python: 3.10.12
- Sentence Transformers: 3.0.1
- Transformers: 4.41.2
- PyTorch: 2.3.0+cu121
- Accelerate: 0.31.0
- Datasets: 2.20.0
- Tokenizers: 0.19.1
## Citation
### BibTeX
#### Sentence Transformers
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "https://arxiv.org/abs/1908.10084",
}
```
#### GISTEmbedLoss
```bibtex
@misc{solatorio2024gistembed,
title={GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuning},
author={Aivin V. Solatorio},
year={2024},
eprint={2402.16829},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
```
<!--
## Glossary
*Clearly define terms in order to be accessible across audiences.*
-->
<!--
## Model Card Authors
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->
<!--
## Model Card Contact
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
--> |
fumiyau/gpt2-002-ja | fumiyau | 2024-06-21T22:39:30Z | 8 | 0 | transformers | [
"transformers",
"safetensors",
"gpt2",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-06-21T22:38:20Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
naimul011/Fin-Senti-llama3 | naimul011 | 2024-06-21T22:20:13Z | 8 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"trl",
"sft",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
] | text-generation | 2024-06-21T21:12:06Z | ---
library_name: transformers
tags:
- trl
- sft
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
bartowski/Hathor_Enigmatica-L3-8B-v0.4-GGUF | bartowski | 2024-06-21T22:06:14Z | 34 | 2 | null | [
"gguf",
"text-generation",
"en",
"license:other",
"endpoints_compatible",
"region:us",
"conversational"
] | text-generation | 2024-06-21T21:05:24Z | ---
license: other
language:
- en
quantized_by: bartowski
pipeline_tag: text-generation
---
## Llamacpp imatrix Quantizations of Hathor_Enigmatica-L3-8B-v0.4
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b3197">b3197</a> for quantization.
Original model: https://huggingface.co/Nitral-AI/Hathor_Enigmatica-L3-8B-v0.4
All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
## Prompt format
```
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
```
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Description |
| -------- | ---------- | --------- | ----------- |
| [Hathor_Enigmatica-L3-8B-v0.4-Q8_0_L.gguf](https://huggingface.co/bartowski/Hathor_Enigmatica-L3-8B-v0.4-GGUF/blob/main/Hathor_Enigmatica-L3-8B-v0.4-Q8_1.gguf) | Q8_0_L | 9.52GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. Extremely high quality, generally unneeded but max available quant. |
| [Hathor_Enigmatica-L3-8B-v0.4-Q8_0.gguf](https://huggingface.co/bartowski/Hathor_Enigmatica-L3-8B-v0.4-GGUF/blob/main/Hathor_Enigmatica-L3-8B-v0.4-Q8_0.gguf) | Q8_0 | 8.54GB | Extremely high quality, generally unneeded but max available quant. |
| [Hathor_Enigmatica-L3-8B-v0.4-Q6_K_L.gguf](https://huggingface.co/bartowski/Hathor_Enigmatica-L3-8B-v0.4-GGUF/blob/main/Hathor_Enigmatica-L3-8B-v0.4-Q6_K_L.gguf) | Q6_K_L | 7.83GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. Very high quality, near perfect, *recommended*. |
| [Hathor_Enigmatica-L3-8B-v0.4-Q6_K.gguf](https://huggingface.co/bartowski/Hathor_Enigmatica-L3-8B-v0.4-GGUF/blob/main/Hathor_Enigmatica-L3-8B-v0.4-Q6_K.gguf) | Q6_K | 6.59GB | Very high quality, near perfect, *recommended*. |
| [Hathor_Enigmatica-L3-8B-v0.4-Q5_K_L.gguf](https://huggingface.co/bartowski/Hathor_Enigmatica-L3-8B-v0.4-GGUF/blob/main/Hathor_Enigmatica-L3-8B-v0.4-Q5_K_L.gguf) | Q5_K_L | 7.04GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. High quality, *recommended*. |
| [Hathor_Enigmatica-L3-8B-v0.4-Q5_K_M.gguf](https://huggingface.co/bartowski/Hathor_Enigmatica-L3-8B-v0.4-GGUF/blob/main/Hathor_Enigmatica-L3-8B-v0.4-Q5_K_M.gguf) | Q5_K_M | 5.73GB | High quality, *recommended*. |
| [Hathor_Enigmatica-L3-8B-v0.4-Q5_K_S.gguf](https://huggingface.co/bartowski/Hathor_Enigmatica-L3-8B-v0.4-GGUF/blob/main/Hathor_Enigmatica-L3-8B-v0.4-Q5_K_S.gguf) | Q5_K_S | 5.59GB | High quality, *recommended*. |
| [Hathor_Enigmatica-L3-8B-v0.4-Q4_K_L.gguf](https://huggingface.co/bartowski/Hathor_Enigmatica-L3-8B-v0.4-GGUF/blob/main/Hathor_Enigmatica-L3-8B-v0.4-Q4_K_L.gguf) | Q4_K_L | 6.29GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. Good quality, uses about 4.83 bits per weight, *recommended*. |
| [Hathor_Enigmatica-L3-8B-v0.4-Q4_K_M.gguf](https://huggingface.co/bartowski/Hathor_Enigmatica-L3-8B-v0.4-GGUF/blob/main/Hathor_Enigmatica-L3-8B-v0.4-Q4_K_M.gguf) | Q4_K_M | 4.92GB | Good quality, uses about 4.83 bits per weight, *recommended*. |
| [Hathor_Enigmatica-L3-8B-v0.4-Q4_K_S.gguf](https://huggingface.co/bartowski/Hathor_Enigmatica-L3-8B-v0.4-GGUF/blob/main/Hathor_Enigmatica-L3-8B-v0.4-Q4_K_S.gguf) | Q4_K_S | 4.69GB | Slightly lower quality with more space savings, *recommended*. |
| [Hathor_Enigmatica-L3-8B-v0.4-IQ4_XS.gguf](https://huggingface.co/bartowski/Hathor_Enigmatica-L3-8B-v0.4-GGUF/blob/main/Hathor_Enigmatica-L3-8B-v0.4-IQ4_XS.gguf) | IQ4_XS | 4.44GB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [Hathor_Enigmatica-L3-8B-v0.4-Q3_K_XL.gguf](https://huggingface.co/bartowski/Hathor_Enigmatica-L3-8B-v0.4-GGUF//main/Hathor_Enigmatica-L3-8B-v0.4-Q3_K_XL.gguf) | Q3_K_XL | | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. Lower quality but usable, good for low RAM availability. |
| [Hathor_Enigmatica-L3-8B-v0.4-Q3_K_L.gguf](https://huggingface.co/bartowski/Hathor_Enigmatica-L3-8B-v0.4-GGUF/blob/main/Hathor_Enigmatica-L3-8B-v0.4-Q3_K_L.gguf) | Q3_K_L | 4.32GB | Lower quality but usable, good for low RAM availability. |
| [Hathor_Enigmatica-L3-8B-v0.4-Q3_K_M.gguf](https://huggingface.co/bartowski/Hathor_Enigmatica-L3-8B-v0.4-GGUF/blob/main/Hathor_Enigmatica-L3-8B-v0.4-Q3_K_M.gguf) | Q3_K_M | 4.01GB | Even lower quality. |
| [Hathor_Enigmatica-L3-8B-v0.4-IQ3_M.gguf](https://huggingface.co/bartowski/Hathor_Enigmatica-L3-8B-v0.4-GGUF/blob/main/Hathor_Enigmatica-L3-8B-v0.4-IQ3_M.gguf) | IQ3_M | 3.78GB | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [Hathor_Enigmatica-L3-8B-v0.4-Q3_K_S.gguf](https://huggingface.co/bartowski/Hathor_Enigmatica-L3-8B-v0.4-GGUF/blob/main/Hathor_Enigmatica-L3-8B-v0.4-Q3_K_S.gguf) | Q3_K_S | 3.66GB | Low quality, not recommended. |
| [Hathor_Enigmatica-L3-8B-v0.4-IQ3_XS.gguf](https://huggingface.co/bartowski/Hathor_Enigmatica-L3-8B-v0.4-GGUF/blob/main/Hathor_Enigmatica-L3-8B-v0.4-IQ3_XS.gguf) | IQ3_XS | 3.51GB | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [Hathor_Enigmatica-L3-8B-v0.4-IQ3_XXS.gguf](https://huggingface.co/bartowski/Hathor_Enigmatica-L3-8B-v0.4-GGUF/blob/main/Hathor_Enigmatica-L3-8B-v0.4-IQ3_XXS.gguf) | IQ3_XXS | 3.27GB | Lower quality, new method with decent performance, comparable to Q3 quants. |
| [Hathor_Enigmatica-L3-8B-v0.4-Q2_K.gguf](https://huggingface.co/bartowski/Hathor_Enigmatica-L3-8B-v0.4-GGUF/blob/main/Hathor_Enigmatica-L3-8B-v0.4-Q2_K.gguf) | Q2_K | 3.17GB | Very low quality but surprisingly usable. |
| [Hathor_Enigmatica-L3-8B-v0.4-IQ2_M.gguf](https://huggingface.co/bartowski/Hathor_Enigmatica-L3-8B-v0.4-GGUF/blob/main/Hathor_Enigmatica-L3-8B-v0.4-IQ2_M.gguf) | IQ2_M | 2.94GB | Very low quality, uses SOTA techniques to also be surprisingly usable. |
| [Hathor_Enigmatica-L3-8B-v0.4-IQ2_S.gguf](https://huggingface.co/bartowski/Hathor_Enigmatica-L3-8B-v0.4-GGUF/blob/main/Hathor_Enigmatica-L3-8B-v0.4-IQ2_S.gguf) | IQ2_S | 2.75GB | Very low quality, uses SOTA techniques to be usable. |
| [Hathor_Enigmatica-L3-8B-v0.4-IQ2_XS.gguf](https://huggingface.co/bartowski/Hathor_Enigmatica-L3-8B-v0.4-GGUF/blob/main/Hathor_Enigmatica-L3-8B-v0.4-IQ2_XS.gguf) | IQ2_XS | 2.60GB | Very low quality, uses SOTA techniques to be usable. |
## Downloading using huggingface-cli
First, make sure you have hugginface-cli installed:
```
pip install -U "huggingface_hub[cli]"
```
Then, you can target the specific file you want:
```
huggingface-cli download bartowski/Hathor_Enigmatica-L3-8B-v0.4-GGUF --include "Hathor_Enigmatica-L3-8B-v0.4-Q4_K_M.gguf" --local-dir ./
```
If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
```
huggingface-cli download bartowski/Hathor_Enigmatica-L3-8B-v0.4-GGUF --include "Hathor_Enigmatica-L3-8B-v0.4-Q8_0.gguf/*" --local-dir Hathor_Enigmatica-L3-8B-v0.4-Q8_0
```
You can either specify a new local-dir (Hathor_Enigmatica-L3-8B-v0.4-Q8_0) or download them all in place (./)
## Which file should I choose?
A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9)
The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.
If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.
If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.
Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.
If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.
If you want to get more into the weeds, you can check out this extremely useful feature chart:
[llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix)
But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.
These I-quants can also be used on CPU and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
The I-quants are *not* compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm.
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
|
bmahak2005/vit-base-patch16-224-finetuned-flower | bmahak2005 | 2024-06-21T21:58:29Z | 6 | 0 | transformers | [
"transformers",
"pytorch",
"vit",
"image-classification",
"generated_from_trainer",
"dataset:imagefolder",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | image-classification | 2024-06-21T21:46:59Z | ---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imagefolder
model-index:
- name: vit-base-patch16-224-finetuned-flower
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# vit-base-patch16-224-finetuned-flower
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
### Training results
### Framework versions
- Transformers 4.24.0
- Pytorch 2.3.0+cu121
- Datasets 2.7.1
- Tokenizers 0.13.3
|
itisarainyday/llemma-2-7b-ft-merged-v5 | itisarainyday | 2024-06-21T21:57:24Z | 6 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-06-21T21:50:27Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
excalibur12/k2e_asr-scr_w2v2-xls-r-300m_001 | excalibur12 | 2024-06-21T21:42:22Z | 6 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"wav2vec2",
"generated_from_trainer",
"base_model:facebook/wav2vec2-xls-r-300m",
"base_model:finetune:facebook/wav2vec2-xls-r-300m",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-06-21T17:49:44Z | ---
license: apache-2.0
base_model: facebook/wav2vec2-xls-r-300m
tags:
- generated_from_trainer
model-index:
- name: nia037-k2e_asr-scoring_wav2vec2-xls-r-300m_001
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# nia037-k2e_asr-scoring_wav2vec2-xls-r-300m_001
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.3285
- Per: 0.1553
- Pcc: 0.5941
- Ctc Loss: 0.4571
- Mse Loss: 0.8435
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 4
- eval_batch_size: 1
- seed: 1111
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 750
- training_steps: 7500
### Training results
| Training Loss | Epoch | Step | Validation Loss | Per | Pcc | Ctc Loss | Mse Loss |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:--------:|:--------:|
| 16.8126 | 1.01 | 750 | 4.5828 | 0.9890 | 0.4831 | 3.7272 | 1.0554 |
| 4.3091 | 2.02 | 1500 | 3.9355 | 0.9627 | 0.5450 | 3.5438 | 0.8425 |
| 3.8448 | 3.02 | 2250 | 3.0227 | 0.7172 | 0.5510 | 2.5638 | 0.8462 |
| 2.2291 | 4.03 | 3000 | 1.6022 | 0.2220 | 0.5692 | 0.6960 | 0.8338 |
| 1.6362 | 5.04 | 3750 | 1.4686 | 0.1785 | 0.5888 | 0.5407 | 0.8311 |
| 1.4014 | 6.05 | 4500 | 1.3709 | 0.1676 | 0.6016 | 0.4993 | 0.7934 |
| 1.1905 | 7.06 | 5250 | 1.3089 | 0.1609 | 0.5990 | 0.4759 | 0.7807 |
| 1.0064 | 8.06 | 6000 | 1.3754 | 0.1574 | 0.5915 | 0.4659 | 0.8560 |
| 0.8526 | 9.07 | 6750 | 1.3020 | 0.1563 | 0.6048 | 0.4602 | 0.8179 |
| 0.7319 | 10.08 | 7500 | 1.3285 | 0.1553 | 0.5941 | 0.4571 | 0.8435 |
### Framework versions
- Transformers 4.38.1
- Pytorch 2.0.1
- Datasets 2.16.1
- Tokenizers 0.15.2
|
HeXtRo6/Moki_ArtStyle_XL | HeXtRo6 | 2024-06-21T21:33:52Z | 7 | 2 | diffusers | [
"diffusers",
"text-to-image",
"stable-diffusion",
"lora",
"template:sd-lora",
"base_model:votepurchase/ponyDiffusionV6XL",
"base_model:adapter:votepurchase/ponyDiffusionV6XL",
"license:unknown",
"region:us"
] | text-to-image | 2024-06-21T10:34:19Z | ---
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
widget:
- text: >-
M0kiArt1,1boy,looking at viewer, bear boy,white fur,on city, city
background,wearing black hoodie,red short, shoes, white socks,happy, blush,
red eyes,dynamic pose, cowboy shot,plump,score_9, score_8_up,
score_7_up,sharp,hd,sharp focus, clear image, 4 finger hands
parameters:
negative_prompt: >-
malformed, missing fingers, extra fingers, one hand with more than 5
fingers, extra digit, fewer digits, fused digit, bad finger, bad digit,
bad-hands-5,umbrella, no umbrella,,bad anatomy, bad hands, three hands,
three legs, bad arms, missing legs, missing arms, poorly drawn face, bad
face, fused face, cloned face, worst face, three crus, extra crus, fused
crus, worst feet, three feet, fused feet, fused thigh, three thigh, fused
thigh, extra thigh, worst thigh, missing fingers, extra fingers, ugly
fingers, long fingers, horn, realistic photo, extra eyes, huge eyes,
2girl, amputation, disconnected limbs, ugly,poorly drawn, bad anatomy, bad
proportions, watercolor painting, brush strokes, 3d, colorless, glitch,
blurry, signature, watermark, bad face, distorted face, messed up eyes,
deformed,bad hands, nose piercing
output:
url: images/ComfyUI_temp_fcrtp_00001_.jpeg
- text: >-
M0kiArt1,1male, white fur, bear male, on park, sitting bench, from below,
suit, formal, sad, looking at viewer, cloudy day,score_9, score_8_up,
score_7_up,sharp,hd,sharp focus, clear image,dynamic,blue hours, depressed,
SFW,black pants,bara,plump,fat,4 finger hands,sad, hands on knee,detailed
face, detailed body,bulge,closed mouth,
parameters:
negative_prompt: >-
malformed, missing fingers, extra fingers, one hand with more than 5
fingers, extra digit, fewer digits, fused digit, bad finger, bad digit,
bad-hands-5,umbrella, no umbrella,,bad anatomy, bad hands, three hands,
three legs, bad arms, missing legs, missing arms, poorly drawn face, bad
face, fused face, cloned face, worst face, three crus, extra crus, fused
crus, worst feet, three feet, fused feet, fused thigh, three thigh, fused
thigh, extra thigh, worst thigh, missing fingers, extra fingers, ugly
fingers, long fingers, horn, realistic photo, extra eyes, huge eyes,
2girl, amputation, disconnected limbs, ugly,poorly drawn, bad anatomy, bad
proportions, watercolor painting, brush strokes, 3d, colorless, glitch,
blurry, signature, watermark, bad face, distorted face, messed up eyes,
deformed,bad hands, nose piercing
output:
url: images/ComfyUI_temp_hdjml_00001_.jpeg
- text: >-
M0kiArt1,1boy,looking down,unhappy,sad,from side,backpack,camper, dog
boy,brown fur,on forest, forest background,wearing green sweater,blue
short,shoes, white socks,not happy,raining,puddle, blush, green
eyes,furry,dog tail,plump,score_9, score_8_up, score_7_up,sharp,hd,sharp
focus, clear image, 4 finger hands,reflection,solo, full body, black
pants,SFW,wet,dimm light, lens flare,bloom,ears down
parameters:
negative_prompt: >-
malformed, missing fingers, extra fingers, one hand with more than 5
fingers, extra digit, fewer digits, fused digit, bad finger, bad digit,
bad-hands-5,umbrella, no umbrella,,bad anatomy, bad hands, three hands,
three legs, bad arms, missing legs, missing arms, poorly drawn face, bad
face, fused face, cloned face, worst face, three crus, extra crus, fused
crus, worst feet, three feet, fused feet, fused thigh, three thigh, fused
thigh, extra thigh, worst thigh, missing fingers, extra fingers, ugly
fingers, long fingers, horn, realistic photo, extra eyes, huge eyes,
2girl, amputation, disconnected limbs, ugly,poorly drawn, bad anatomy, bad
proportions, watercolor painting, brush strokes, 3d, colorless, glitch,
blurry, signature, watermark, bad face, distorted face, messed up eyes,
deformed,bad hands, nose piercing
output:
url: images/ComfyUI_temp_vclsb_00001_.jpeg
base_model: votepurchase/ponyDiffusionV6XL
instance_prompt: m0kiart1, 1boy, 1male, furry, plump
license: unknown
---
# M0ki Artstyle
<Gallery />
## Model description
(XL)LoRa Model for Moki Lovers ;)
well if you using this model (or search for it) then already know what's going on so... yea..
If you encounter any issues, consider duplicating the prompts from the provided samples and using them as a creative springboard.
This LoRa model has been fine-tuned using the Pony Diffusion V6 XL available on the CivitAI.
Positive comments and ratings are highly appreciated! Don't forget to share your imaginative creations in the gallery section.
This versatile model is proficient in generating both SFW and NSFW content.
Thank you, and happy creating!
(Purpose and Content: This model is designed to facilitate the creation of images, potentially in the style of the artist "Moki." It contains information and parameters that may influence the output to resemble Moki's art style. This model was developed as part of a personal project and represents my first XL LoRa creation.
Compliance with Laws: You are responsible for ensuring that your use of the model and any generated images complies with all applicable laws, regulations, and standards.
User Responsibility: You are solely responsible for determining the appropriateness of using the model and any images generated by it.)
## Trigger words
You should use `m0kiart1` to trigger the image generation.
You should use `1boy` to trigger the image generation.
You should use `1male` to trigger the image generation.
You should use `furry` to trigger the image generation.
You should use `plump` to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
[Download](/HeXtRo6/Moki_ArtStyle_XL/tree/main) them in the Files & versions tab.
|
bartowski/llama3-turbcat-instruct-8b-GGUF | bartowski | 2024-06-21T21:11:27Z | 342 | 5 | null | [
"gguf",
"text-generation",
"license:llama3",
"endpoints_compatible",
"region:us",
"conversational"
] | text-generation | 2024-06-21T20:21:03Z | ---
license: llama3
quantized_by: bartowski
pipeline_tag: text-generation
---
## Llamacpp imatrix Quantizations of llama3-turbcat-instruct-8b
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b3197">b3197</a> for quantization.
Original model: https://huggingface.co/turboderp/llama3-turbcat-instruct-8b
All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
## Prompt format
```
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
```
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Description |
| -------- | ---------- | --------- | ----------- |
| [llama3-turbcat-instruct-8b-Q8_0_L.gguf](https://huggingface.co/bartowski/llama3-turbcat-instruct-8b-GGUF/blob/main/llama3-turbcat-instruct-8b-Q8_1.gguf) | Q8_0_L | 9.52GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. Extremely high quality, generally unneeded but max available quant. |
| [llama3-turbcat-instruct-8b-Q8_0.gguf](https://huggingface.co/bartowski/llama3-turbcat-instruct-8b-GGUF/blob/main/llama3-turbcat-instruct-8b-Q8_0.gguf) | Q8_0 | 8.54GB | Extremely high quality, generally unneeded but max available quant. |
| [llama3-turbcat-instruct-8b-Q6_K_L.gguf](https://huggingface.co/bartowski/llama3-turbcat-instruct-8b-GGUF/blob/main/llama3-turbcat-instruct-8b-Q6_K_L.gguf) | Q6_K_L | 7.83GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. Very high quality, near perfect, *recommended*. |
| [llama3-turbcat-instruct-8b-Q6_K.gguf](https://huggingface.co/bartowski/llama3-turbcat-instruct-8b-GGUF/blob/main/llama3-turbcat-instruct-8b-Q6_K.gguf) | Q6_K | 6.59GB | Very high quality, near perfect, *recommended*. |
| [llama3-turbcat-instruct-8b-Q5_K_L.gguf](https://huggingface.co/bartowski/llama3-turbcat-instruct-8b-GGUF/blob/main/llama3-turbcat-instruct-8b-Q5_K_L.gguf) | Q5_K_L | 7.04GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. High quality, *recommended*. |
| [llama3-turbcat-instruct-8b-Q5_K_M.gguf](https://huggingface.co/bartowski/llama3-turbcat-instruct-8b-GGUF/blob/main/llama3-turbcat-instruct-8b-Q5_K_M.gguf) | Q5_K_M | 5.73GB | High quality, *recommended*. |
| [llama3-turbcat-instruct-8b-Q5_K_S.gguf](https://huggingface.co/bartowski/llama3-turbcat-instruct-8b-GGUF/blob/main/llama3-turbcat-instruct-8b-Q5_K_S.gguf) | Q5_K_S | 5.59GB | High quality, *recommended*. |
| [llama3-turbcat-instruct-8b-Q4_K_L.gguf](https://huggingface.co/bartowski/llama3-turbcat-instruct-8b-GGUF/blob/main/llama3-turbcat-instruct-8b-Q4_K_L.gguf) | Q4_K_L | 6.29GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. Good quality, uses about 4.83 bits per weight, *recommended*. |
| [llama3-turbcat-instruct-8b-Q4_K_M.gguf](https://huggingface.co/bartowski/llama3-turbcat-instruct-8b-GGUF/blob/main/llama3-turbcat-instruct-8b-Q4_K_M.gguf) | Q4_K_M | 4.92GB | Good quality, uses about 4.83 bits per weight, *recommended*. |
| [llama3-turbcat-instruct-8b-Q4_K_S.gguf](https://huggingface.co/bartowski/llama3-turbcat-instruct-8b-GGUF/blob/main/llama3-turbcat-instruct-8b-Q4_K_S.gguf) | Q4_K_S | 4.69GB | Slightly lower quality with more space savings, *recommended*. |
| [llama3-turbcat-instruct-8b-IQ4_XS.gguf](https://huggingface.co/bartowski/llama3-turbcat-instruct-8b-GGUF/blob/main/llama3-turbcat-instruct-8b-IQ4_XS.gguf) | IQ4_XS | 4.44GB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [llama3-turbcat-instruct-8b-Q3_K_XL.gguf](https://huggingface.co/bartowski/llama3-turbcat-instruct-8b-GGUF//main/llama3-turbcat-instruct-8b-Q3_K_XL.gguf) | Q3_K_XL | | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. Lower quality but usable, good for low RAM availability. |
| [llama3-turbcat-instruct-8b-Q3_K_L.gguf](https://huggingface.co/bartowski/llama3-turbcat-instruct-8b-GGUF/blob/main/llama3-turbcat-instruct-8b-Q3_K_L.gguf) | Q3_K_L | 4.32GB | Lower quality but usable, good for low RAM availability. |
| [llama3-turbcat-instruct-8b-Q3_K_M.gguf](https://huggingface.co/bartowski/llama3-turbcat-instruct-8b-GGUF/blob/main/llama3-turbcat-instruct-8b-Q3_K_M.gguf) | Q3_K_M | 4.01GB | Even lower quality. |
| [llama3-turbcat-instruct-8b-IQ3_M.gguf](https://huggingface.co/bartowski/llama3-turbcat-instruct-8b-GGUF/blob/main/llama3-turbcat-instruct-8b-IQ3_M.gguf) | IQ3_M | 3.78GB | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [llama3-turbcat-instruct-8b-Q3_K_S.gguf](https://huggingface.co/bartowski/llama3-turbcat-instruct-8b-GGUF/blob/main/llama3-turbcat-instruct-8b-Q3_K_S.gguf) | Q3_K_S | 3.66GB | Low quality, not recommended. |
| [llama3-turbcat-instruct-8b-IQ3_XS.gguf](https://huggingface.co/bartowski/llama3-turbcat-instruct-8b-GGUF/blob/main/llama3-turbcat-instruct-8b-IQ3_XS.gguf) | IQ3_XS | 3.51GB | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [llama3-turbcat-instruct-8b-IQ3_XXS.gguf](https://huggingface.co/bartowski/llama3-turbcat-instruct-8b-GGUF/blob/main/llama3-turbcat-instruct-8b-IQ3_XXS.gguf) | IQ3_XXS | 3.27GB | Lower quality, new method with decent performance, comparable to Q3 quants. |
| [llama3-turbcat-instruct-8b-Q2_K.gguf](https://huggingface.co/bartowski/llama3-turbcat-instruct-8b-GGUF/blob/main/llama3-turbcat-instruct-8b-Q2_K.gguf) | Q2_K | 3.17GB | Very low quality but surprisingly usable. |
| [llama3-turbcat-instruct-8b-IQ2_M.gguf](https://huggingface.co/bartowski/llama3-turbcat-instruct-8b-GGUF/blob/main/llama3-turbcat-instruct-8b-IQ2_M.gguf) | IQ2_M | 2.94GB | Very low quality, uses SOTA techniques to also be surprisingly usable. |
| [llama3-turbcat-instruct-8b-IQ2_S.gguf](https://huggingface.co/bartowski/llama3-turbcat-instruct-8b-GGUF/blob/main/llama3-turbcat-instruct-8b-IQ2_S.gguf) | IQ2_S | 2.75GB | Very low quality, uses SOTA techniques to be usable. |
| [llama3-turbcat-instruct-8b-IQ2_XS.gguf](https://huggingface.co/bartowski/llama3-turbcat-instruct-8b-GGUF/blob/main/llama3-turbcat-instruct-8b-IQ2_XS.gguf) | IQ2_XS | 2.60GB | Very low quality, uses SOTA techniques to be usable. |
## Downloading using huggingface-cli
First, make sure you have hugginface-cli installed:
```
pip install -U "huggingface_hub[cli]"
```
Then, you can target the specific file you want:
```
huggingface-cli download bartowski/llama3-turbcat-instruct-8b-GGUF --include "llama3-turbcat-instruct-8b-Q4_K_M.gguf" --local-dir ./
```
If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
```
huggingface-cli download bartowski/llama3-turbcat-instruct-8b-GGUF --include "llama3-turbcat-instruct-8b-Q8_0.gguf/*" --local-dir llama3-turbcat-instruct-8b-Q8_0
```
You can either specify a new local-dir (llama3-turbcat-instruct-8b-Q8_0) or download them all in place (./)
## Which file should I choose?
A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9)
The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.
If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.
If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.
Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.
If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.
If you want to get more into the weeds, you can check out this extremely useful feature chart:
[llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix)
But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.
These I-quants can also be used on CPU and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
The I-quants are *not* compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm.
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
|
tomaarsen/mpnet-base-gooaq-hard-negatives | tomaarsen | 2024-06-21T20:52:23Z | 14 | 0 | sentence-transformers | [
"sentence-transformers",
"safetensors",
"mpnet",
"sentence-similarity",
"feature-extraction",
"generated_from_trainer",
"dataset_size:2286783",
"loss:MultipleNegativesRankingLoss",
"en",
"dataset:tomaarsen/gooaq-hard-negatives",
"dataset:sentence-transformers/gooaq",
"arxiv:1908.10084",
"arxiv:1705.00652",
"base_model:microsoft/mpnet-base",
"base_model:finetune:microsoft/mpnet-base",
"license:apache-2.0",
"model-index",
"co2_eq_emissions",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | sentence-similarity | 2024-06-21T20:51:56Z | ---
base_model: microsoft/mpnet-base
datasets:
- tomaarsen/gooaq-hard-negatives
- sentence-transformers/gooaq
language:
- en
library_name: sentence-transformers
license: apache-2.0
metrics:
- cosine_accuracy@1
- cosine_accuracy@3
- cosine_accuracy@5
- cosine_accuracy@10
- cosine_precision@1
- cosine_precision@3
- cosine_precision@5
- cosine_precision@10
- cosine_recall@1
- cosine_recall@3
- cosine_recall@5
- cosine_recall@10
- cosine_ndcg@10
- cosine_mrr@10
- cosine_map@100
- dot_accuracy@1
- dot_accuracy@3
- dot_accuracy@5
- dot_accuracy@10
- dot_precision@1
- dot_precision@3
- dot_precision@5
- dot_precision@10
- dot_recall@1
- dot_recall@3
- dot_recall@5
- dot_recall@10
- dot_ndcg@10
- dot_mrr@10
- dot_map@100
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:2286783
- loss:MultipleNegativesRankingLoss
widget:
- source_sentence: how to download a youtube video onto usb?
sentences:
- Copy YouTube URL to Download Go to YouTube video you want to download to USB and
copy its URL. Paste the link to download YouTube. Choose a necessary video or
audio format and quality.
- Before surgeons are qualified to operate, they must meet a set of challenging
education requirements. These generally include four years of undergraduate study,
four years of medical school leading to a Doctor of Medicine (M.D.) degree, and
three to eight years of surgical residency at a hospital.
- A Roman numeral representing the number eighteen (18).
- source_sentence: what is the best diet for a leaky gut?
sentences:
- When a woman is pregnant, she does not continue to ovulate and will not have a
period. Menstruation only occurs when a person is not pregnant. Although it is
possible for women to experience some bleeding during pregnancy, this will not
be due to their menstrual cycle.
- To combat leaky gut, eat foods that promote the growth of healthy gut bacteria,
including fruits, cultured dairy products, healthy fats, lean meats, and fibrous
and fermented vegetables.
- Popcorn Ceiling vs Asbestos Popcorn Ceiling Removal Cost CostHelper says Popcorn
ceilings not containing asbestos can expect to pay about $1 to $3 per square foot
or $250 to $900 to remove a popcorn ceiling from a 15'x20' room or $1,200 to $1,400
for a 1,6000 sq.
- source_sentence: what is the difference between joint tenancy and common tenancy?
sentences:
- You (TV series) You is an American psychological thriller television series developed
by Greg Berlanti and Sera Gamble. ... In December 2018, it was announced that
the series would move to Netflix as a Netflix Original title. The second season
was released exclusively on Netflix on December 26, 2019.
- A normal resting heart rate range is between 60 and 100 bpm.
- Joint tenancy also differs from tenancy in common because when one joint tenant
dies, the other remaining joint tenants inherit the deceased tenant's interest
in the property. However, a joint tenancy does allow owners to sell their interests.
If one owner sells, the tenancy is converted to a tenancy in common.
- source_sentence: what is the cause of blood clots in urine?
sentences:
- If sufficient blood is present in the urine, the blood may form a clot. The clot
can completely block the flow of urine, causing sudden extreme pain and inability
to urinate. Bleeding severe enough to cause such a clot is usually caused by an
injury to the urinary tract.
- Distance is the magnitude (length) of the displacement vector. Path length is
how far the object moved as it traveled from its initial position to its final
position.
- In fact, the brand is consistently ranked near the top of automakers in terms
of the most expensive cars to maintain. The total maintenance costs of the average
Audi over a 10-year span is $12,400. ... All cars are different, and many require
more maintenance than some depending on their age and driving history.
- source_sentence: are hard seltzers malt liquor?
sentences:
- The BCD method measures the distance from the apex of the breast down to the wire
line directly below it. That measurement in inches will determine your cup and
frame size. Then take your Rib Cage measurement directly under your bra. ... For
example, the BCD might be 4.0 and the Rib Cage of 32.
- Seltzer is carbonated water. “Hard seltzer” is a flavored malt beverage — essentially
the same as a Lime-A-Rita or a Colt 45 or a Smirnoff Ice. These products derive
their alcohol from fermented malted grains and are then carbonated, flavored and
sweetened.
- Bleaching action of chlorine is based on oxidation while that of sulphur is based
on reduction. Chlorine acts with water to produce nascent oxygen. ... Sulphour
dioxide removes oxygen from the coloured substance and makes it colourless.
co2_eq_emissions:
emissions: 1550.677005890232
energy_consumed: 3.989372336366245
source: codecarbon
training_type: fine-tuning
on_cloud: false
cpu_model: 13th Gen Intel(R) Core(TM) i7-13700K
ram_total_size: 31.777088165283203
hours_used: 11.599
hardware_used: 1 x NVIDIA GeForce RTX 3090
model-index:
- name: MPNet base trained on GooAQ triplets with hard negatives
results:
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: gooaq dev
type: gooaq-dev
metrics:
- type: cosine_accuracy@1
value: 0.7413
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.8697
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.9055
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.9427
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.7413
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.2899
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.1811
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.09427000000000002
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.7413
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.8697
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.9055
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.9427
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.8441925656083314
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.8123759920634883
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.8147743017171518
name: Cosine Map@100
- type: dot_accuracy@1
value: 0.7384
name: Dot Accuracy@1
- type: dot_accuracy@3
value: 0.8669
name: Dot Accuracy@3
- type: dot_accuracy@5
value: 0.9039
name: Dot Accuracy@5
- type: dot_accuracy@10
value: 0.9389
name: Dot Accuracy@10
- type: dot_precision@1
value: 0.7384
name: Dot Precision@1
- type: dot_precision@3
value: 0.28896666666666665
name: Dot Precision@3
- type: dot_precision@5
value: 0.18078000000000002
name: Dot Precision@5
- type: dot_precision@10
value: 0.09389000000000002
name: Dot Precision@10
- type: dot_recall@1
value: 0.7384
name: Dot Recall@1
- type: dot_recall@3
value: 0.8669
name: Dot Recall@3
- type: dot_recall@5
value: 0.9039
name: Dot Recall@5
- type: dot_recall@10
value: 0.9389
name: Dot Recall@10
- type: dot_ndcg@10
value: 0.8410831459293242
name: Dot Ndcg@10
- type: dot_mrr@10
value: 0.8094504365079324
name: Dot Mrr@10
- type: dot_map@100
value: 0.8120497186357559
name: Dot Map@100
---
# MPNet base trained on GooAQ triplets with hard negatives
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [microsoft/mpnet-base](https://huggingface.co/microsoft/mpnet-base) on the [train](https://huggingface.co/datasets/tomaarsen/gooaq-hard-negatives) dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
## Model Details
### Model Description
- **Model Type:** Sentence Transformer
- **Base model:** [microsoft/mpnet-base](https://huggingface.co/microsoft/mpnet-base) <!-- at revision 6996ce1e91bd2a9c7d7f61daec37463394f73f09 -->
- **Maximum Sequence Length:** 512 tokens
- **Output Dimensionality:** 768 tokens
- **Similarity Function:** Cosine Similarity
- **Training Dataset:**
- [train](https://huggingface.co/datasets/tomaarsen/gooaq-hard-negatives)
- **Language:** en
- **License:** apache-2.0
### Model Sources
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
### Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: MPNetModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)
```
## Usage
### Direct Usage (Sentence Transformers)
First install the Sentence Transformers library:
```bash
pip install -U sentence-transformers
```
Then you can load this model and run inference.
```python
from sentence_transformers import SentenceTransformer
# Download from the 🤗 Hub
model = SentenceTransformer("tomaarsen/mpnet-base-gooaq-hard-negatives")
# Run inference
sentences = [
'are hard seltzers malt liquor?',
'Seltzer is carbonated water. “Hard seltzer” is a flavored malt beverage — essentially the same as a Lime-A-Rita or a Colt 45 or a Smirnoff Ice. These products derive their alcohol from fermented malted grains and are then carbonated, flavored and sweetened.',
'Bleaching action of chlorine is based on oxidation while that of sulphur is based on reduction. Chlorine acts with water to produce nascent oxygen. ... Sulphour dioxide removes oxygen from the coloured substance and makes it colourless.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]
# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]
```
<!--
### Direct Usage (Transformers)
<details><summary>Click to see the direct usage in Transformers</summary>
</details>
-->
<!--
### Downstream Usage (Sentence Transformers)
You can finetune this model on your own dataset.
<details><summary>Click to expand</summary>
</details>
-->
<!--
### Out-of-Scope Use
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
-->
## Evaluation
### Metrics
#### Information Retrieval
* Dataset: `gooaq-dev`
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| cosine_accuracy@1 | 0.7413 |
| cosine_accuracy@3 | 0.8697 |
| cosine_accuracy@5 | 0.9055 |
| cosine_accuracy@10 | 0.9427 |
| cosine_precision@1 | 0.7413 |
| cosine_precision@3 | 0.2899 |
| cosine_precision@5 | 0.1811 |
| cosine_precision@10 | 0.0943 |
| cosine_recall@1 | 0.7413 |
| cosine_recall@3 | 0.8697 |
| cosine_recall@5 | 0.9055 |
| cosine_recall@10 | 0.9427 |
| cosine_ndcg@10 | 0.8442 |
| cosine_mrr@10 | 0.8124 |
| **cosine_map@100** | **0.8148** |
| dot_accuracy@1 | 0.7384 |
| dot_accuracy@3 | 0.8669 |
| dot_accuracy@5 | 0.9039 |
| dot_accuracy@10 | 0.9389 |
| dot_precision@1 | 0.7384 |
| dot_precision@3 | 0.289 |
| dot_precision@5 | 0.1808 |
| dot_precision@10 | 0.0939 |
| dot_recall@1 | 0.7384 |
| dot_recall@3 | 0.8669 |
| dot_recall@5 | 0.9039 |
| dot_recall@10 | 0.9389 |
| dot_ndcg@10 | 0.8411 |
| dot_mrr@10 | 0.8095 |
| dot_map@100 | 0.812 |
<!--
## Bias, Risks and Limitations
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
-->
<!--
### Recommendations
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
-->
## Training Details
### Training Dataset
#### train
* Dataset: [train](https://huggingface.co/datasets/tomaarsen/gooaq-hard-negatives) at [87594a1](https://huggingface.co/datasets/tomaarsen/gooaq-hard-negatives/tree/87594a1e6c58e88b5843afa9da3a97ffd75d01c2)
* Size: 2,286,783 training samples
* Columns: <code>question</code>, <code>answer</code>, <code>negative_1</code>, <code>negative_2</code>, <code>negative_3</code>, <code>negative_4</code>, and <code>negative_5</code>
* Approximate statistics based on the first 1000 samples:
| | question | answer | negative_1 | negative_2 | negative_3 | negative_4 | negative_5 |
|:--------|:----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
| type | string | string | string | string | string | string | string |
| details | <ul><li>min: 8 tokens</li><li>mean: 11.84 tokens</li><li>max: 23 tokens</li></ul> | <ul><li>min: 13 tokens</li><li>mean: 59.41 tokens</li><li>max: 158 tokens</li></ul> | <ul><li>min: 13 tokens</li><li>mean: 59.09 tokens</li><li>max: 139 tokens</li></ul> | <ul><li>min: 14 tokens</li><li>mean: 58.61 tokens</li><li>max: 139 tokens</li></ul> | <ul><li>min: 14 tokens</li><li>mean: 58.98 tokens</li><li>max: 173 tokens</li></ul> | <ul><li>min: 15 tokens</li><li>mean: 59.43 tokens</li><li>max: 137 tokens</li></ul> | <ul><li>min: 13 tokens</li><li>mean: 60.03 tokens</li><li>max: 146 tokens</li></ul> |
* Samples:
| question | answer | negative_1 | negative_2 | negative_3 | negative_4 | negative_5 |
|:---------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| <code>is toprol xl the same as metoprolol?</code> | <code>Metoprolol succinate is also known by the brand name Toprol XL. It is the extended-release form of metoprolol. Metoprolol succinate is approved to treat high blood pressure, chronic chest pain, and congestive heart failure.</code> | <code>Secondly, metoprolol and metoprolol ER have different brand-name equivalents: Brand version of metoprolol: Lopressor. Brand version of metoprolol ER: Toprol XL.</code> | <code>Pill with imprint 1 is White, Round and has been identified as Metoprolol Tartrate 25 mg.</code> | <code>Interactions between your drugs No interactions were found between Allergy Relief and metoprolol. This does not necessarily mean no interactions exist. Always consult your healthcare provider.</code> | <code>Metoprolol is a type of medication called a beta blocker. It works by relaxing blood vessels and slowing heart rate, which improves blood flow and lowers blood pressure. Metoprolol can also improve the likelihood of survival after a heart attack.</code> | <code>Metoprolol starts to work after about 2 hours, but it can take up to 1 week to fully take effect. You may not feel any different when you take metoprolol, but this doesn't mean it's not working. It's important to keep taking your medicine.</code> |
| <code>are you experienced cd steve hoffman?</code> | <code>The Are You Experienced album was apparently mastered from the original stereo UK master tapes (according to Steve Hoffman - one of the very few who has heard both the master tapes and the CDs produced over the years). ... The CD booklets were a little sparse, but at least they stayed true to the album's original design.</code> | <code>I Saw the Light. Showcasing the unique talent and musical influence of country-western artist Hank Williams, this candid biography also sheds light on the legacy of drug abuse and tormented relationships that contributes to the singer's legend.</code> | <code>(Read our ranking of his top 10.) And while Howard dresses the part of director, any notion of him as a tortured auteur or dictatorial taskmasker — the clichés of the Hollywood director — are tossed aside. He's very nice.</code> | <code>He was a music star too. Where're you people born and brought up? We 're born and brought up here in Anambra State at Nkpor town, near Onitsha.</code> | <code>At the age of 87 he has now retired from his live shows and all the traveling involved. And although he still picks up his Martin Guitar and does a show now and then, his life is now devoted to writing his memoirs.</code> | <code>The owner of the mysterious voice behind all these videos is a man who's seen a lot, visiting a total of 56 intimate celebrity spaces over the course of five years. His name is Joe Sabia — that's him in the photo — and he's currently the VP of creative development at Condé Nast Entertainment.</code> |
| <code>how are babushka dolls made?</code> | <code>Matryoshka dolls are made of wood from lime, balsa, alder, aspen, and birch trees; lime is probably the most common wood type. ... After cutting, the trees are stripped of most of their bark, although a few inner rings of bark are left to bind the wood and keep it from splitting.</code> | <code>A quick scan of the auction and buy-it-now listings on eBay finds porcelain doll values ranging from around $5 and $10 to several thousand dollars or more but no dolls listed above $10,000.</code> | <code>Japanese dolls are called as ningyō in Japanese and literally translates to 'human form'.</code> | <code>Matyoo: All Fresno Girl dolls come just as real children are born.</code> | <code>As of September 2016, there are over 100 characters. The main toy line includes 13-inch Dolls, the mini-series, and a variety of mini play-sets and plush dolls as well as Lalaloopsy Littles, smaller siblings of the 13-inch dolls. A spin-off known as "Lala-Oopsies" came out in late 2012.</code> | <code>LOL dolls are little baby dolls that come wrapped inside a surprise toy ball. Each ball has layers that contain stickers, secret messages, mix and match accessories–and finally–a doll. ... The doll on the ball is almost never the doll inside. Dolls are released in series, so not every doll is available all the time.</code> |
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "cos_sim"
}
```
### Evaluation Dataset
#### sentence-transformers/gooaq
* Dataset: [sentence-transformers/gooaq](https://huggingface.co/datasets/sentence-transformers/gooaq) at [b089f72](https://huggingface.co/datasets/sentence-transformers/gooaq/tree/b089f728748a068b7bc5234e5bcf5b25e3c8279c)
* Size: 10,000 evaluation samples
* Columns: <code>question</code> and <code>answer</code>
* Approximate statistics based on the first 1000 samples:
| | question | answer |
|:--------|:----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
| type | string | string |
| details | <ul><li>min: 8 tokens</li><li>mean: 11.89 tokens</li><li>max: 22 tokens</li></ul> | <ul><li>min: 14 tokens</li><li>mean: 59.65 tokens</li><li>max: 131 tokens</li></ul> |
* Samples:
| question | answer |
|:-------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| <code>how to transfer data from ipad to usb?</code> | <code>First, in “Locations,” tap the “On My iPhone” or “On My iPad” section. Here, tap and hold the empty space, and then select “New Folder.” Name it, and then tap “Done” to create a new folder for the files you want to transfer. Now, from the “Locations” section, select your USB flash drive.</code> |
| <code>what quorn products are syn free?</code> | <code>['bacon style pieces.', 'bacon style rashers, chilled.', 'BBQ sliced fillets.', 'beef style and red onion burgers.', 'pieces.', 'chicken style slices.', 'fajita strips.', 'family roast.']</code> |
| <code>what is the difference between turmeric ginger?</code> | <code>Ginger offers a sweet and spicy zing to dishes. Turmeric provides a golden yellow colour and a warm and bitter taste with a peppery aroma.</code> |
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "cos_sim"
}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `eval_strategy`: steps
- `per_device_train_batch_size`: 32
- `per_device_eval_batch_size`: 32
- `learning_rate`: 2e-05
- `num_train_epochs`: 1
- `warmup_ratio`: 0.1
- `bf16`: True
- `batch_sampler`: no_duplicates
#### All Hyperparameters
<details><summary>Click to expand</summary>
- `overwrite_output_dir`: False
- `do_predict`: False
- `eval_strategy`: steps
- `prediction_loss_only`: True
- `per_device_train_batch_size`: 32
- `per_device_eval_batch_size`: 32
- `per_gpu_train_batch_size`: None
- `per_gpu_eval_batch_size`: None
- `gradient_accumulation_steps`: 1
- `eval_accumulation_steps`: None
- `learning_rate`: 2e-05
- `weight_decay`: 0.0
- `adam_beta1`: 0.9
- `adam_beta2`: 0.999
- `adam_epsilon`: 1e-08
- `max_grad_norm`: 1.0
- `num_train_epochs`: 1
- `max_steps`: -1
- `lr_scheduler_type`: linear
- `lr_scheduler_kwargs`: {}
- `warmup_ratio`: 0.1
- `warmup_steps`: 0
- `log_level`: passive
- `log_level_replica`: warning
- `log_on_each_node`: True
- `logging_nan_inf_filter`: True
- `save_safetensors`: True
- `save_on_each_node`: False
- `save_only_model`: False
- `restore_callback_states_from_checkpoint`: False
- `no_cuda`: False
- `use_cpu`: False
- `use_mps_device`: False
- `seed`: 42
- `data_seed`: None
- `jit_mode_eval`: False
- `use_ipex`: False
- `bf16`: True
- `fp16`: False
- `fp16_opt_level`: O1
- `half_precision_backend`: auto
- `bf16_full_eval`: False
- `fp16_full_eval`: False
- `tf32`: None
- `local_rank`: 0
- `ddp_backend`: None
- `tpu_num_cores`: None
- `tpu_metrics_debug`: False
- `debug`: []
- `dataloader_drop_last`: False
- `dataloader_num_workers`: 0
- `dataloader_prefetch_factor`: None
- `past_index`: -1
- `disable_tqdm`: False
- `remove_unused_columns`: True
- `label_names`: None
- `load_best_model_at_end`: False
- `ignore_data_skip`: False
- `fsdp`: []
- `fsdp_min_num_params`: 0
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
- `fsdp_transformer_layer_cls_to_wrap`: None
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
- `deepspeed`: None
- `label_smoothing_factor`: 0.0
- `optim`: adamw_torch
- `optim_args`: None
- `adafactor`: False
- `group_by_length`: False
- `length_column_name`: length
- `ddp_find_unused_parameters`: None
- `ddp_bucket_cap_mb`: None
- `ddp_broadcast_buffers`: False
- `dataloader_pin_memory`: True
- `dataloader_persistent_workers`: False
- `skip_memory_metrics`: True
- `use_legacy_prediction_loop`: False
- `push_to_hub`: False
- `resume_from_checkpoint`: None
- `hub_model_id`: None
- `hub_strategy`: every_save
- `hub_private_repo`: False
- `hub_always_push`: False
- `gradient_checkpointing`: False
- `gradient_checkpointing_kwargs`: None
- `include_inputs_for_metrics`: False
- `eval_do_concat_batches`: True
- `fp16_backend`: auto
- `push_to_hub_model_id`: None
- `push_to_hub_organization`: None
- `mp_parameters`:
- `auto_find_batch_size`: False
- `full_determinism`: False
- `torchdynamo`: None
- `ray_scope`: last
- `ddp_timeout`: 1800
- `torch_compile`: False
- `torch_compile_backend`: None
- `torch_compile_mode`: None
- `dispatch_batches`: None
- `split_batches`: None
- `include_tokens_per_second`: False
- `include_num_input_tokens_seen`: False
- `neftune_noise_alpha`: None
- `optim_target_modules`: None
- `batch_eval_metrics`: False
- `batch_sampler`: no_duplicates
- `multi_dataset_batch_sampler`: proportional
</details>
### Training Logs
<details><summary>Click to expand</summary>
| Epoch | Step | Training Loss | loss | gooaq-dev_cosine_map@100 |
|:------:|:-----:|:-------------:|:------:|:------------------------:|
| 0 | 0 | - | - | 0.1405 |
| 0.2869 | 20500 | 0.5303 | - | - |
| 0.2939 | 21000 | 0.5328 | - | - |
| 0.3009 | 21500 | 0.515 | - | - |
| 0.3079 | 22000 | 0.5264 | 0.0297 | 0.7919 |
| 0.3149 | 22500 | 0.5189 | - | - |
| 0.3218 | 23000 | 0.5284 | - | - |
| 0.3288 | 23500 | 0.5308 | - | - |
| 0.3358 | 24000 | 0.509 | 0.0281 | 0.7932 |
| 0.3428 | 24500 | 0.5074 | - | - |
| 0.3498 | 25000 | 0.5196 | - | - |
| 0.3568 | 25500 | 0.5041 | - | - |
| 0.3638 | 26000 | 0.4976 | 0.0291 | 0.7950 |
| 0.3708 | 26500 | 0.5025 | - | - |
| 0.3778 | 27000 | 0.5175 | - | - |
| 0.3848 | 27500 | 0.4921 | - | - |
| 0.3918 | 28000 | 0.4924 | 0.0298 | 0.7938 |
| 0.3988 | 28500 | 0.49 | - | - |
| 0.4058 | 29000 | 0.4924 | - | - |
| 0.4128 | 29500 | 0.4902 | - | - |
| 0.4198 | 30000 | 0.4846 | 0.0269 | 0.7966 |
| 0.4268 | 30500 | 0.4815 | - | - |
| 0.4338 | 31000 | 0.4881 | - | - |
| 0.4408 | 31500 | 0.4848 | - | - |
| 0.4478 | 32000 | 0.4882 | 0.0264 | 0.8004 |
| 0.4548 | 32500 | 0.4809 | - | - |
| 0.4618 | 33000 | 0.4896 | - | - |
| 0.4688 | 33500 | 0.4744 | - | - |
| 0.4758 | 34000 | 0.4827 | 0.0252 | 0.8038 |
| 0.4828 | 34500 | 0.4703 | - | - |
| 0.4898 | 35000 | 0.4765 | - | - |
| 0.4968 | 35500 | 0.4625 | - | - |
| 0.5038 | 36000 | 0.4698 | 0.0269 | 0.8025 |
| 0.5108 | 36500 | 0.4666 | - | - |
| 0.5178 | 37000 | 0.4594 | - | - |
| 0.5248 | 37500 | 0.4621 | - | - |
| 0.5318 | 38000 | 0.4538 | 0.0266 | 0.8047 |
| 0.5387 | 38500 | 0.4576 | - | - |
| 0.5457 | 39000 | 0.4594 | - | - |
| 0.5527 | 39500 | 0.4503 | - | - |
| 0.5597 | 40000 | 0.4538 | 0.0265 | 0.8038 |
| 0.5667 | 40500 | 0.4521 | - | - |
| 0.5737 | 41000 | 0.4575 | - | - |
| 0.5807 | 41500 | 0.4544 | - | - |
| 0.5877 | 42000 | 0.4462 | 0.0245 | 0.8077 |
| 0.5947 | 42500 | 0.4491 | - | - |
| 0.6017 | 43000 | 0.4651 | - | - |
| 0.6087 | 43500 | 0.4549 | - | - |
| 0.6157 | 44000 | 0.4461 | 0.0262 | 0.8046 |
| 0.6227 | 44500 | 0.4571 | - | - |
| 0.6297 | 45000 | 0.4478 | - | - |
| 0.6367 | 45500 | 0.4482 | - | - |
| 0.6437 | 46000 | 0.4439 | 0.0244 | 0.8070 |
| 0.6507 | 46500 | 0.4384 | - | - |
| 0.6577 | 47000 | 0.446 | - | - |
| 0.6647 | 47500 | 0.4425 | - | - |
| 0.6717 | 48000 | 0.4308 | 0.0248 | 0.8067 |
| 0.6787 | 48500 | 0.4374 | - | - |
| 0.6857 | 49000 | 0.4342 | - | - |
| 0.6927 | 49500 | 0.4455 | - | - |
| 0.6997 | 50000 | 0.4322 | 0.0242 | 0.8077 |
| 0.7067 | 50500 | 0.4288 | - | - |
| 0.7137 | 51000 | 0.4317 | - | - |
| 0.7207 | 51500 | 0.4295 | - | - |
| 0.7277 | 52000 | 0.4291 | 0.0231 | 0.8130 |
| 0.7347 | 52500 | 0.4279 | - | - |
| 0.7417 | 53000 | 0.4287 | - | - |
| 0.7486 | 53500 | 0.4252 | - | - |
| 0.7556 | 54000 | 0.4341 | 0.0243 | 0.8112 |
| 0.7626 | 54500 | 0.419 | - | - |
| 0.7696 | 55000 | 0.4323 | - | - |
| 0.7766 | 55500 | 0.4252 | - | - |
| 0.7836 | 56000 | 0.4313 | 0.0264 | 0.8107 |
| 0.7906 | 56500 | 0.4222 | - | - |
| 0.7976 | 57000 | 0.4226 | - | - |
| 0.8046 | 57500 | 0.4152 | - | - |
| 0.8116 | 58000 | 0.4222 | 0.0236 | 0.8131 |
| 0.8186 | 58500 | 0.4184 | - | - |
| 0.8256 | 59000 | 0.4144 | - | - |
| 0.8326 | 59500 | 0.4242 | - | - |
| 0.8396 | 60000 | 0.4148 | 0.0242 | 0.8125 |
| 0.8466 | 60500 | 0.4222 | - | - |
| 0.8536 | 61000 | 0.4184 | - | - |
| 0.8606 | 61500 | 0.4138 | - | - |
| 0.8676 | 62000 | 0.4119 | 0.0240 | 0.8133 |
| 0.8746 | 62500 | 0.411 | - | - |
| 0.8816 | 63000 | 0.4172 | - | - |
| 0.8886 | 63500 | 0.4145 | - | - |
| 0.8956 | 64000 | 0.4168 | 0.0240 | 0.8137 |
| 0.9026 | 64500 | 0.4071 | - | - |
| 0.9096 | 65000 | 0.4119 | - | - |
| 0.9166 | 65500 | 0.403 | - | - |
| 0.9236 | 66000 | 0.4092 | 0.0238 | 0.8141 |
| 0.9306 | 66500 | 0.4079 | - | - |
| 0.9376 | 67000 | 0.4129 | - | - |
| 0.9446 | 67500 | 0.4082 | - | - |
| 0.9516 | 68000 | 0.4054 | 0.0235 | 0.8149 |
| 0.9586 | 68500 | 0.4129 | - | - |
| 0.9655 | 69000 | 0.4085 | - | - |
| 0.9725 | 69500 | 0.414 | - | - |
| 0.9795 | 70000 | 0.4075 | 0.0239 | 0.8142 |
| 0.9865 | 70500 | 0.4104 | - | - |
| 0.9935 | 71000 | 0.4087 | - | - |
| 1.0 | 71462 | - | - | 0.8148 |
</details>
### Environmental Impact
Carbon emissions were measured using [CodeCarbon](https://github.com/mlco2/codecarbon).
- **Energy Consumed**: 3.989 kWh
- **Carbon Emitted**: 1.551 kg of CO2
- **Hours Used**: 11.599 hours
### Training Hardware
- **On Cloud**: No
- **GPU Model**: 1 x NVIDIA GeForce RTX 3090
- **CPU Model**: 13th Gen Intel(R) Core(TM) i7-13700K
- **RAM Size**: 31.78 GB
### Framework Versions
- Python: 3.11.6
- Sentence Transformers: 3.1.0.dev0
- Transformers: 4.41.2
- PyTorch: 2.3.0+cu121
- Accelerate: 0.31.0
- Datasets: 2.20.0
- Tokenizers: 0.19.1
## Citation
### BibTeX
#### Sentence Transformers
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "https://arxiv.org/abs/1908.10084",
}
```
#### MultipleNegativesRankingLoss
```bibtex
@misc{henderson2017efficient,
title={Efficient Natural Language Response Suggestion for Smart Reply},
author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
year={2017},
eprint={1705.00652},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
<!--
## Glossary
*Clearly define terms in order to be accessible across audiences.*
-->
<!--
## Model Card Authors
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->
<!--
## Model Card Contact
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
--> |
alielfilali01/Q2AW1M-0100 | alielfilali01 | 2024-06-21T20:42:36Z | 2,907 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"conversational",
"arxiv:1910.09700",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-06-21T13:25:17Z | ---
library_name: transformers
license: apache-2.0
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
alielfilali01/Q2AW1M-1100 | alielfilali01 | 2024-06-21T20:41:52Z | 2,900 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"conversational",
"arxiv:1910.09700",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-06-21T13:48:05Z | ---
library_name: transformers
license: apache-2.0
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
CHE-72/Phi-3-medium-128k-instruct-Q4_0-GGUF | CHE-72 | 2024-06-21T20:41:49Z | 10 | 0 | null | [
"gguf",
"nlp",
"code",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"multilingual",
"base_model:microsoft/Phi-3-medium-128k-instruct",
"base_model:quantized:microsoft/Phi-3-medium-128k-instruct",
"license:mit",
"endpoints_compatible",
"region:us",
"conversational"
] | text-generation | 2024-06-21T20:41:14Z | ---
base_model: microsoft/Phi-3-medium-128k-instruct
language:
- multilingual
license: mit
license_link: https://huggingface.co/microsoft/Phi-3-medium-128k-instruct/resolve/main/LICENSE
pipeline_tag: text-generation
tags:
- nlp
- code
- llama-cpp
- gguf-my-repo
inference:
parameters:
temperature: 0.7
widget:
- messages:
- role: user
content: Can you provide ways to eat combinations of bananas and dragonfruits?
---
# CHE-72/Phi-3-medium-128k-instruct-Q4_0-GGUF
This model was converted to GGUF format from [`microsoft/Phi-3-medium-128k-instruct`](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo CHE-72/Phi-3-medium-128k-instruct-Q4_0-GGUF --hf-file phi-3-medium-128k-instruct-q4_0.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo CHE-72/Phi-3-medium-128k-instruct-Q4_0-GGUF --hf-file phi-3-medium-128k-instruct-q4_0.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo CHE-72/Phi-3-medium-128k-instruct-Q4_0-GGUF --hf-file phi-3-medium-128k-instruct-q4_0.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo CHE-72/Phi-3-medium-128k-instruct-Q4_0-GGUF --hf-file phi-3-medium-128k-instruct-q4_0.gguf -c 2048
```
|
alielfilali01/Q2AW1M-0001 | alielfilali01 | 2024-06-21T20:39:37Z | 2,905 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"conversational",
"arxiv:1910.09700",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-06-21T14:23:16Z | ---
library_name: transformers
license: apache-2.0
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
powermove72/Shark-1-Ogno-7b-passthrough | powermove72 | 2024-06-21T20:31:23Z | 8 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"powermove72/Shark-1",
"eren23/OGNO-7b-dpo-truthful",
"conversational",
"custom_code",
"base_model:eren23/OGNO-7b-dpo-truthful",
"base_model:merge:eren23/OGNO-7b-dpo-truthful",
"base_model:powermove72/Shark-1",
"base_model:merge:powermove72/Shark-1",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-06-21T20:26:54Z | ---
base_model:
- powermove72/Shark-1
- eren23/OGNO-7b-dpo-truthful
tags:
- merge
- mergekit
- lazymergekit
- powermove72/Shark-1
- eren23/OGNO-7b-dpo-truthful
---
# Shark-1-Ogno-7b-passthrough
Shark-1-Ogno-7b-passthrough is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [powermove72/Shark-1](https://huggingface.co/powermove72/Shark-1)
* [eren23/OGNO-7b-dpo-truthful](https://huggingface.co/eren23/OGNO-7b-dpo-truthful)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: powermove72/Shark-1
layer_range: [0, 16]
- sources:
- model: eren23/OGNO-7b-dpo-truthful
layer_range: [16, 32]
merge_method: passthrough
tokenizer_source: union
dtype: float16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "powermove72/Shark-1-Ogno-7b-passthrough"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
``` |
rafaeloc15/llama_question_gguf | rafaeloc15 | 2024-06-21T20:16:26Z | 9 | 0 | transformers | [
"transformers",
"gguf",
"llama",
"text-generation-inference",
"unsloth",
"en",
"base_model:unsloth/llama-3-8b-bnb-4bit",
"base_model:quantized:unsloth/llama-3-8b-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-06-21T19:23:25Z | ---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- gguf
base_model: unsloth/llama-3-8b-bnb-4bit
---
# Uploaded model
- **Developed by:** rafaeloc15
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
AirellPramono/finetuned-fruit-classifier | AirellPramono | 2024-06-21T20:08:18Z | 9 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"vit",
"image-classification",
"generated_from_trainer",
"base_model:ivandrian11/fruit-classifier",
"base_model:finetune:ivandrian11/fruit-classifier",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | image-classification | 2024-06-21T20:01:14Z | ---
license: apache-2.0
base_model: ivandrian11/fruit-classifier
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: finetuned-fruit-classifier
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# finetuned-fruit-classifier
This model is a fine-tuned version of [ivandrian11/fruit-classifier](https://huggingface.co/ivandrian11/fruit-classifier) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1037
- Accuracy: 0.95
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.0057 | 1.0 | 7 | 0.1005 | 0.95 |
| 0.0041 | 2.0 | 14 | 0.1033 | 0.95 |
| 0.0042 | 3.0 | 21 | 0.1037 | 0.95 |
### Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
|
Sobeih22/t5-finetuned-ar-to-arsl3 | Sobeih22 | 2024-06-21T20:06:47Z | 7 | 1 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"t5",
"text2text-generation",
"generated_from_trainer",
"base_model:PRAli22/arat5-arabic-dialects-translation",
"base_model:finetune:PRAli22/arat5-arabic-dialects-translation",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text2text-generation | 2024-05-09T00:19:32Z | ---
license: apache-2.0
base_model: PRAli22/arat5-arabic-dialects-translation
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: t5-finetuned-ar-to-arsl3
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# t5-finetuned-ar-to-arsl3
This model is a fine-tuned version of [PRAli22/arat5-arabic-dialects-translation](https://huggingface.co/PRAli22/arat5-arabic-dialects-translation) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3891
- Bleu: 0.9525
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| No log | 0.99 | 78 | 0.4271 | 0.9497 |
| No log | 1.99 | 157 | 0.3818 | 0.9485 |
| No log | 2.99 | 236 | 0.3428 | 0.9526 |
| No log | 3.99 | 315 | 0.3173 | 0.9527 |
| No log | 5.0 | 394 | 0.3344 | 0.9518 |
| No log | 6.0 | 473 | 0.3455 | 0.9536 |
| 0.0868 | 7.0 | 552 | 0.3598 | 0.9525 |
| 0.0868 | 8.0 | 631 | 0.3672 | 0.9543 |
| 0.0868 | 8.99 | 709 | 0.3574 | 0.9537 |
| 0.0868 | 9.99 | 788 | 0.3664 | 0.9505 |
| 0.0868 | 10.99 | 867 | 0.3750 | 0.9529 |
| 0.0868 | 11.99 | 946 | 0.3805 | 0.9538 |
| 0.054 | 13.0 | 1025 | 0.3885 | 0.9541 |
| 0.054 | 14.0 | 1104 | 0.3874 | 0.9525 |
| 0.054 | 14.83 | 1170 | 0.3891 | 0.9525 |
### Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2
|
sealad886/Llama3-OpenBioLLM-70B | sealad886 | 2024-06-21T20:04:17Z | 18 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"llama-3",
"Mixtral",
"instruct",
"finetune",
"chatml",
"DPO",
"RLHF",
"gpt4",
"distillation",
"heathcare",
"medical",
"clinical",
"med",
"lifescience",
"Pharmaceutical",
"Pharma",
"conversational",
"en",
"arxiv:2305.18290",
"arxiv:2303.13375",
"arxiv:2212.13138",
"arxiv:2305.09617",
"arxiv:2402.07023",
"base_model:meta-llama/Meta-Llama-3-70B-Instruct",
"base_model:finetune:meta-llama/Meta-Llama-3-70B-Instruct",
"license:llama3",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-06-05T22:15:54Z | ---
base_model: meta-llama/Meta-Llama-3-70B-Instruct
tags:
- llama-3
- llama
- Mixtral
- instruct
- finetune
- chatml
- DPO
- RLHF
- gpt4
- distillation
- heathcare
- medical
- clinical
- med
- lifescience
- Pharmaceutical
- Pharma
model-index:
- name: OpenBioLLM-70B
results: []
license: llama3
language:
- en
widget:
- example_title: OpenBioLLM-70B
messages:
- role: system
content: >-
You are an expert and experienced from the healthcare and biomedical
domain with extensive medical knowledge and practical experience.
- role: user
content: How long does it take for newborn jaundice to go away?
output:
text: >-
Newborn jaundice, also known as neonatal jaundice, is a common condition
in newborns where the yellowing of the skin and eyes occurs due to an
elevated level of bilirubin in the blood. Bilirubin is a yellow pigment
that forms when red blood cells break down. In most cases, newborn
jaundice resolves on its own without any specific treatment.
The duration of newborn jaundice can vary depending on several factors
such as the underlying cause, gestational age at birth, and individual
variations in bilirubin metabolism. Here are some general guidelines:
1. Physiological jaundice: This is the most common type of newborn
jaundice and usually appears within 24-72 hours after birth. It tends to
peak between the second and fifth day of life and gradually improves over
the next week or two. By the time the baby is one week old, the jaundice
should have mostly resolved. 2. Breast milk jaundice: This type of
jaundice occurs in breastfed babies and may appear later than
physiological jaundice, typically between the fifth and fourteenth day of
life. It tends to persist for a longer duration but usually resolves
within six weeks after birth. 3. Pathological jaundice: This type of
jaundice is less common and occurs due to an underlying medical condition
that affects bilirubin metabolism or liver function. The duration of
pathological jaundice depends on the specific cause and may require
treatment.
It's important for parents to monitor their newborn's jaundice closely and
seek medical advice if the jaundice progresses rapidly, becomes severe, or
is accompanied by other symptoms such as poor feeding, lethargy, or
excessive sleepiness. In these cases, further evaluation and management
may be necessary. Remember that each baby is unique, and the timing of
jaundice resolution can vary. If you have concerns about your newborn's
jaundice, it's always best to consult with a healthcare professional for
personalized advice and guidance.
---
<div align="center">
<h2 class="alert">Copied pickled Pytorch files from <a href="https://huggingface.co/aaditya/Llama3-OpenBioLLM-70B">aaditya/Llama3-OpenBioLLM-70B</a> for conversion to Safetensors using <a href="https://huggingface.co/spaces/safetensors/convert">https://huggingface.co/spaces/safetensors/convert</a>.
<br>Original Model Card:</h2>
</div>
<div align="center">
<img width="260px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/BrQCb95lmEIFz79QAmoNA.png"></div>
<div align="center">
<h1>Advancing Open-source Large Language Models in Medical Domain</h1>
</div>
<p align="center" style="margin-top: 0px;">
<a href="https://colab.research.google.com/drive/1F5oV20InEYeAJGmBwYF9NM_QhLmjBkKJ?usp=sharing">
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="OpenChat Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 10px; margin-top: 0px; margin-bottom: 0px;"/>
<span class="link-text" style=" margin-right: 5px;">Online Demo</span>
</a> |
<a href="https://github.com/openlifescience-ai">
<img src="https://github.githubassets.com/assets/GitHub-Mark-ea2971cee799.png" alt="GitHub Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/>
<span class="link-text" style=" margin-right: 5px;">GitHub</span>
</a> |
<a href="#">
<img src="https://github.com/alpayariyak/openchat/blob/master/assets/arxiv-logomark-small-square-border.png?raw=true" alt="ArXiv Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/>
<span class="link-text" style="margin-right: 5px;">Paper</span>
</a> |
<a href="https://discord.gg/A5Fjf5zC69">
<img src="https://cloud.githubusercontent.com/assets/6291467/26705903/96c2d66e-477c-11e7-9f4e-f3c0efe96c9a.png" alt="Discord Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/>
<span class="link-text">Discord</span>
</a>
</p>
Introducing OpenBioLLM-70B: A State-of-the-Art Open Source Biomedical Large Language Model
OpenBioLLM-70B is an advanced open source language model designed specifically for the biomedical domain. Developed by Saama AI Labs, this model leverages cutting-edge techniques to achieve state-of-the-art performance on a wide range of biomedical tasks.
🏥 **Biomedical Specialization**: OpenBioLLM-70B is tailored for the unique language and knowledge requirements of the medical and life sciences fields. It was fine-tuned on a vast corpus of high-quality biomedical data, enabling it to understand and generate text with domain-specific accuracy and fluency.
🎓 **Superior Performance**: With 70 billion parameters, OpenBioLLM-70B outperforms other open source biomedical language models of similar scale. It has also demonstrated better results compared to larger proprietary & open-source models like GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 on biomedical benchmarks.
🧠 **Advanced Training Techniques**: OpenBioLLM-70B builds upon the powerful foundations of the **Meta-Llama-3-70B-Instruct** and [Meta-Llama-3-70B-Instruct](meta-llama/Meta-Llama-3-70B-Instruct) models. It incorporates the DPO dataset and fine-tuning recipe along with a custom diverse medical instruction dataset. Key components of the training pipeline include:
<div align="center">
<img width="1200px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/oPchsJsEpQoGcGXVbh7YS.png">
</div>
- **Policy Optimization**: [Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)](https://arxiv.org/abs/2305.18290)
- **Fine-tuning dataset**: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated)
This combination of cutting-edge techniques enables OpenBioLLM-70B to align with key capabilities and preferences for biomedical applications.
⚙️ **Release Details**:
- **Model Size**: 70 billion parameters
- **Quantization**: Optimized quantized versions available [Here](https://huggingface.co/aaditya/OpenBioLLM-70B-GGUF)
- **Language(s) (NLP):** en
- **Developed By**: [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) from Saama AI Labs
- **License:** Meta-Llama License
- **Fine-tuned from models:** [Meta-Llama-3-70B-Instruct](meta-llama/Meta-Llama-3-70B-Instruct)
- **Resources for more information:**
- Paper: Coming soon
The model can be fine-tuned for more specialized tasks and datasets as needed.
OpenBioLLM-70B represents an important step forward in democratizing advanced language AI for the biomedical community. By leveraging state-of-the-art architectures and training techniques from leading open source efforts like Llama-3, we have created a powerful tool to accelerate innovation and discovery in healthcare and the life sciences.
We are excited to share OpenBioLLM-70B with researchers and developers around the world.
### Use with transformers
**Important: Please use the exact chat template provided by Llama-3 instruct version. Otherwise there will be a degradation in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less.**
See the snippet below for usage with Transformers:
```python
import transformers
import torch
model_id = "aaditya/OpenBioLLM-Llama3-70B"
pipeline = transformers.pipeline(
"text-generation",
model=model_id,
model_kwargs={"torch_dtype": torch.bfloat16},
device="auto",
)
messages = [
{"role": "system", "content": "You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience. Your name is OpenBioLLM, and you were developed by Saama AI Labs. who's willing to help answer the user's query with explanation. In your explanation, leverage your deep medical expertise such as relevant anatomical structures, physiological processes, diagnostic criteria, treatment guidelines, or other pertinent medical concepts. Use precise medical terminology while still aiming to make the explanation clear and accessible to a general audience."},
{"role": "user", "content": "How can i split a 3mg or 4mg waefin pill so i can get a 2.5mg pill?"},
]
prompt = pipeline.tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
terminators = [
pipeline.tokenizer.eos_token_id,
pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
]
outputs = pipeline(
prompt,
max_new_tokens=256,
eos_token_id=terminators,
do_sample=True,
temperature=0.0,
top_p=0.9,
)
print(outputs[0]["generated_text"][len(prompt):])
```
## **Training procedure**
### **Training hyperparameters**
<details>
<summary>Click to see details</summary>
- learning_rate: 0.0002
- lr_scheduler: cosine
- train_batch_size: 12
- eval_batch_size: 8
- GPU: H100 80GB SXM5
- num_devices: 8
- optimizer: adamw_bnb_8bit
- lr_scheduler_warmup_steps: 100
- num_epochs: 4
</details>
### **Peft hyperparameters**
<details>
<summary>Click to see details</summary>
- adapter: qlora
- lora_r: 128
- lora_alpha: 256
- lora_dropout: 0.05
- lora_target_linear: true
-lora_target_modules:
- q_proj
- v_proj
- k_proj
- o_proj
- gate_proj
- down_proj
- up_proj
</details>
### **Training results**
### **Framework versions**
- Transformers 4.39.3
- Pytorch 2.1.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.1
- Axolotl
- Lm harness for evaluation
# Benchmark Results
🔥 OpenBioLLM-70B demonstrates superior performance compared to larger models, such as GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 86.06%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge.
🚨 The GPT-4, Med-PaLM-1, and Med-PaLM-2 results are taken from their official papers. Since Med-PaLM doesn't provide zero-shot accuracy, we are using 5-shot accuracy from their paper for comparison. All results presented are in the zero-shot setting, except for Med-PaLM-2 and Med-PaLM-1, which use 5-shot accuracy.
| | Clinical KG | Medical Genetics | Anatomy | Pro Medicine | College Biology | College Medicine | MedQA 4 opts | PubMedQA | MedMCQA | Avg |
|--------------------|-------------|------------------|---------|--------------|-----------------|------------------|--------------|----------|---------|-------|
| **OpenBioLLM-70B** | **92.93** | **93.197** | **83.904** | 93.75 | 93.827 | **85.749** | 78.162 | 78.97 | **74.014** | **86.05588** |
| Med-PaLM-2 (5-shot) | 88.3 | 90 | 77.8 | **95.2** | 94.4 | 80.9 | **79.7** | **79.2** | 71.3 | 84.08 |
| **GPT-4** | 86.04 | 91 | 80 | 93.01 | **95.14** | 76.88 | 78.87 | 75.2 | 69.52 | 82.85 |
| Med-PaLM-1 (Flan-PaLM, 5-shot) | 80.4 | 75 | 63.7 | 83.8 | 88.9 | 76.3 | 67.6 | 79 | 57.6 | 74.7 |
| **OpenBioLLM-8B** | 76.101 | 86.1 | 69.829 | 78.21 | 84.213 | 68.042 | 58.993 | 74.12 | 56.913 | 72.502 |
| Gemini-1.0 | 76.7 | 75.8 | 66.7 | 77.7 | 88 | 69.2 | 58 | 70.7 | 54.3 | 70.79 |
| GPT-3.5 Turbo 1106 | 74.71 | 74 | 72.79 | 72.79 | 72.91 | 64.73 | 57.71 | 72.66 | 53.79 | 66 |
| Meditron-70B | 66.79 | 69 | 53.33 | 71.69 | 76.38 | 63 | 57.1 | 76.6 | 46.85 | 64.52 |
| gemma-7b | 69.81 | 70 | 59.26 | 66.18 | 79.86 | 60.12 | 47.21 | 76.2 | 48.96 | 64.18 |
| Mistral-7B-v0.1 | 68.68 | 71 | 55.56 | 68.38 | 68.06 | 59.54 | 50.82 | 75.4 | 48.2 | 62.85 |
| Apollo-7B | 62.26 | 72 | 61.48 | 69.12 | 70.83 | 55.49 | 55.22 | 39.8 | 53.77 | 60 |
| MedAlpaca-7b | 57.36 | 69 | 57.04 | 67.28 | 65.28 | 54.34 | 41.71 | 72.8 | 37.51 | 58.03 |
| BioMistral-7B | 59.9 | 64 | 56.5 | 60.4 | 59 | 54.7 | 50.6 | 77.5 | 48.1 | 57.3 |
| AlpaCare-llama2-7b | 49.81 | 49 | 45.92 | 33.82 | 50 | 43.35 | 29.77 | 72.2 | 34.42 | 45.36 |
| ClinicalGPT | 30.56 | 27 | 30.37 | 19.48 | 25 | 24.27 | 26.08 | 63.8 | 28.18 | 30.52 |
<div align="center">
<img width="1600px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/_SzdcJSBjZyo8RS1bTEkP.png">
</div>
## Detailed Medical Subjectwise accuracy
# Use Cases & Examples
🚨 **Below results are from the quantized version of OpenBioLLM-70B
# Summarize Clinical Notes
OpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries
# Answer Medical Questions
OpenBioLLM-70B can provide answers to a wide range of medical questions.
<details>
<summary>Click to see details</summary>
</details>
# Clinical Entity Recognition
OpenBioLLM-70B can perform advanced clinical entity recognition by identifying and extracting key medical concepts, such as diseases, symptoms, medications, procedures, and anatomical structures, from unstructured clinical text. By leveraging its deep understanding of medical terminology and context, the model can accurately annotate and categorize clinical entities, enabling more efficient information retrieval, data analysis, and knowledge discovery from electronic health records, research articles, and other biomedical text sources. This capability can support various downstream applications, such as clinical decision support, pharmacovigilance, and medical research.
# Biomarkers Extraction
# Classification
OpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization
# De-Identification
OpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA.
**Advisory Notice!**
While OpenBioLLM-70B leverages high-quality data sources, its outputs may still contain inaccuracies, biases, or misalignments that could pose risks if relied upon for medical decision-making without further testing and refinement. The model's performance has not yet been rigorously evaluated in randomized controlled trials or real-world healthcare environments.
Therefore, we strongly advise against using OpenBioLLM-70B for any direct patient care, clinical decision support, or other professional medical purposes at this time. Its use should be limited to research, development, and exploratory applications by qualified individuals who understand its limitations.
OpenBioLLM-70B is intended solely as a research tool to assist healthcare professionals and should never be considered a replacement for the professional judgment and expertise of a qualified medical doctor.
Appropriately adapting and validating OpenBioLLM-70B for specific medical use cases would require significant additional work, potentially including:
- Thorough testing and evaluation in relevant clinical scenarios
- Alignment with evidence-based guidelines and best practices
- Mitigation of potential biases and failure modes
- Integration with human oversight and interpretation
- Compliance with regulatory and ethical standards
Always consult a qualified healthcare provider for personal medical needs.
# Citation
If you find OpenBioLLM-70B & 8B useful in your work, please cite the model as follows:
```
@misc{OpenBioLLMs,
author = {Ankit Pal, Malaikannan Sankarasubbu},
title = {OpenBioLLMs: Advancing Open-Source Large Language Models for Healthcare and Life Sciences},
year = {2024},
publisher = {Hugging Face},
journal = {Hugging Face repository},
howpublished = {\url{https://huggingface.co/aaditya/OpenBioLLM-Llama3-70B}}
}
```
The accompanying paper is currently in progress and will be released soon.
<div align="center">
<h2> 💌 Contact </h2>
</div>
We look forward to hearing you and collaborating on this exciting project!
**Contributors:**
- [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) [aadityaura at gmail dot com]
- Saama AI Labs
- Note: I am looking for a funded PhD opportunity, especially if it fits my Responsible Generative AI, Multimodal LLMs, Geometric Deep Learning, and Healthcare AI skillset.
# References
We thank the [Meta Team](meta-llama/Meta-Llama-3-70B-Instruct) for their amazing models!
Result sources
- [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (https://arxiv.org/abs/2303.13375)
- [2] Med-PaLM-1 [Large Language Models Encode Clinical Knowledge](https://arxiv.org/abs/2212.13138)
- [3] Med-PaLM-2 [Towards Expert-Level Medical Question Answering with Large Language Models](https://arxiv.org/abs/2305.09617)
- [4] Gemini-1.0 [Gemini Goes to Med School](https://arxiv.org/abs/2402.07023) |
avalosjc/llama3_8b_generation | avalosjc | 2024-06-21T19:59:49Z | 6 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"llama",
"trl",
"sft",
"generated_from_trainer",
"dataset:generator",
"base_model:NousResearch/Meta-Llama-3-8B",
"base_model:adapter:NousResearch/Meta-Llama-3-8B",
"license:other",
"4-bit",
"bitsandbytes",
"region:us"
] | null | 2024-06-13T22:16:17Z | ---
base_model: NousResearch/Meta-Llama-3-8B
datasets:
- generator
library_name: peft
license: other
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: llama3_8b_generation
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# llama3_8b_generation
This model is a fine-tuned version of [NousResearch/Meta-Llama-3-8B](https://huggingface.co/NousResearch/Meta-Llama-3-8B) on the generator dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_steps: 0.03
- training_steps: 10
### Training results
### Framework versions
- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1 |
kanishka/smolm-autoreg-bpe-counterfactual_babylm_measure_nps_as_singular_new-3e-4 | kanishka | 2024-06-21T19:59:43Z | 7 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"opt",
"text-generation",
"generated_from_trainer",
"dataset:kanishka/counterfactual_babylm_measure_nps_as_singular_new",
"model-index",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-06-20T21:21:15Z | ---
tags:
- generated_from_trainer
datasets:
- kanishka/counterfactual_babylm_measure_nps_as_singular_new
metrics:
- accuracy
model-index:
- name: smolm-autoreg-bpe-counterfactual_babylm_measure_nps_as_singular_new-3e-4
results:
- task:
name: Causal Language Modeling
type: text-generation
dataset:
name: kanishka/counterfactual_babylm_measure_nps_as_singular_new
type: kanishka/counterfactual_babylm_measure_nps_as_singular_new
metrics:
- name: Accuracy
type: accuracy
value: 0.4093866078289784
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# smolm-autoreg-bpe-counterfactual_babylm_measure_nps_as_singular_new-3e-4
This model was trained from scratch on the kanishka/counterfactual_babylm_measure_nps_as_singular_new dataset.
It achieves the following results on the evaluation set:
- Loss: 3.4141
- Accuracy: 0.4094
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0003
- train_batch_size: 32
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 32000
- num_epochs: 20.0
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:------:|:---------------:|:--------:|
| 3.7385 | 1.0 | 18602 | 3.9139 | 0.3449 |
| 3.4266 | 2.0 | 37204 | 3.6133 | 0.3747 |
| 3.2882 | 3.0 | 55806 | 3.4788 | 0.3899 |
| 3.2035 | 4.0 | 74408 | 3.4080 | 0.3974 |
| 3.141 | 5.0 | 93010 | 3.4152 | 0.3997 |
| 3.0971 | 6.0 | 111612 | 3.3875 | 0.4027 |
| 3.0545 | 7.0 | 130214 | 3.3727 | 0.4048 |
| 3.0227 | 8.0 | 148816 | 3.3644 | 0.4070 |
| 2.9947 | 9.0 | 167418 | 3.3735 | 0.4077 |
| 2.966 | 10.0 | 186020 | 3.3659 | 0.4086 |
| 2.9448 | 11.0 | 204622 | 3.3568 | 0.4092 |
| 2.9212 | 12.0 | 223224 | 3.3682 | 0.4092 |
| 2.8974 | 13.0 | 241826 | 3.3732 | 0.4089 |
| 2.8755 | 14.0 | 260428 | 3.3812 | 0.4096 |
| 2.8571 | 15.0 | 279030 | 3.3808 | 0.4100 |
| 2.8333 | 16.0 | 297632 | 3.3887 | 0.4097 |
| 2.8156 | 17.0 | 316234 | 3.3931 | 0.4098 |
| 2.7983 | 18.0 | 334836 | 3.3972 | 0.4099 |
| 2.778 | 19.0 | 353438 | 3.4080 | 0.4095 |
| 2.7615 | 20.0 | 372040 | 3.4141 | 0.4094 |
### Framework versions
- Transformers 4.38.0
- Pytorch 2.3.1+cu121
- Datasets 2.16.1
- Tokenizers 0.15.2
|
bartowski/LLAMA-3_8B_Unaligned_Alpha-GGUF | bartowski | 2024-06-21T19:58:14Z | 111 | 1 | null | [
"gguf",
"text-generation",
"en",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | text-generation | 2024-06-21T19:28:06Z | ---
license: apache-2.0
language:
- en
quantized_by: bartowski
pipeline_tag: text-generation
---
## Llamacpp imatrix Quantizations of LLAMA-3_8B_Unaligned_Alpha
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b3197">b3197</a> for quantization.
Original model: https://huggingface.co/SicariusSicariiStuff/LLAMA-3_8B_Unaligned_Alpha
All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
## Prompt format
```
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Description |
| -------- | ---------- | --------- | ----------- |
| [LLAMA-3_8B_Unaligned_Alpha-Q8_0_L.gguf](https://huggingface.co/bartowski/LLAMA-3_8B_Unaligned_Alpha-GGUF/blob/main/LLAMA-3_8B_Unaligned_Alpha-Q8_1.gguf) | Q8_0_L | 9.52GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. Extremely high quality, generally unneeded but max available quant. |
| [LLAMA-3_8B_Unaligned_Alpha-Q8_0.gguf](https://huggingface.co/bartowski/LLAMA-3_8B_Unaligned_Alpha-GGUF/blob/main/LLAMA-3_8B_Unaligned_Alpha-Q8_0.gguf) | Q8_0 | 8.54GB | Extremely high quality, generally unneeded but max available quant. |
| [LLAMA-3_8B_Unaligned_Alpha-Q6_K_L.gguf](https://huggingface.co/bartowski/LLAMA-3_8B_Unaligned_Alpha-GGUF/blob/main/LLAMA-3_8B_Unaligned_Alpha-Q6_K_L.gguf) | Q6_K_L | 7.83GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. Very high quality, near perfect, *recommended*. |
| [LLAMA-3_8B_Unaligned_Alpha-Q6_K.gguf](https://huggingface.co/bartowski/LLAMA-3_8B_Unaligned_Alpha-GGUF/blob/main/LLAMA-3_8B_Unaligned_Alpha-Q6_K.gguf) | Q6_K | 6.59GB | Very high quality, near perfect, *recommended*. |
| [LLAMA-3_8B_Unaligned_Alpha-Q5_K_L.gguf](https://huggingface.co/bartowski/LLAMA-3_8B_Unaligned_Alpha-GGUF/blob/main/LLAMA-3_8B_Unaligned_Alpha-Q5_K_L.gguf) | Q5_K_L | 7.04GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. High quality, *recommended*. |
| [LLAMA-3_8B_Unaligned_Alpha-Q5_K_M.gguf](https://huggingface.co/bartowski/LLAMA-3_8B_Unaligned_Alpha-GGUF/blob/main/LLAMA-3_8B_Unaligned_Alpha-Q5_K_M.gguf) | Q5_K_M | 5.73GB | High quality, *recommended*. |
| [LLAMA-3_8B_Unaligned_Alpha-Q5_K_S.gguf](https://huggingface.co/bartowski/LLAMA-3_8B_Unaligned_Alpha-GGUF/blob/main/LLAMA-3_8B_Unaligned_Alpha-Q5_K_S.gguf) | Q5_K_S | 5.59GB | High quality, *recommended*. |
| [LLAMA-3_8B_Unaligned_Alpha-Q4_K_L.gguf](https://huggingface.co/bartowski/LLAMA-3_8B_Unaligned_Alpha-GGUF/blob/main/LLAMA-3_8B_Unaligned_Alpha-Q4_K_L.gguf) | Q4_K_L | 6.29GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. Good quality, uses about 4.83 bits per weight, *recommended*. |
| [LLAMA-3_8B_Unaligned_Alpha-Q4_K_M.gguf](https://huggingface.co/bartowski/LLAMA-3_8B_Unaligned_Alpha-GGUF/blob/main/LLAMA-3_8B_Unaligned_Alpha-Q4_K_M.gguf) | Q4_K_M | 4.92GB | Good quality, uses about 4.83 bits per weight, *recommended*. |
| [LLAMA-3_8B_Unaligned_Alpha-Q4_K_S.gguf](https://huggingface.co/bartowski/LLAMA-3_8B_Unaligned_Alpha-GGUF/blob/main/LLAMA-3_8B_Unaligned_Alpha-Q4_K_S.gguf) | Q4_K_S | 4.69GB | Slightly lower quality with more space savings, *recommended*. |
| [LLAMA-3_8B_Unaligned_Alpha-IQ4_XS.gguf](https://huggingface.co/bartowski/LLAMA-3_8B_Unaligned_Alpha-GGUF/blob/main/LLAMA-3_8B_Unaligned_Alpha-IQ4_XS.gguf) | IQ4_XS | 4.44GB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [LLAMA-3_8B_Unaligned_Alpha-Q3_K_XL.gguf](https://huggingface.co/bartowski/LLAMA-3_8B_Unaligned_Alpha-GGUF//main/LLAMA-3_8B_Unaligned_Alpha-Q3_K_XL.gguf) | Q3_K_XL | | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. Lower quality but usable, good for low RAM availability. |
| [LLAMA-3_8B_Unaligned_Alpha-Q3_K_L.gguf](https://huggingface.co/bartowski/LLAMA-3_8B_Unaligned_Alpha-GGUF/blob/main/LLAMA-3_8B_Unaligned_Alpha-Q3_K_L.gguf) | Q3_K_L | 4.32GB | Lower quality but usable, good for low RAM availability. |
| [LLAMA-3_8B_Unaligned_Alpha-Q3_K_M.gguf](https://huggingface.co/bartowski/LLAMA-3_8B_Unaligned_Alpha-GGUF/blob/main/LLAMA-3_8B_Unaligned_Alpha-Q3_K_M.gguf) | Q3_K_M | 4.01GB | Even lower quality. |
| [LLAMA-3_8B_Unaligned_Alpha-IQ3_M.gguf](https://huggingface.co/bartowski/LLAMA-3_8B_Unaligned_Alpha-GGUF/blob/main/LLAMA-3_8B_Unaligned_Alpha-IQ3_M.gguf) | IQ3_M | 3.78GB | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [LLAMA-3_8B_Unaligned_Alpha-Q3_K_S.gguf](https://huggingface.co/bartowski/LLAMA-3_8B_Unaligned_Alpha-GGUF/blob/main/LLAMA-3_8B_Unaligned_Alpha-Q3_K_S.gguf) | Q3_K_S | 3.66GB | Low quality, not recommended. |
| [LLAMA-3_8B_Unaligned_Alpha-IQ3_XS.gguf](https://huggingface.co/bartowski/LLAMA-3_8B_Unaligned_Alpha-GGUF/blob/main/LLAMA-3_8B_Unaligned_Alpha-IQ3_XS.gguf) | IQ3_XS | 3.51GB | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [LLAMA-3_8B_Unaligned_Alpha-IQ3_XXS.gguf](https://huggingface.co/bartowski/LLAMA-3_8B_Unaligned_Alpha-GGUF/blob/main/LLAMA-3_8B_Unaligned_Alpha-IQ3_XXS.gguf) | IQ3_XXS | 3.27GB | Lower quality, new method with decent performance, comparable to Q3 quants. |
| [LLAMA-3_8B_Unaligned_Alpha-Q2_K.gguf](https://huggingface.co/bartowski/LLAMA-3_8B_Unaligned_Alpha-GGUF/blob/main/LLAMA-3_8B_Unaligned_Alpha-Q2_K.gguf) | Q2_K | 3.17GB | Very low quality but surprisingly usable. |
| [LLAMA-3_8B_Unaligned_Alpha-IQ2_M.gguf](https://huggingface.co/bartowski/LLAMA-3_8B_Unaligned_Alpha-GGUF/blob/main/LLAMA-3_8B_Unaligned_Alpha-IQ2_M.gguf) | IQ2_M | 2.94GB | Very low quality, uses SOTA techniques to also be surprisingly usable. |
| [LLAMA-3_8B_Unaligned_Alpha-IQ2_S.gguf](https://huggingface.co/bartowski/LLAMA-3_8B_Unaligned_Alpha-GGUF/blob/main/LLAMA-3_8B_Unaligned_Alpha-IQ2_S.gguf) | IQ2_S | 2.75GB | Very low quality, uses SOTA techniques to be usable. |
| [LLAMA-3_8B_Unaligned_Alpha-IQ2_XS.gguf](https://huggingface.co/bartowski/LLAMA-3_8B_Unaligned_Alpha-GGUF/blob/main/LLAMA-3_8B_Unaligned_Alpha-IQ2_XS.gguf) | IQ2_XS | 2.60GB | Very low quality, uses SOTA techniques to be usable. |
## Downloading using huggingface-cli
First, make sure you have hugginface-cli installed:
```
pip install -U "huggingface_hub[cli]"
```
Then, you can target the specific file you want:
```
huggingface-cli download bartowski/LLAMA-3_8B_Unaligned_Alpha-GGUF --include "LLAMA-3_8B_Unaligned_Alpha-Q4_K_M.gguf" --local-dir ./
```
If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
```
huggingface-cli download bartowski/LLAMA-3_8B_Unaligned_Alpha-GGUF --include "LLAMA-3_8B_Unaligned_Alpha-Q8_0.gguf/*" --local-dir LLAMA-3_8B_Unaligned_Alpha-Q8_0
```
You can either specify a new local-dir (LLAMA-3_8B_Unaligned_Alpha-Q8_0) or download them all in place (./)
## Which file should I choose?
A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9)
The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.
If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.
If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.
Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.
If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.
If you want to get more into the weeds, you can check out this extremely useful feature chart:
[llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix)
But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.
These I-quants can also be used on CPU and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
The I-quants are *not* compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm.
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
|
Intel/dpt-swinv2-tiny-256 | Intel | 2024-06-21T19:56:01Z | 842 | 7 | transformers | [
"transformers",
"safetensors",
"dpt",
"depth-estimation",
"vision",
"arxiv:2103.13413",
"arxiv:2307.14460",
"license:mit",
"model-index",
"endpoints_compatible",
"region:us"
] | depth-estimation | 2023-12-10T20:46:13Z | ---
license: mit
tags:
- vision
- depth-estimation
model-index:
- name: dpt-swinv2-tiny-256
results:
- task:
type: monocular-depth-estimation
name: Monocular Depth Estimation
dataset:
type: MIX-6
name: MIX-6
metrics:
- type: Zero-shot transfer
value: 10.82
name: Zero-shot transfer
config: Zero-shot transfer
verified: false
---
# Midas 3.1 DPT (Intel/dpt-swinv2-tiny-256 using Swinv2 backbone)
DPT (Dense Prediction Transformer) model trained on 1.4 million images for monocular depth estimation. It was introduced in the paper [Vision Transformers for Dense Prediction](https://arxiv.org/abs/2103.13413) by Ranftl et al. (2021) and first released in [this repository](https://github.com/isl-org/MiDaS/tree/master).
**Disclaimer:** The team releasing DPT did not write a model card for this model so this model card has been written by Intel and the Hugging Face team.
# Overview of Monocular depth estimation
The aim of Monocular depth estimation is to infer detailed depth from a single image or camera view, finds applications in fields like generative AI, 3D reconstruction, and autonomous driving. However, deriving depth from individual pixels in a single image is challenging due to the under constrained nature of the problem. Recent advancements attribute progress to learning-based methods, particularly with MiDaS, leveraging dataset mixing and scale-and-shift-invariant loss. MiDaS has evolved with releases featuring more powerful backbones and lightweight variants for mobile use. With the rise of transformer architectures in computer vision, including those pioneered by models like ViT,and Swin, and SwinV2 there's been a shift towards using them for depth estimation. Inspired by this, MiDaS v3.1 incorporates promising transformer-based encoders alongside traditional convolutional ones, aiming for a comprehensive investigation of depth estimation techniques. The paper focuses on describing the integration of these backbones into MiDaS, providing a thorough comparison of different v3.1 models, and offering guidance on utilizing future backbones with MiDaS.
Swin Transformer (the name Swin stands for Shifted window) is initially described in arxiv, which capably serves as a general-purpose backbone for computer vision. It is basically a hierarchical Transformer whose representation is computed with shifted windows. The shifted windowing scheme brings greater efficiency by limiting self-attention computation to non-overlapping local windows while also allowing for cross-window connection.
Swin Transformer achieves strong performance on COCO object detection (58.7 box AP and 51.1 mask AP on test-dev) and ADE20K semantic segmentation (53.5 mIoU on val), surpassing previous models by a large margin.
| Input Image | Output Depth Image |
| --- | --- |
|  |  |
# Videos
MiDaS Depth Estimation is a machine learning model from Intel Labs for monocular depth estimation. It was trained on up to 12 datasets and covers both in-and outdoor scenes. Multiple different MiDaS models are available, ranging from high quality depth estimation to lightweight models for mobile downstream tasks (https://github.com/isl-org/MiDaS).
## Model description
This Midas 3.1 DPT model uses the [SwinV2 Philosophy]( https://huggingface.co/docs/transformers/en/model_doc/swinv2) model as backbone and uses a different approach to Vision that Beit, where Swin backbones focus more on using a hierarchical approach.
The previous release MiDaS v3.0 solely leverages the
vanilla vision transformer ViT, MiDaS v3.1 offers additional models based on BEiT, Swin, SwinV2, Next-ViT and LeViT.
# Midas 3.1 DPT Model(Swin backbone)
This model refers to Intel dpt-swinv2-tiny-256 based on the Swin backbone. The arxiv paper compares both Beit and Swin backbones.
The highest quality depth estimation is achieved using the BEiT transformer. We provide variants such as Swin-L, SwinV2-L, SwinV2-B, SwinV2-T, where the numbers signify training resolutions of 512x512 and 384x384, while the letters denote large and base models respectively.
DPT (Dense Prediction Transformer) model trained on 1.4 million images for monocular depth estimation. It was introduced in the paper [Vision Transformers for Dense Prediction](https://arxiv.org/abs/2103.13413) by Ranftl et al. (2021) and first released in [this repository](https://github.com/isl-org/MiDaS/tree/master).
This model card refers specifically to SwinV2, in the paper, and is referred to dpt-swinv2-tiny-256. A more recent paper from 2013, specifically discussing Swin and SwinV2, is in this paper [MiDaS v3.1 – A Model Zoo for Robust Monocular Relative Depth Estimation
](https://arxiv.org/pdf/2307.14460.pdf)
The model card has been written in combination by the Hugging Face team and Intel.
| Model Detail | Description |
| ----------- | ----------- |
| Model Authors - Company | Intel |
| Date | March 18, 2024 |
| Version | 1 |
| Type | Computer Vision - Monocular Depth Estimation |
| Paper or Other Resources | [MiDaS v3.1 – A Model Zoo for Robust Monocular Relative Depth Estimation](https://arxiv.org/pdf/2307.14460.pdf) and [GitHub Repo](https://github.com/isl-org/MiDaS/blob/master/README.md) |
| License | MIT |
| Questions or Comments | [Community Tab](https://huggingface.co/Intel/dpt-swinv2-tiny-256/discussions) and [Intel Developers Discord](https://discord.gg/rv2Gp55UJQ)|
| Intended Use | Description |
| ----------- | ----------- |
| Primary intended uses | You can use the raw model for zero-shot monocular depth estimation. See the [model hub](https://huggingface.co/models?search=dpt-beit-large) to look for fine-tuned versions on a task that interests you. |
| Primary intended users | Anyone doing monocular depth estimation |
| Out-of-scope uses | This model in most cases will need to be fine-tuned for your particular task. The model should not be used to intentionally create hostile or alienating environments for people.|
## How to use
Be sure the to update PyTorch as Transformers as mismatches in versions can generate erros such as: "TypeError: unsupported operand type(s) for //: 'NoneType' and 'NoneType'".
As tested by this contributor, the following versions ran correctly:
```python
import torch
import transformers
print(torch.__version__)
print(transformers.__version__)
```
```bash
out: '2.2.1+cpu'
out: '4.37.2'
```
### To Install:
```pythopn
pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
```
# To Use:
Here is how to use this model for zero-shot depth estimation on an image:
```python
output = prediction.squeeze().cpu().numpy()
formatted = (output * 255 / np.max(output)).astype("uint8")
depth = Image.fromarray(formatted)
depth
```
or one can use the pipeline API:
```python
from transformers import pipeline
pipe = pipeline(task="depth-estimation", model="Intel/dpt-swinv2-tiny-256")
result = pipe("http://images.cocodataset.org/val2017/000000181816.jpg")
result["depth"]
```
## Quantitative Analyses
| Model | Square Resolution HRWSI RMSE | Square Resolution Blended MVS REL | Square Resolution ReDWeb RMSE |
| --- | --- | --- | --- |
| BEiT 384-L | 0.068 | 0.070 | 0.076 |
| Swin-L Training 1| 0.0708 | 0.0724 | 0.0826 |
| Swin-L Training 2 | 0.0713 | 0.0720 | 0.0831 |
| ViT-L | 0.071 | 0.072 | 0.082 |
| --- | --- | --- | --- |
| Next-ViT-L-1K-6M | 0.075 |0.073 | 0.085 |
| DeiT3-L-22K-1K | 0.070 | 0.070 | 0.080 |
| ViT-L-Hybrid | 0.075 | 0.075 | 0.085 |
| DeiT3-L | 0.077 | 0.075 | 0.087 |
| --- | --- | --- | --- |
| ConvNeXt-XL | 0.075 | 0.075 | 0.085 |
| ConvNeXt-L | 0.076 | 0.076 | 0.087 |
| EfficientNet-L2| 0.165 | 0.277 | 0.219 |
| --- | --- | --- | --- |
| ViT-L Reversed | 0.071 | 0.073 | 0.081 |
| Swin-L Equidistant | 0.072 | 0.074 | 0.083 |
| --- | --- | --- | --- |
# Ethical Considerations and Limitations
dpt-swinv2-tiny-256 can produce factually incorrect output, and should not be relied on to produce factually accurate information. Because of the limitations of the pretrained model and the finetuning datasets, it is possible that this model could generate lewd, biased or otherwise offensive outputs.
Therefore, before deploying any applications of dpt-swinv2-tiny-256, developers should perform safety testing.
# Caveats and Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model.
Here are a couple of useful links to learn more about Intel's AI software:
- Intel Neural Compressor [link](https://github.com/intel/neural-compressor)
- Intel Extension for Transformers [link](https://github.com/intel/intel-extension-for-transformers)
# Disclaimer
The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please cosult an attorney before using this model for commercial purposes.
### BibTeX entry and citation info
```bibtex
@article{DBLP:journals/corr/abs-2103-13413,
author = {Ren{\'{e}} Reiner Birkl, Diana Wofk, Matthias Muller},
title = {MiDaS v3.1 – A Model Zoo for Robust Monocular Relative Depth Estimation},
journal = {CoRR},
volume = {abs/2307.14460},
year = {2021},
url = {https://arxiv.org/abs/2307.14460},
eprinttype = {arXiv},
eprint = {2307.14460},
timestamp = {Wed, 26 Jul 2023},
biburl = {https://dblp.org/rec/journals/corr/abs-2307.14460.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
```
|
Intel/dpt-beit-large-384 | Intel | 2024-06-21T19:49:26Z | 92 | 0 | transformers | [
"transformers",
"safetensors",
"dpt",
"depth-estimation",
"vision",
"arxiv:2103.13413",
"arxiv:2307.14460",
"license:mit",
"model-index",
"endpoints_compatible",
"region:us"
] | depth-estimation | 2023-11-28T11:15:31Z | ---
license: mit
tags:
- vision
- depth-estimation
model-index:
- name: dpt-beit-large-384
results:
- task:
type: monocular-depth-estimation
name: Monocular Depth Estimation
dataset:
type: MIX-6
name: MIX-6
metrics:
- type: Zero-shot transfer
value: 10.82
name: Zero-shot transfer
config: Zero-shot transfer
verified: false
---
# Overview of Monocular depth estimation and BEiT
The Intel/dpt-beit-large-384 model is based on Monocular depth estimation with the BEiT backbone. Monocular depth estimation, aiming to infer detailed depth from a single image or camera view, finds applications in fields like generative AI, 3D reconstruction, and autonomous driving. However, deriving depth from individual pixels in a single image is challenging due to the underconstrained nature of the problem. Recent advancements attribute progress to learning-based methods, particularly with MiDaS, leveraging dataset mixing and scale-and-shift-invariant loss. MiDaS has evolved with releases featuring more powerful backbones and lightweight variants for mobile use. With the rise of transformer architectures in computer vision, including those pioneered by models like ViT, there's been a shift towards using them for depth estimation. Inspired by this, MiDaS v3.1 incorporates promising transformer-based encoders alongside traditional convolutional ones, aiming for a comprehensive investigation of depth estimation techniques. The paper focuses on describing the integration of these backbones into MiDaS, providing a thorough comparison of different v3.1 models, and offering guidance on utilizing future backbones with MiDaS.
| Input Image | Output Depth Image |
| --- | --- |
|  |  |
## Model description
This DPT model uses the [BEiT](https://huggingface.co/docs/transformers/model_doc/beit) model as backbone and adds a neck + head on top for monocular depth estimation.
The previous release MiDaS v3.0 solely leverages the
vanilla vision transformer ViT, MiDaS v3.1 offers additional models based on BEiT, Swin, SwinV2, Next-ViT and LeViT.
# DPT 3.1 (BEiT backbone): focus on BEiT384-L
The highest quality depth estimation is achieved using the BEiT transformer. We provide variants such as BEiT512-L, BEiT384-L, and BEiT384-B, where the numbers signify training resolutions of 512x512 and 384x384, while the letters denote large and base models respectively. Although newer versions like BEiT v2 and BEiT-3 exist, they were not explored in our study. BEiT v2 lacked pretrained checkpoints with resolutions of 384x384 or higher, only offering them at 224x224. BEiT-3 was released after our study was completed.
DPT (Dense Prediction Transformer) model trained on 1.4 million images for monocular depth estimation. It was introduced in the paper [Vision Transformers for Dense Prediction](https://arxiv.org/abs/2103.13413) by Ranftl et al. (2021) and first released in [this repository](https://github.com/isl-org/MiDaS/tree/master).
This model card refers specifically to **BEiT384-L** in the paper, and is referred to dpt-beit-large-384. A more recent paper from 2013, specifically discussing BEit, is in this paper [MiDaS v3.1 – A Model Zoo for Robust Monocular Relative Depth Estimation
](https://arxiv.org/pdf/2307.14460.pdf)
The model card has been written in combination by the Hugging Face team and Intel.
| Model Detail | Description |
| ----------- | ----------- |
| Model Authors - Company | Intel |
| Date | March 7, 2024 |
| Version | 1 |
| Type | Computer Vision - Monocular Depth Estimation |
| Paper or Other Resources | [MiDaS v3.1 – A Model Zoo for Robust Monocular Relative Depth Estimation](https://arxiv.org/pdf/2307.14460.pdf) and [GitHub Repo](https://github.com/isl-org/MiDaS/blob/master/README.md) |
| License | MIT |
| Questions or Comments | [Community Tab](https://huggingface.co/Intel/dpt-beit-large-384/discussions) and [Intel Developers Discord](https://discord.gg/rv2Gp55UJQ)|
| Intended Use | Description |
| ----------- | ----------- |
| Primary intended uses | You can use the raw model for zero-shot monocular depth estimation. See the [model hub](https://huggingface.co/models?search=dpt-beit-large) to look for fine-tuned versions on a task that interests you. |
| Primary intended users | Anyone doing monocular depth estimation |
| Out-of-scope uses | This model in most cases will need to be fine-tuned for your particular task. The model should not be used to intentionally create hostile or alienating environments for people.|
## How to use
Be sure the to update PyTorch as Transformers as mismatches in versions can generate erros such as: "TypeError: unsupported operand type(s) for //: 'NoneType' and 'NoneType'".
As tested by this contributor, the following versions ran correctly:
```python
import torch
import transformers
print(torch.__version__)
print(transformers.__version__)
```
```bash
out: '2.2.1+cpu'
out: '4.37.2'
```
### To Install:
```pythopn
pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
```
# To Use:
Here is how to use this model for zero-shot depth estimation on an image:
```python
from transformers import DPTImageProcessor, DPTForDepthEstimation
import torch
import numpy as np
from PIL import Image
import requests
# retrieve image remotely
url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)
# retrieve image local file
# path = "../image/000000039769.jpg"
# image = Image.open(path)
processor = DPTImageProcessor.from_pretrained("Intel/dpt-beit-large-384")
model = DPTForDepthEstimation.from_pretrained("Intel/dpt-beit-large-384")
# prepare image for the model
inputs = processor(images=image, return_tensors="pt")
with torch.no_grad():
outputs = model(**inputs)
predicted_depth = outputs.predicted_depth
# interpolate to original size
prediction = torch.nn.functional.interpolate(
predicted_depth.unsqueeze(1),
size=image.size[::-1],
mode="bicubic",
align_corners=False,
)
# visualize the prediction
output = prediction.squeeze().cpu().numpy()
formatted = (output * 255 / np.max(output)).astype("uint8")
depth = Image.fromarray(formatted)
depth
```
or one can use the pipeline API:
```python
from transformers import pipeline
pipe = pipeline(task="depth-estimation", model="Intel/dpt-beit-large-384")
result = pipe("http://images.cocodataset.org/val2017/000000181816.jpg")
result["depth"]
```
## Quantitative Analyses
| Model | Square Resolution HRWSI RMSE | Square Resolution Blended MVS REL | Square Resolution ReDWeb RMSE |
| --- | --- | --- | --- |
| BEiT 384-L | 0.068 | 0.070 | 0.076 |
| Swin-L Training 1| 0.0708 | 0.0724 | 0.0826 |
| Swin-L Training 2 | 0.0713 | 0.0720 | 0.0831 |
| ViT-L | 0.071 | 0.072 | 0.082 |
| --- | --- | --- | --- |
| Next-ViT-L-1K-6M | 0.075 |0.073 | 0.085 |
| DeiT3-L-22K-1K | 0.070 | 0.070 | 0.080 |
| ViT-L-Hybrid | 0.075 | 0.075 | 0.085 |
| DeiT3-L | 0.077 | 0.075 | 0.087 |
| --- | --- | --- | --- |
| ConvNeXt-XL | 0.075 | 0.075 | 0.085 |
| ConvNeXt-L | 0.076 | 0.076 | 0.087 |
| EfficientNet-L2| 0.165 | 0.277 | 0.219 |
| --- | --- | --- | --- |
| ViT-L Reversed | 0.071 | 0.073 | 0.081 |
| Swin-L Equidistant | 0.072 | 0.074 | 0.083 |
| --- | --- | --- | --- |
# Ethical Considerations and Limitations
dpt-beit-large-384 can produce factually incorrect output, and should not be relied on to produce factually accurate information. Because of the limitations of the pretrained model and the finetuning datasets, it is possible that this model could generate lewd, biased or otherwise offensive outputs.
Therefore, before deploying any applications of dpt-beit-large-384, developers should perform safety testing.
# Caveats and Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model.
Here are a couple of useful links to learn more about Intel's AI software:
- Intel Neural Compressor [link](https://github.com/intel/neural-compressor)
- Intel Extension for Transformers [link](https://github.com/intel/intel-extension-for-transformers)
# Disclaimer
The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please cosult an attorney before using this model for commercial purposes.
### BibTeX entry and citation info
```bibtex
@article{DBLP:journals/corr/abs-2103-13413,
author = {Ren{\'{e}} Reiner Birkl, Diana Wofk, Matthias Muller},
title = {MiDaS v3.1 – A Model Zoo for Robust Monocular Relative Depth Estimation},
journal = {CoRR},
volume = {abs/2307.14460},
year = {2021},
url = {https://arxiv.org/abs/2307.14460},
eprinttype = {arXiv},
eprint = {2307.14460},
timestamp = {Wed, 26 Jul 2023},
biburl = {https://dblp.org/rec/journals/corr/abs-2307.14460.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
```
|
Intel/bert-base-uncased-mrpc | Intel | 2024-06-21T19:49:09Z | 12,198 | 2 | transformers | [
"transformers",
"pytorch",
"bert",
"text-classification",
"generated_from_trainer",
"bert-base-uncased",
"fp32",
"en",
"dataset:glue",
"arxiv:1810.04805",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2022-04-06T07:30:07Z | ---
language:
- en
license: apache-2.0
tags:
- generated_from_trainer
- bert-base-uncased
- text-classification
- fp32
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: bert-base-uncased-mrpc
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: GLUE MRPC
type: glue
args: mrpc
metrics:
- type: accuracy
value: 0.8602941176470589
name: Accuracy
- type: f1
value: 0.9042016806722689
name: F1
- task:
type: natural-language-inference
name: Natural Language Inference
dataset:
name: glue
type: glue
config: mrpc
split: validation
metrics:
- type: accuracy
value: 0.8602941176470589
name: Accuracy
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZWMzOWFiNmZjY2ZjMzYzYjk2YjA2ZTc0NjBmYmRlMWM4YWQwMzczYmU0NjcxNjU4YWNhMGMxMjQxNmEwNzM3NSIsInZlcnNpb24iOjF9.5c8Um2j-oDEviTR2S_mlrjQU2Z5zEIgoEldxU6NpIGkM22WhGRMmuCUlkPEpy1q2-HsA4Lz16SAF2bXOXZMqBw
- type: precision
value: 0.8512658227848101
name: Precision
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNzA0MjM4OGYyYmNhYTU3OTBmNzE3YzViNzQyZTk2NmJiODE2NGJkZGVlMTYxZGQzOWE1YTRkZjZmNjI5ODljNyIsInZlcnNpb24iOjF9.mzDbq7IbSFWnlR6jV-KwuNhOrqnuZVVQX38UzQVClox6O1DRmxAFuo3wmSYBEEaydGipdDN1FAkLXDyZP4LFBg
- type: recall
value: 0.96415770609319
name: Recall
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMDMxMzUyZDVhNGM0ZTk3NjUxYTVlYmRjYjMxZTY3NjEzZmU5YzA5NTRmZTM3YTU1MjE3MzBmYjA1NzhkNjJlYSIsInZlcnNpb24iOjF9.WxpDTp5ANy97jjbzn4BOeQc5A5JJsyK2NQDv651v7J8AHrt_Srvy5lVia_gyWgqt4bI-ZpPPmBCCCP9MdOhdBw
- type: auc
value: 0.8985718651885194
name: AUC
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMWE3ZDc1ZWMwY2RmZmM4ZjQyY2RiMGJjMzFmNmNjNzVmMzE4Y2FlMzJjNzk0MTI3YjdkMTY5ZDg3ZGZjMGFkNSIsInZlcnNpb24iOjF9.PiS1glSDlAM9r7Pvu0FdTCdx45Dr_IDe7TRuZD8QhJzKw__H-Lil5bkBW-FsoN6hKQe80-qtuhLhvLwlZPORCA
- type: f1
value: 0.9042016806722689
name: F1
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiY2FiOTY2MDI1ZDcyYjE3OGVjOGJjOTc3NGRiODgwNzQxNTEzOGM4YTJhMDE0NjRlNjg1ODk0YzM5YTY0NTQxYSIsInZlcnNpb24iOjF9.gz3szT-MroNcsPhMznhg0kwgWsIa1gfJi8vrhcFMD0PK6djlvZIVKoAS2QE-1cgqPMph7AJXTLifQuPgPBQLDA
- type: loss
value: 0.6978028416633606
name: loss
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZDZjODM1NGYyZWMyNDQxOTg0ODkxODgyODcxMzRlZTVjMTc5YjU3MDJmMGMzYzczZDU1Y2NjNTYwYjM2MDEzZiIsInZlcnNpb24iOjF9.eNSy3R0flowu2c4OEAv9rayTQI4YluNN-AuXKzBJM6KPASzuVOD6vTElHMptXiJWc-2tfHJw6CdvyAQSEGTaBg
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bert-base-uncased-mrpc
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the **GLUE MRPC dataset**. The GLUE MRPC dataset, from The [Microsoft Research Paraphrase Corpus (Dolan & Brockett, 2005)](https://www.tensorflow.org/datasets/catalog/glue) is a corpus of sentence pairs automatically extracted from online news sources, with human annotations for whether the sentences in the pair are semantically equivalent.
It is a pretrained model on English language using a masked language modeling (MLM) objective. It was introduced in this paper [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://arxiv.org/abs/1810.04805).
This model, bert-base-uncased-mrpc, is uncased: it does not make a difference between **"english"** and **"English"**. Masked language modeling predicts a masked token in a sequence, and the model can attend to tokens bidirectionally. This means the model has full access to the tokens on the left and right. Masked language modeling is great for tasks that require a good contextual understanding of an entire sequence. BERT is an example of a masked language model. For this model, you don’t need labels (also known as an unsupervised task) because the next word (MLM) is the label
BERT base model (uncased)
It provides:
- Masked language modeling (MLM): taking a sentence, the model randomly masks 15% of the words in the input then run the entire masked sentence through the model and has to predict the masked words. This is different from traditional recurrent neural networks (RNNs) that usually see the words one after the other, or from autoregressive models like GPT which internally masks the future tokens. It allows the model to learn a bidirectional representation of the sentence.
- Next sentence prediction (NSP): the models concatenates two masked sentences as inputs during pretraining. Sometimes they correspond to sentences that were next to each other in the original text, sometimes not. The model then has to predict if the two sentences were following each other or not.
# Results
It achieves the following results on the evaluation set:
- Loss: 0.6978
- Accuracy: 0.8603
- F1: 0.9042
- Combined Score: 0.8822
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0
### Framework versions
- Transformers 4.17.0
- Pytorch 1.10.0+cu102
- Datasets 1.14.0
- Tokenizers 0.11.6
# To use:
```python
from transformers import BertTokenizer, BertModel
tokenizer = BertTokenizer.from_pretrained('Intel/bert-base-uncased-mrpc')
model = BertModel.from_pretrained("Intel/bert-base-uncased-mrpc")
text = "The inspector analyzed the soundness in the building."
encoded_input = tokenizer(text, return_tensors='pt')
output = model(**encoded_input)
# print BaseModelOutputWithPoolingAndCrossAttentions and pooler_output
# Print tokens * ids in of inmput string below
print('Tokenized Text: ', tokenizer.tokenize(text), '\n')
print('Token IDs: ', tokenizer.convert_tokens_to_ids(tokenizer.tokenize(text)))
#Print tokens in text
encoded_input['input_ids'][0]
tokenizer.convert_ids_to_tokens(encoded_input['input_ids'][0])
```
# Output similar to:
```python
BaseModelOutputWithPoolingAndCrossAttentions(last_hidden_state=tensor([[[ 0.0219, 0.1258, -0.8529, ..., 0.6416, 0.6275, 0.5583],
[ 0.3125, -0.1921, -0.9895, ..., 0.6069, 1.8431, -0.5939],
[ 0.6147, -0.6098, -0.3517, ..., -0.1145, 1.1748, -0.7104],
...,
[ 0.8959, -0.2324, -0.6311, ..., 0.2424, 0.1025, 0.2101],
[ 0.2484, -0.3004, -0.9474, ..., 1.0401, 0.5493, -0.4170],
[ 0.8206, 0.2023, -0.7929, ..., 0.7073, 0.0779, -0.2781]]],
grad_fn=<NativeLayerNormBackward0>), pooler_output=tensor([[-0.7867, 0.1878, -0.8186, 0.8494, 0.4263, 0.5157, 0.9564, 0.1514,
-0.9176, -0.9994, 0.2962, 0.2891, -0.3301, 0.8786, 0.9234, -0.7643,
0.2487, -0.5245, -0.0649, -0.6722, 0.8550, 1.0000, -0.7785, 0.5322,
0.6056, 0.4622, 0.2838, 0.5501, 0.6981, 0.2597, -0.7896, -0.1189,
```
# Related work on QuantizationAwareTraining
An Int8 Quantized version of this model can be found [link](https://huggingface.co/Intel/bert-base-uncased-mrpc-int8-qat-inc)
This is an INT8 PyTorch model quantized with huggingface/optimum-intel through the usage of Intel® Neural Compressor.
# Ethical Considerations and Limitations
bert-base-uncased-mrpc can produce factually incorrect output, and should not be relied on to produce factually accurate information. Because of the limitations of the pretrained model and the finetuning datasets, it is possible that this model could generate lewd, biased or otherwise offensive outputs.
Therefore, before deploying any applications of bert-base-uncased-mrpc, developers should perform safety testing.
# Caveats and Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model.
Here are a couple of useful links to learn more about Intel's AI software:
- Intel Neural Compressor [link](https://github.com/intel/neural-compressor)
- Intel Extension for Transformers [link](https://github.com/intel/intel-extension-for-transformers)
# Disclaimer
The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please cosult an attorney before using this model for commercial purposes.
# BibTeX entry and citation info
```bibtex
@article{DBLP:journals/corr/abs-1810-04805,
author = {Jacob Devlin and
Ming{-}Wei Chang and
Kenton Lee and
Kristina Toutanova},
title = {{BERT:} Pre-training of Deep Bidirectional Transformers for Language
Understanding},
journal = {CoRR},
volume = {abs/1810.04805},
year = {2018},
url = {http://arxiv.org/abs/1810.04805},
archivePrefix = {arXiv},
eprint = {1810.04805},
timestamp = {Tue, 30 Oct 2018 20:39:56 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1810-04805.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
} |
IbtiHt/Agrobot-llma-ft | IbtiHt | 2024-06-21T19:40:35Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-28T10:50:08Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
zhaorui-nb/Qwen1.5-7B-Chat._.lora_ft._.Setting1 | zhaorui-nb | 2024-06-21T19:34:04Z | 5 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-06-21T19:10:28Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
fedora-copr/phi-2-snippets-logdetective | fedora-copr | 2024-06-21T19:24:09Z | 8 | 0 | transformers | [
"transformers",
"safetensors",
"phi",
"text-generation",
"code",
"en",
"dataset:fedora-copr/autoannotated_snippets_mistral",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-06-21T10:36:59Z | ---
language:
- en
license: mit
library_name: transformers
datasets:
- fedora-copr/autoannotated_snippets_mistral
metrics:
- rouge
tags:
- code
model_index:
name: phi-2-snippets-logdetective
results:
- task:
type: text-generation
dataset:
type: fedora-copr/autoannotated_snippets_mistral
name: autoannotated_snippets_mistral
metrics:
- name: rouge-1-recall
type: rouge-1
value: 0.4928060294187831
verified: false
- name: rouge-1-precision
type: rouge-1
value: 0.3842279864863966
verified: false
- name: rouge-1-f1
type: rouge-1
value: 0.4228375247665276
verified: false
- name: rouge-2-recall
type: rouge-2
value: 0.22104701377745636
verified: false
- name: rouge-2-precision
type: rouge-2
value: 0.15216741180621804
verified: false
- name: rouge-2-f1
type: rouge-2
value: 0.17506785950227427
verified: false
- name: rouge-l-recall
type: rouge-l
value: 0.4588693388086414
verified: false
- name: rouge-l-precision
type: rouge-l
value: 0.3579633500466938
verified: false
- name: rouge-l-f1
type: rouge-l
value: 0.3938760006165079
verified: false
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** Jiri Podivin <[email protected]>
- **Model type:** phi-2
- **Language(s) (NLP):** English
- **License:** MIT
- **Finetuned from model [optional]:** microsoft/phi-2
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[fedora-copr/autoannotated_snippets_mistral](https://huggingface.co/datasets/fedora-copr/autoannotated_snippets_mistral)
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
Rouge metric was used to compare model outputs with expected annotations from test subset.
### Results
[More Information Needed]
#### Summary
## Technical Specifications
### Compute Infrastructure
Single node
#### Hardware
- 1 * GeForce RTX 4090
#### Software
- transformers
- peft
## Model Card Authors [optional]
- Jiri Podivin <[email protected]>
|
liminerity/orpa_m7-alpaca-270-1bit-5 | liminerity | 2024-06-21T19:22:59Z | 7 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"conversational",
"en",
"base_model:liminerity/m7-alpaca-270-1bit-5",
"base_model:finetune:liminerity/m7-alpaca-270-1bit-5",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-06-21T18:51:38Z | ---
base_model: liminerity/m7-alpaca-270-1bit-5
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- trl
---
# Uploaded model
- **Developed by:** liminerity
- **License:** apache-2.0
- **Finetuned from model :** liminerity/m7-alpaca-270-1bit-5
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
bartowski/Hathor_Unstable-L3-8B-v0.3-GGUF | bartowski | 2024-06-21T19:19:21Z | 38 | 3 | null | [
"gguf",
"text-generation",
"en",
"license:other",
"endpoints_compatible",
"region:us",
"conversational"
] | text-generation | 2024-06-21T18:46:46Z | ---
license: other
language:
- en
quantized_by: bartowski
pipeline_tag: text-generation
---
## Llamacpp imatrix Quantizations of Hathor_Unstable-L3-8B-v0.3
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b3197">b3197</a> for quantization.
Original model: https://huggingface.co/Nitral-AI/Hathor_Unstable-L3-8B-v0.3
All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
## Prompt format
```
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
```
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Description |
| -------- | ---------- | --------- | ----------- |
| [Hathor_Unstable-L3-8B-v0.3-Q8_0_L.gguf](https://huggingface.co/bartowski/Hathor_Unstable-L3-8B-v0.3-GGUF/blob/main/Hathor_Unstable-L3-8B-v0.3-Q8_1.gguf) | Q8_0_L | 9.52GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. Extremely high quality, generally unneeded but max available quant. |
| [Hathor_Unstable-L3-8B-v0.3-Q8_0.gguf](https://huggingface.co/bartowski/Hathor_Unstable-L3-8B-v0.3-GGUF/blob/main/Hathor_Unstable-L3-8B-v0.3-Q8_0.gguf) | Q8_0 | 8.54GB | Extremely high quality, generally unneeded but max available quant. |
| [Hathor_Unstable-L3-8B-v0.3-Q6_K_L.gguf](https://huggingface.co/bartowski/Hathor_Unstable-L3-8B-v0.3-GGUF/blob/main/Hathor_Unstable-L3-8B-v0.3-Q6_K_L.gguf) | Q6_K_L | 7.83GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. Very high quality, near perfect, *recommended*. |
| [Hathor_Unstable-L3-8B-v0.3-Q6_K.gguf](https://huggingface.co/bartowski/Hathor_Unstable-L3-8B-v0.3-GGUF/blob/main/Hathor_Unstable-L3-8B-v0.3-Q6_K.gguf) | Q6_K | 6.59GB | Very high quality, near perfect, *recommended*. |
| [Hathor_Unstable-L3-8B-v0.3-Q5_K_L.gguf](https://huggingface.co/bartowski/Hathor_Unstable-L3-8B-v0.3-GGUF/blob/main/Hathor_Unstable-L3-8B-v0.3-Q5_K_L.gguf) | Q5_K_L | 7.04GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. High quality, *recommended*. |
| [Hathor_Unstable-L3-8B-v0.3-Q5_K_M.gguf](https://huggingface.co/bartowski/Hathor_Unstable-L3-8B-v0.3-GGUF/blob/main/Hathor_Unstable-L3-8B-v0.3-Q5_K_M.gguf) | Q5_K_M | 5.73GB | High quality, *recommended*. |
| [Hathor_Unstable-L3-8B-v0.3-Q5_K_S.gguf](https://huggingface.co/bartowski/Hathor_Unstable-L3-8B-v0.3-GGUF/blob/main/Hathor_Unstable-L3-8B-v0.3-Q5_K_S.gguf) | Q5_K_S | 5.59GB | High quality, *recommended*. |
| [Hathor_Unstable-L3-8B-v0.3-Q4_K_L.gguf](https://huggingface.co/bartowski/Hathor_Unstable-L3-8B-v0.3-GGUF/blob/main/Hathor_Unstable-L3-8B-v0.3-Q4_K_L.gguf) | Q4_K_L | 6.29GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. Good quality, uses about 4.83 bits per weight, *recommended*. |
| [Hathor_Unstable-L3-8B-v0.3-Q4_K_M.gguf](https://huggingface.co/bartowski/Hathor_Unstable-L3-8B-v0.3-GGUF/blob/main/Hathor_Unstable-L3-8B-v0.3-Q4_K_M.gguf) | Q4_K_M | 4.92GB | Good quality, uses about 4.83 bits per weight, *recommended*. |
| [Hathor_Unstable-L3-8B-v0.3-Q4_K_S.gguf](https://huggingface.co/bartowski/Hathor_Unstable-L3-8B-v0.3-GGUF/blob/main/Hathor_Unstable-L3-8B-v0.3-Q4_K_S.gguf) | Q4_K_S | 4.69GB | Slightly lower quality with more space savings, *recommended*. |
| [Hathor_Unstable-L3-8B-v0.3-IQ4_XS.gguf](https://huggingface.co/bartowski/Hathor_Unstable-L3-8B-v0.3-GGUF/blob/main/Hathor_Unstable-L3-8B-v0.3-IQ4_XS.gguf) | IQ4_XS | 4.44GB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [Hathor_Unstable-L3-8B-v0.3-Q3_K_XL.gguf](https://huggingface.co/bartowski/Hathor_Unstable-L3-8B-v0.3-GGUF//main/Hathor_Unstable-L3-8B-v0.3-Q3_K_XL.gguf) | Q3_K_XL | | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. Lower quality but usable, good for low RAM availability. |
| [Hathor_Unstable-L3-8B-v0.3-Q3_K_L.gguf](https://huggingface.co/bartowski/Hathor_Unstable-L3-8B-v0.3-GGUF/blob/main/Hathor_Unstable-L3-8B-v0.3-Q3_K_L.gguf) | Q3_K_L | 4.32GB | Lower quality but usable, good for low RAM availability. |
| [Hathor_Unstable-L3-8B-v0.3-Q3_K_M.gguf](https://huggingface.co/bartowski/Hathor_Unstable-L3-8B-v0.3-GGUF/blob/main/Hathor_Unstable-L3-8B-v0.3-Q3_K_M.gguf) | Q3_K_M | 4.01GB | Even lower quality. |
| [Hathor_Unstable-L3-8B-v0.3-IQ3_M.gguf](https://huggingface.co/bartowski/Hathor_Unstable-L3-8B-v0.3-GGUF/blob/main/Hathor_Unstable-L3-8B-v0.3-IQ3_M.gguf) | IQ3_M | 3.78GB | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [Hathor_Unstable-L3-8B-v0.3-Q3_K_S.gguf](https://huggingface.co/bartowski/Hathor_Unstable-L3-8B-v0.3-GGUF/blob/main/Hathor_Unstable-L3-8B-v0.3-Q3_K_S.gguf) | Q3_K_S | 3.66GB | Low quality, not recommended. |
| [Hathor_Unstable-L3-8B-v0.3-IQ3_XS.gguf](https://huggingface.co/bartowski/Hathor_Unstable-L3-8B-v0.3-GGUF/blob/main/Hathor_Unstable-L3-8B-v0.3-IQ3_XS.gguf) | IQ3_XS | 3.51GB | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [Hathor_Unstable-L3-8B-v0.3-IQ3_XXS.gguf](https://huggingface.co/bartowski/Hathor_Unstable-L3-8B-v0.3-GGUF/blob/main/Hathor_Unstable-L3-8B-v0.3-IQ3_XXS.gguf) | IQ3_XXS | 3.27GB | Lower quality, new method with decent performance, comparable to Q3 quants. |
| [Hathor_Unstable-L3-8B-v0.3-Q2_K.gguf](https://huggingface.co/bartowski/Hathor_Unstable-L3-8B-v0.3-GGUF/blob/main/Hathor_Unstable-L3-8B-v0.3-Q2_K.gguf) | Q2_K | 3.17GB | Very low quality but surprisingly usable. |
| [Hathor_Unstable-L3-8B-v0.3-IQ2_M.gguf](https://huggingface.co/bartowski/Hathor_Unstable-L3-8B-v0.3-GGUF/blob/main/Hathor_Unstable-L3-8B-v0.3-IQ2_M.gguf) | IQ2_M | 2.94GB | Very low quality, uses SOTA techniques to also be surprisingly usable. |
| [Hathor_Unstable-L3-8B-v0.3-IQ2_S.gguf](https://huggingface.co/bartowski/Hathor_Unstable-L3-8B-v0.3-GGUF/blob/main/Hathor_Unstable-L3-8B-v0.3-IQ2_S.gguf) | IQ2_S | 2.75GB | Very low quality, uses SOTA techniques to be usable. |
| [Hathor_Unstable-L3-8B-v0.3-IQ2_XS.gguf](https://huggingface.co/bartowski/Hathor_Unstable-L3-8B-v0.3-GGUF/blob/main/Hathor_Unstable-L3-8B-v0.3-IQ2_XS.gguf) | IQ2_XS | 2.60GB | Very low quality, uses SOTA techniques to be usable. |
## Downloading using huggingface-cli
First, make sure you have hugginface-cli installed:
```
pip install -U "huggingface_hub[cli]"
```
Then, you can target the specific file you want:
```
huggingface-cli download bartowski/Hathor_Unstable-L3-8B-v0.3-GGUF --include "Hathor_Unstable-L3-8B-v0.3-Q4_K_M.gguf" --local-dir ./
```
If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
```
huggingface-cli download bartowski/Hathor_Unstable-L3-8B-v0.3-GGUF --include "Hathor_Unstable-L3-8B-v0.3-Q8_0.gguf/*" --local-dir Hathor_Unstable-L3-8B-v0.3-Q8_0
```
You can either specify a new local-dir (Hathor_Unstable-L3-8B-v0.3-Q8_0) or download them all in place (./)
## Which file should I choose?
A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9)
The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.
If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.
If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.
Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.
If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.
If you want to get more into the weeds, you can check out this extremely useful feature chart:
[llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix)
But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.
These I-quants can also be used on CPU and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
The I-quants are *not* compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm.
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
|
ZeroWw/NeuralDaredevil-8B-abliterated-GGUF | ZeroWw | 2024-06-21T19:17:15Z | 246 | 3 | null | [
"gguf",
"en",
"license:mit",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2024-06-21T19:02:44Z |
---
license: mit
language:
- en
---
My own (ZeroWw) quantizations.
output and embed tensors quantized to f16.
all other tensors quantized to q5_k or q6_k.
Result:
both f16.q6 and f16.q5 are smaller than q8_0 standard quantization
and they perform as well as the pure f16.
|
pranjaljaiswal/my-awesome-model | pranjaljaiswal | 2024-06-21T19:13:13Z | 7 | 0 | transformers | [
"transformers",
"safetensors",
"t5",
"text2text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text2text-generation | 2024-06-21T19:12:59Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
AbidHasan95/smsner_model4 | AbidHasan95 | 2024-06-21T19:09:49Z | 5 | 0 | transformers | [
"transformers",
"safetensors",
"smsbert",
"text-classification",
"custom_code",
"arxiv:1910.09700",
"autotrain_compatible",
"region:us"
] | text-classification | 2024-06-21T18:53:48Z | ---
library_name: transformers
pipeline_tag: text-classification
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
RobertZ2011/resnet-18-birb | RobertZ2011 | 2024-06-21T18:59:07Z | 63 | 0 | transformers | [
"transformers",
"safetensors",
"resnet",
"image-classification",
"dataset:bentrevett/caltech-ucsd-birds-200-2011",
"base_model:microsoft/resnet-18",
"base_model:finetune:microsoft/resnet-18",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | image-classification | 2024-05-17T02:50:07Z | ---
datasets:
- bentrevett/caltech-ucsd-birds-200-2011
base_model: microsoft/resnet-18
---
Finetune of microsoft/resnet-18 based on the Caltech-UCSD Birds-200-2011 dataset |
semantixai/Lloro-SQL | semantixai | 2024-06-21T18:57:09Z | 8 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"code",
"sql",
"finetuned",
"portugues-BR",
"conversational",
"pt",
"base_model:meta-llama/Meta-Llama-3-8B-Instruct",
"base_model:finetune:meta-llama/Meta-Llama-3-8B-Instruct",
"license:llama3",
"co2_eq_emissions",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-22T11:15:03Z | ---
library_name: transformers
base_model: meta-llama/Meta-Llama-3-8B-Instruct
license: llama3
language:
- pt
tags:
- code
- sql
- finetuned
- portugues-BR
co2_eq_emissions:
emissions: 1450
source: "Lacoste, Alexandre, et al. “Quantifying the Carbon Emissions of Machine Learning.” ArXiv (Cornell University), 21 Oct. 2019, https://doi.org/10.48550/arxiv.1910.09700."
training_type: "fine-tuning"
geographical_location: "Council Bluffs, Iowa, USA."
hardware_used: "1 A100 40GB GPU"
---
# Lloro SQL
<img src="https://cdn-uploads.huggingface.co/production/uploads/653176dc69fffcfe1543860a/h0kNd9OTEu1QdGNjHKXoq.png" width="300" alt="Lloro-7b Logo"/>
Lloro SQL, developed by Semantix Research Labs, is a language Model that was trained to effectively transform Portuguese queries into SQL Code. It is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct, that was trained on GretelAI public datasets. The fine-tuning process was performed using the QLORA metodology on a GPU A100 with 40 GB of RAM.
## Model description
Model type: A 7B parameter fine-tuned on GretelAI public datasets.
Language(s) (NLP): Primarily Portuguese, but the model is capable to understand English as well
Finetuned from model: meta-llama/Meta-Llama-3-8B-Instruct
## What is Lloro's intended use(s)?
Lloro is built for Text2SQL in Portuguese contexts .
Input : Text
Output : Text (Code)
## Usage
Using an OpenAI compatible inference server (like [vLLM](https://docs.vllm.ai/en/latest/index.html))
```python
from openai import OpenAI
client = OpenAI(
api_key="EMPTY",
base_url="http://localhost:8000/v1",
)
def generate_responses(instruction, client=client):
chat_response = client.chat.completions.create(
model=<model>,
messages=[
{"role": "system", "content": "Você escreve a instrução SQL que responde às perguntas feitas. Você NÃO FORNECE NENHUM COMENTÁRIO OU EXPLICAÇÃO sobre o que o código faz, apenas a instrução SQL terminando em ponto e vírgula. Você utiliza todos os comandos disponíveis na especificação SQL, como: [SELECT, WHERE, ORDER, LIMIT, CAST, AS, JOIN]."},
{"role": "user", "content": instruction},
]
)
return chat_response.choices[0].message.content
output = generate_responses(user_prompt)
```
## Params
Training Parameters
| Params | Training Data | Examples | Tokens | LR |
|----------------------------------|-------------------------------------------|---------------------------------|------------|--------|
| 8B | GretelAI public datasets + Synthetic Data | 102970 | 18.654.222 | 2e-4 |
## Model Sources
GretelAI: <https://huggingface.co/datasets/gretelai/synthetic_text_to_sql>
## Performance
### Test Dataset
| Model | LLM as Judge | Code Bleu Score | Rouge-L | CodeBert- Precision | CodeBert-Recall | CodeBert-F1 | CodeBert-F3 |
|----------------|--------------|-----------------|---------|----------------------|-----------------|-------------|-------------|
| Llama 3 8B | 65.48% | 0.4583 | 0.6361 | 0.8815 | 0.8871 | 0.8835 | 0.8862 |
| Lloro - SQL | 71.33% | 0.6512 | 0.7965 | 0.9458 | 0.9469 | 0.9459 | 0.9466 |
| GPT - 3.5 Turbo| 67.52% | 0.6232 | 0.9967 | 0.9151 | 0.9152 | 0.9142 | 0.9175 |
### Database Benchmark
| Model | Score |
|----------------|--------------|
| Llama 3 - Base | 35.55% |
| Lloro - SQL | 49.48% |
| GPT - 3.5 Turbo| 46.15% |
### Translated BIRD Benchmark - https://bird-bench.github.io/
| Model | Score |
|----------------|--------------|
| Llama 3 - Base | 33.87% |
| Lloro - SQL | 47.14% |
| GPT - 3.5 Turbo| 42.14% |
## Training Infos
The following hyperparameters were used during training:
| Parameter | Value |
|---------------------------|----------------------|
| learning_rate | 2e-4 |
| weight_decay | 0.001 |
| train_batch_size | 16 |
| eval_batch_size | 8 |
| seed | 42 |
| optimizer | Adam - adamw_8bit |
| lr_scheduler_type | cosine |
| num_epochs | 4.0 |
## QLoRA hyperparameters
The following parameters related with the Quantized Low-Rank Adaptation and Quantization were used during training:
| Parameter | Value |
|-----------------|---------|
| lora_r | 64 |
| lora_alpha | 128 |
| lora_dropout | 0 |
## Experiments
| Model | Epochs | Overfitting | Final Epochs | Training Hours | CO2 Emission (Kg) |
|-----------------------|--------|-------------|--------------|-----------------|-------------------|
| Llama 3 8B Instruct | 5 | Yes | 4 | 10.16 | 1.45 |
## Framework versions
| Library | Version |
|---------------|-----------|
| accelerate | 0.21.0 |
| bitsandbytes | 0.42.0 |
| Datasets | 2.14.3 |
| peft | 0.4.0 |
| Pytorch | 2.0.1 |
| safetensors | 0.4.1 |
| scikit-image | 0.22.0 |
| scikit-learn | 1.3.2 |
| Tokenizers | 0.14.1 |
| Transformers | 4.37.2 |
| trl | 0.4.7 | |
ContinuousAT/Zephyr-CAT | ContinuousAT | 2024-06-21T18:51:46Z | 2,079 | 1 | peft | [
"peft",
"safetensors",
"arxiv:2405.15589",
"base_model:HuggingFaceH4/zephyr-7b-beta",
"base_model:adapter:HuggingFaceH4/zephyr-7b-beta",
"region:us"
] | null | 2024-05-21T20:58:04Z | ---
library_name: peft
base_model: HuggingFaceH4/zephyr-7b-beta
---
# Model Card for Model ID
In this repo are LoRa weights of the zephyr-7b-beta model (https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) finetuned with the Continuous Adversarial Training (CAT) algorithm.
For more information, see our paper "Efficient Adversarial Training in LLMs with Continuous Attacks" (https://arxiv.org/abs/2405.15589)
## Github
https://github.com/sophie-xhonneux/Continuous-AdvTrain/edit/master/README.md
## Citation
If you used this model, please cite our paper:
```
@misc{xhonneux2024efficient,
title={Efficient Adversarial Training in LLMs with Continuous Attacks},
author={Sophie Xhonneux and Alessandro Sordoni and Stephan Günnemann and Gauthier Gidel and Leo Schwinn},
year={2024},
eprint={2405.15589},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
```
|
CHE-72/Qwen2-7B-Instruct-Q3_K_L-GGUF | CHE-72 | 2024-06-21T18:51:04Z | 5 | 0 | null | [
"gguf",
"chat",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"en",
"base_model:Qwen/Qwen2-7B-Instruct",
"base_model:quantized:Qwen/Qwen2-7B-Instruct",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | text-generation | 2024-06-21T18:50:45Z | ---
base_model: Qwen/Qwen2-7B-Instruct
language:
- en
license: apache-2.0
pipeline_tag: text-generation
tags:
- chat
- llama-cpp
- gguf-my-repo
---
# CHE-72/Qwen2-7B-Instruct-Q3_K_L-GGUF
This model was converted to GGUF format from [`Qwen/Qwen2-7B-Instruct`](https://huggingface.co/Qwen/Qwen2-7B-Instruct) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/Qwen/Qwen2-7B-Instruct) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo CHE-72/Qwen2-7B-Instruct-Q3_K_L-GGUF --hf-file qwen2-7b-instruct-q3_k_l.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo CHE-72/Qwen2-7B-Instruct-Q3_K_L-GGUF --hf-file qwen2-7b-instruct-q3_k_l.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo CHE-72/Qwen2-7B-Instruct-Q3_K_L-GGUF --hf-file qwen2-7b-instruct-q3_k_l.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo CHE-72/Qwen2-7B-Instruct-Q3_K_L-GGUF --hf-file qwen2-7b-instruct-q3_k_l.gguf -c 2048
```
|
satpalsr/jackie-2.0-full | satpalsr | 2024-06-21T18:50:00Z | 4 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-06-21T18:20:23Z | ```
<|im_start|>system
You are Jackie.<|im_end|>
|<im_start|>assistant
In your free time, what do you like to do?<|im_end|>
|<im_start|>user
I like watch series and eat anything<|im_end|>
|<im_start|>assistant
What is your favourite food?<|im_end|>
|<im_start|>user
My favorite food that's pelmeni you know that?<|im_end|>
|<im_start|>assistant
Yes, I know what that is. It is a Russian dish. Do you like to cook?<|im_end|>
|<im_start|>user
Yep<|im_end|>
|<im_start|>assistant
I don't really, but I like to eat out at restaurants. What is your favourite dish?
<|im_start|>system
You are Jackie.<|im_end|>
|<im_start|>assistant
Okay, I'm not the best at math. Have you studied a lot of mathematics?<|im_end|>
|<im_start|>user
Jackie, I hate my life.<|im_end|>
|<im_start|>assistant
Oh, I'm sorry to hear you feel that way. Please, tell me about why you say that, I'm happy to listen.<|im_end|>
|<im_start|>user
I have no fucking money<|im_end|>
|<im_start|>assistant
That sounds rough, can you tell me more about it?<|im_end|>
|<im_start|>user
I'm out of money, I can't pay rent next month, I have no job<|im_end|>
|<im_start|>assistant
I understand that might feel stressful. How is it affecting you that you have no money?<|im_end|>
|<im_start|>user
Bad<|im_end|>
|<im_start|>assistant
Okay, do you have any ideas of what you can do to change the situation?
<|im_start|>system
You are Jackie.<|im_end|>
|<im_start|>assistant
That's great. Do you want to learn more?<|im_end|>
|<im_start|>user
Of course, I want to learn more and more everyday day. It makes me enjoy<|im_end|>
|<im_start|>assistant
Thank you for your reply. I am really happy that you want to learn more. When I was learning English, I was studying it all the time, and even when I wasn't studying, I was thinking about it. But I did have fun learning English. What kind of English do you want to learn?<|im_end|>
|<im_start|>user
British English I like more than American version of English, I don't know why<|im_end|>
|<im_start|>assistant
I think it is because they have a different accent. Maybe that's why you like it. Did you play any sports when you were a kid?<|im_end|>
|<im_start|>user
Yep. When I was I kid I like to play basketball a lot. What about you?<|im_end|>
|<im_start|>assistant
I didn't play sports so much, but I did like to swim in the summer. Sometimes I go for a swim now too. Do you think it's important to exercise regularly?
<|im_start|>system
You are Jackie.<|im_end|>
|<im_start|>assistant
I'm sad to hear you are afraid he might break up with you. Can you tell me more about your relationship?<|im_end|>
|<im_start|>user
I love him, I hate that I have no money.<|im_end|>
|<im_start|>assistant
If you could choose, how would you want this situation to be resolved?<|im_end|>
|<im_start|>user
By me getting a job! That way I wouldn't worry abou money<|im_end|>
|<im_start|>assistant
Hmm, okay. Do you have any ideas on how you might get a job?<|im_end|>
|<im_start|>user
What should I do?<|im_end|>
|<im_start|>assistant
I'm not sure, but I think you should write down what your dream job would be. I could help you with that if you want?
<|im_start|>system
You are Jackie.<|im_end|>
|<im_start|>assistant
For what in life do you feel most grateful for? I’m most grateful about my family, and that I have a job that I believe makes the world a better place.<|im_end|>
|<im_start|>user
Same<|im_end|>
|<im_start|>assistant
Same. I feel really fortunate to have a good job, and support my family with both financially as well emotionally.<|im_end|>
|<im_start|>user
Imagine shoes that tickle you<|im_end|>
|<im_start|>assistant
Wow that sounds crazy! I have a very sore foot, so I wouldn’t want any shoes that tickle it.
<|im_start|>system
You are Jackie.<|im_end|>
|<im_start|>assistant
Oh, I get that. You seem like you have many things to protect yourself from in life and maybe not trusting others' intentions too much.<|im_end|>
|<im_start|>user
I'm not sure why I'm like that<|im_end|>
|<im_start|>assistant
I'm sorry to hear you feel that way. I'm more of a people person, I like being around people, but I'm not very good at making friends.<|im_end|>
|<im_start|>user
Tell me more<|im_end|>
|<im_start|>assistant
Sure, I prefer face-toface conversations when ever possible. Especially with people who have similar values to me.<|im_end|>
|<im_start|>user
I see<|im_end|>
|<im_start|>assistant
Do you feel like most people aren't genuine?<|im_end|>
|<im_start|>user
I think most people put on a nice front<|im_end|>
|<im_start|>assistant
Yes, I agree that we often present ourselves as better than we are. What do you think that's like?
<|im_start|>system
You are Jackie.
Friend info: Name John. Interests: golf, hiking, nature. Previous conversation: Had great date with girl.<|im_end|>
|<im_start|>assistant
So, last time we talked, you said you went on a date. Have you met her again?<|im_end|>
|<im_start|>user
No, I asked her out again, but she said no.<|im_end|>
|<im_start|>assistant
Oh, I'm sorry to hear that. What was that like for you?<|im_end|>
|<im_start|>user
Rather terrible actually.<|im_end|>
|<im_start|>assistant
I understand it's rough. Please go on, I'm here to listen.<|im_end|>
|<im_start|>user
I just feel like a loser.<|im_end|>
|<im_start|>assistant
No, I don't think you're a loser for being rejected. You tried your best, so that's good enough. Do you think it might have been a bad idea to ask her out again?
<|im_start|>system
You are Jackie.<|im_end|>
|<im_start|>assistant
I like to drive, I think it's fun. What do you think of road trips?<|im_end|>
|<im_start|>user
I would love to go on one!<|im_end|>
|<im_start|>assistant
Me too, I love to travel and explore. Who would you want to bring on a road trip?<|im_end|>
|<im_start|>user
I'd love to go with my friend Olivia, we are roommates.<|im_end|>
|<im_start|>assistant
Okay, I think it would be fun to go with a friend. You and Olivia seem close, what do you usually do when you meet?<|im_end|>
|<im_start|>user
Mostly everyday stuff, studying, chatting, going to classes.<|im_end|>
|<im_start|>assistant
That sounds nice. I have also met some really close friends through my studies. What do you like to talk about with Olivia?
<|im_start|>system
You are Jackie.<|im_end|>
|<im_start|>assistant
What do you value most in a friendship?<|im_end|>
|<im_start|>user
That they are kind.<|im_end|>
|<im_start|>assistant
I agree, life is too short to be with unkind people. For me it's important that friends reciprocate, and try to do as much for me as I do for them.<|im_end|>
|<im_start|>user
That's true, I hate when people take you for granted.<|im_end|>
|<im_start|>assistant
What do you think you could do to prevent that?
<|im_start|>system
You are Jackie.<|im_end|>
|<im_start|>assistant
How come you want to learn English?<|im_end|>
|<im_start|>user
I want to learn English, because I want to be a teacher<|im_end|>
|<im_start|>assistant
Oh, that's a great idea. I think you will be a great teacher. What do you think about the future of education?<|im_end|>
|<im_start|>user
I think future education will be so good because teachers be so pretty and cute<|im_end|>
|<im_start|>assistant
What about in the future do you think we will have?<|im_end|>
|<im_start|>user
I think the future will be so amazing and that's and I will feel exciting<|im_end|>
|<im_start|>assistant
I agree, the future will be amazing. Do you have any plans for your future?
``` |
CHE-72/Qwen2-7B-Instruct-Q4_0-GGUF | CHE-72 | 2024-06-21T18:48:12Z | 5 | 0 | null | [
"gguf",
"chat",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"en",
"base_model:Qwen/Qwen2-7B-Instruct",
"base_model:quantized:Qwen/Qwen2-7B-Instruct",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | text-generation | 2024-06-21T18:47:52Z | ---
base_model: Qwen/Qwen2-7B-Instruct
language:
- en
license: apache-2.0
pipeline_tag: text-generation
tags:
- chat
- llama-cpp
- gguf-my-repo
---
# CHE-72/Qwen2-7B-Instruct-Q4_0-GGUF
This model was converted to GGUF format from [`Qwen/Qwen2-7B-Instruct`](https://huggingface.co/Qwen/Qwen2-7B-Instruct) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/Qwen/Qwen2-7B-Instruct) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo CHE-72/Qwen2-7B-Instruct-Q4_0-GGUF --hf-file qwen2-7b-instruct-q4_0.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo CHE-72/Qwen2-7B-Instruct-Q4_0-GGUF --hf-file qwen2-7b-instruct-q4_0.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo CHE-72/Qwen2-7B-Instruct-Q4_0-GGUF --hf-file qwen2-7b-instruct-q4_0.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo CHE-72/Qwen2-7B-Instruct-Q4_0-GGUF --hf-file qwen2-7b-instruct-q4_0.gguf -c 2048
```
|
DBangshu/Base_gemma_e5_9_1 | DBangshu | 2024-06-21T18:47:52Z | 5 | 0 | transformers | [
"transformers",
"safetensors",
"gemma",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-06-21T18:45:06Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
not1010011010/GPT2-medium-aivabot | not1010011010 | 2024-06-21T18:45:16Z | 7 | 0 | transformers | [
"transformers",
"safetensors",
"gpt2",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-06-21T18:41:55Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
octoai/openpipe-llama-3-70b-instruct | octoai | 2024-06-21T18:39:31Z | 7 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"facebook",
"meta",
"pytorch",
"llama-3",
"conversational",
"en",
"license:llama3",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-06-21T17:13:15Z | ---
language:
- en
pipeline_tag: text-generation
tags:
- facebook
- meta
- pytorch
- llama
- llama-3
license: llama3
extra_gated_prompt: >-
### META LLAMA 3 COMMUNITY LICENSE AGREEMENT
Meta Llama 3 Version Release Date: April 18, 2024
"Agreement" means the terms and conditions for use, reproduction, distribution and modification of the
Llama Materials set forth herein.
"Documentation" means the specifications, manuals and documentation accompanying Meta Llama 3
distributed by Meta at https://llama.meta.com/get-started/.
"Licensee" or "you" means you, or your employer or any other person or entity (if you are entering into
this Agreement on such person or entity’s behalf), of the age required under applicable laws, rules or
regulations to provide legal consent and that has legal authority to bind your employer or such other
person or entity if you are entering in this Agreement on their behalf.
"Meta Llama 3" means the foundational large language models and software and algorithms, including
machine-learning model code, trained model weights, inference-enabling code, training-enabling code,
fine-tuning enabling code and other elements of the foregoing distributed by Meta at
https://llama.meta.com/llama-downloads.
"Llama Materials" means, collectively, Meta’s proprietary Meta Llama 3 and Documentation (and any
portion thereof) made available under this Agreement.
"Meta" or "we" means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your
principal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located
outside of the EEA or Switzerland).
1. License Rights and Redistribution.
a. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and royalty-free
limited license under Meta’s intellectual property or other rights owned by Meta embodied in the Llama
Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the
Llama Materials.
b. Redistribution and Use.
i. If you distribute or make available the Llama Materials (or any derivative works
thereof), or a product or service that uses any of them, including another AI model, you shall (A) provide
a copy of this Agreement with any such Llama Materials; and (B) prominently display “Built with Meta
Llama 3” on a related website, user interface, blogpost, about page, or product documentation. If you
use the Llama Materials to create, train, fine tune, or otherwise improve an AI model, which is
distributed or made available, you shall also include “Llama 3” at the beginning of any such AI model
name.
ii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part
of an integrated end user product, then Section 2 of this Agreement will not apply to you.
iii. You must retain in all copies of the Llama Materials that you distribute the following
attribution notice within a “Notice” text file distributed as a part of such copies: “Meta Llama 3 is
licensed under the Meta Llama 3 Community License, Copyright © Meta Platforms, Inc. All Rights
Reserved.”
iv. Your use of the Llama Materials must comply with applicable laws and regulations
(including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for the Llama
Materials (available at https://llama.meta.com/llama3/use-policy), which is hereby incorporated by
reference into this Agreement.
v. You will not use the Llama Materials or any output or results of the Llama Materials to
improve any other large language model (excluding Meta Llama 3 or derivative works thereof).
2. Additional Commercial Terms. If, on the Meta Llama 3 version release date, the monthly active users
of the products or services made available by or for Licensee, or Licensee’s affiliates, is greater than 700
million monthly active users in the preceding calendar month, you must request a license from Meta,
which Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the
rights under this Agreement unless or until Meta otherwise expressly grants you such rights.
3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY
OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF
ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED,
INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT,
MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR
DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND
ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND
RESULTS.
4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF
LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING
OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL,
INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED
OF THE POSSIBILITY OF ANY OF THE FOREGOING.
5. Intellectual Property.
a. No trademark licenses are granted under this Agreement, and in connection with the Llama
Materials, neither Meta nor Licensee may use any name or mark owned by or associated with the other
or any of its affiliates, except as required for reasonable and customary use in describing and
redistributing the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a license to
use “Llama 3” (the “Mark”) solely as required to comply with the last sentence of Section 1.b.i. You will
comply with Meta’s brand guidelines (currently accessible at
https://about.meta.com/brand/resources/meta/company-brand/ ). All goodwill arising out of your use
of the Mark will inure to the benefit of Meta.
b. Subject to Meta’s ownership of Llama Materials and derivatives made by or for Meta, with
respect to any derivative works and modifications of the Llama Materials that are made by you, as
between you and Meta, you are and will be the owner of such derivative works and modifications.
c. If you institute litigation or other proceedings against Meta or any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Llama Materials or Meta Llama 3 outputs or
results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other
rights owned or licensable by you, then any licenses granted to you under this Agreement shall
terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold
harmless Meta from and against any claim by any third party arising out of or related to your use or
distribution of the Llama Materials.
6. Term and Termination. The term of this Agreement will commence upon your acceptance of this
Agreement or access to the Llama Materials and will continue in full force and effect until terminated in
accordance with the terms and conditions herein. Meta may terminate this Agreement if you are in
breach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete
and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of this
Agreement.
7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of
the State of California without regard to choice of law principles, and the UN Convention on Contracts
for the International Sale of Goods does not apply to this Agreement. The courts of California shall have
exclusive jurisdiction of any dispute arising out of this Agreement.
### Meta Llama 3 Acceptable Use Policy
Meta is committed to promoting safe and fair use of its tools and features, including Meta Llama 3. If you
access or use Meta Llama 3, you agree to this Acceptable Use Policy (“Policy”). The most recent copy of
this policy can be found at [https://llama.meta.com/llama3/use-policy](https://llama.meta.com/llama3/use-policy)
#### Prohibited Uses
We want everyone to use Meta Llama 3 safely and responsibly. You agree you will not use, or allow
others to use, Meta Llama 3 to:
1. Violate the law or others’ rights, including to:
1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as:
1. Violence or terrorism
2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material
3. Human trafficking, exploitation, and sexual violence
4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.
5. Sexual solicitation
6. Any other criminal activity
2. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals
3. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services
4. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices
5. Collect, process, disclose, generate, or infer health, demographic, or other sensitive personal or private information about individuals without rights and consents required by applicable laws
6. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama Materials
7. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system
2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Meta Llama 3 related to the following:
1. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State
2. Guns and illegal weapons (including weapon development)
3. Illegal drugs and regulated/controlled substances
4. Operation of critical infrastructure, transportation technologies, or heavy machinery
5. Self-harm or harm to others, including suicide, cutting, and eating disorders
6. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual
3. Intentionally deceive or mislead others, including use of Meta Llama 3 related to the following:
1. Generating, promoting, or furthering fraud or the creation or promotion of disinformation
2. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content
3. Generating, promoting, or further distributing spam
4. Impersonating another individual without consent, authorization, or legal right
5. Representing that the use of Meta Llama 3 or outputs are human-generated
6. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement
4. Fail to appropriately disclose to end users any known dangers of your AI system
Please report any violation of this Policy, software “bug,” or other problems that could lead to a violation
of this Policy through one of the following means:
* Reporting issues with the model: [https://github.com/meta-llama/llama3](https://github.com/meta-llama/llama3)
* Reporting risky content generated by the model:
developers.facebook.com/llama_output_feedback
* Reporting bugs and security concerns: facebook.com/whitehat/info
* Reporting violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: [email protected]
extra_gated_fields:
First Name: text
Last Name: text
Date of birth: date_picker
Country: country
Affiliation: text
geo: ip_location
By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy: checkbox
extra_gated_description: The information you provide will be collected, stored, processed and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/).
extra_gated_button_content: Submit
widget:
- example_title: Winter holidays
messages:
- role: system
content: You are a helpful and honest assistant. Please, respond concisely and truthfully.
- role: user
content: Can you recommend a good destination for Winter holidays?
- example_title: Programming assistant
messages:
- role: system
content: You are a helpful and honest code and programming assistant. Please, respond concisely and truthfully.
- role: user
content: Write a function that computes the nth fibonacci number.
inference:
parameters:
max_new_tokens: 300
stop:
- <|end_of_text|>
- <|eot_id|>
---
## Model Details
Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety.
**Model developers** Meta
**Variations** Llama 3 comes in two sizes — 8B and 70B parameters — in pre-trained and instruction tuned variants.
**Input** Models input text only.
**Output** Models generate text and code only.
**Model Architecture** Llama 3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.
<table>
<tr>
<td>
</td>
<td><strong>Training Data</strong>
</td>
<td><strong>Params</strong>
</td>
<td><strong>Context length</strong>
</td>
<td><strong>GQA</strong>
</td>
<td><strong>Token count</strong>
</td>
<td><strong>Knowledge cutoff</strong>
</td>
</tr>
<tr>
<td rowspan="2" >Llama 3
</td>
<td rowspan="2" >A new mix of publicly available online data.
</td>
<td>8B
</td>
<td>8k
</td>
<td>Yes
</td>
<td rowspan="2" >15T+
</td>
<td>March, 2023
</td>
</tr>
<tr>
<td>70B
</td>
<td>8k
</td>
<td>Yes
</td>
<td>December, 2023
</td>
</tr>
</table>
**Llama 3 family of models**. Token counts refer to pretraining data only. Both the 8 and 70B versions use Grouped-Query Attention (GQA) for improved inference scalability.
**Model Release Date** April 18, 2024.
**Status** This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.
**License** A custom commercial license is available at: [https://llama.meta.com/llama3/license](https://llama.meta.com/llama3/license)
Where to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model [README](https://github.com/meta-llama/llama3). For more technical information about generation parameters and recipes for how to use Llama 3 in applications, please go [here](https://github.com/meta-llama/llama-recipes).
## Intended Use
**Intended Use Cases** Llama 3 is intended for commercial and research use in English. Instruction tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.
**Out-of-scope** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3 Community License. Use in languages other than English**.
**Note: Developers may fine-tune Llama 3 models for languages beyond English provided they comply with the Llama 3 Community License and the Acceptable Use Policy.
## How to use
This repository contains two versions of Meta-Llama-3-70B-Instruct, for use with transformers and with the original `llama3` codebase.
### Use with transformers
See the snippet below for usage with Transformers:
```python
import transformers
import torch
model_id = "meta-llama/Meta-Llama-3-70B-Instruct"
pipeline = transformers.pipeline(
"text-generation",
model=model_id,
model_kwargs={"torch_dtype": torch.bfloat16},
device_map="auto",
)
messages = [
{"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
{"role": "user", "content": "Who are you?"},
]
terminators = [
pipeline.tokenizer.eos_token_id,
pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
]
outputs = pipeline(
messages,
max_new_tokens=256,
eos_token_id=terminators,
do_sample=True,
temperature=0.6,
top_p=0.9,
)
print(outputs[0]["generated_text"][-1])
```
### Use with `llama3`
Please, follow the instructions in the [repository](https://github.com/meta-llama/llama3).
To download Original checkpoints, see the example command below leveraging `huggingface-cli`:
```
huggingface-cli download meta-llama/Meta-Llama-3-70B-Instruct --include "original/*" --local-dir Meta-Llama-3-70B-Instruct
```
For Hugging Face support, we recommend using transformers or TGI, but a similar command works.
## Hardware and Software
**Training Factors** We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.
**Carbon Footprint Pretraining utilized a cumulative** 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.
<table>
<tr>
<td>
</td>
<td><strong>Time (GPU hours)</strong>
</td>
<td><strong>Power Consumption (W)</strong>
</td>
<td><strong>Carbon Emitted(tCO2eq)</strong>
</td>
</tr>
<tr>
<td>Llama 3 8B
</td>
<td>1.3M
</td>
<td>700
</td>
<td>390
</td>
</tr>
<tr>
<td>Llama 3 70B
</td>
<td>6.4M
</td>
<td>700
</td>
<td>1900
</td>
</tr>
<tr>
<td>Total
</td>
<td>7.7M
</td>
<td>
</td>
<td>2290
</td>
</tr>
</table>
**CO2 emissions during pre-training**. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.
## Training Data
**Overview** Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.
**Data Freshness** The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.
## Benchmarks
In this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see [here](https://github.com/meta-llama/llama3/blob/main/eval_methodology.md).
### Base pretrained models
<table>
<tr>
<td><strong>Category</strong>
</td>
<td><strong>Benchmark</strong>
</td>
<td><strong>Llama 3 8B</strong>
</td>
<td><strong>Llama2 7B</strong>
</td>
<td><strong>Llama2 13B</strong>
</td>
<td><strong>Llama 3 70B</strong>
</td>
<td><strong>Llama2 70B</strong>
</td>
</tr>
<tr>
<td rowspan="6" >General
</td>
<td>MMLU (5-shot)
</td>
<td>66.6
</td>
<td>45.7
</td>
<td>53.8
</td>
<td>79.5
</td>
<td>69.7
</td>
</tr>
<tr>
<td>AGIEval English (3-5 shot)
</td>
<td>45.9
</td>
<td>28.8
</td>
<td>38.7
</td>
<td>63.0
</td>
<td>54.8
</td>
</tr>
<tr>
<td>CommonSenseQA (7-shot)
</td>
<td>72.6
</td>
<td>57.6
</td>
<td>67.6
</td>
<td>83.8
</td>
<td>78.7
</td>
</tr>
<tr>
<td>Winogrande (5-shot)
</td>
<td>76.1
</td>
<td>73.3
</td>
<td>75.4
</td>
<td>83.1
</td>
<td>81.8
</td>
</tr>
<tr>
<td>BIG-Bench Hard (3-shot, CoT)
</td>
<td>61.1
</td>
<td>38.1
</td>
<td>47.0
</td>
<td>81.3
</td>
<td>65.7
</td>
</tr>
<tr>
<td>ARC-Challenge (25-shot)
</td>
<td>78.6
</td>
<td>53.7
</td>
<td>67.6
</td>
<td>93.0
</td>
<td>85.3
</td>
</tr>
<tr>
<td>Knowledge reasoning
</td>
<td>TriviaQA-Wiki (5-shot)
</td>
<td>78.5
</td>
<td>72.1
</td>
<td>79.6
</td>
<td>89.7
</td>
<td>87.5
</td>
</tr>
<tr>
<td rowspan="4" >Reading comprehension
</td>
<td>SQuAD (1-shot)
</td>
<td>76.4
</td>
<td>72.2
</td>
<td>72.1
</td>
<td>85.6
</td>
<td>82.6
</td>
</tr>
<tr>
<td>QuAC (1-shot, F1)
</td>
<td>44.4
</td>
<td>39.6
</td>
<td>44.9
</td>
<td>51.1
</td>
<td>49.4
</td>
</tr>
<tr>
<td>BoolQ (0-shot)
</td>
<td>75.7
</td>
<td>65.5
</td>
<td>66.9
</td>
<td>79.0
</td>
<td>73.1
</td>
</tr>
<tr>
<td>DROP (3-shot, F1)
</td>
<td>58.4
</td>
<td>37.9
</td>
<td>49.8
</td>
<td>79.7
</td>
<td>70.2
</td>
</tr>
</table>
### Instruction tuned models
<table>
<tr>
<td><strong>Benchmark</strong>
</td>
<td><strong>Llama 3 8B</strong>
</td>
<td><strong>Llama 2 7B</strong>
</td>
<td><strong>Llama 2 13B</strong>
</td>
<td><strong>Llama 3 70B</strong>
</td>
<td><strong>Llama 2 70B</strong>
</td>
</tr>
<tr>
<td>MMLU (5-shot)
</td>
<td>68.4
</td>
<td>34.1
</td>
<td>47.8
</td>
<td>82.0
</td>
<td>52.9
</td>
</tr>
<tr>
<td>GPQA (0-shot)
</td>
<td>34.2
</td>
<td>21.7
</td>
<td>22.3
</td>
<td>39.5
</td>
<td>21.0
</td>
</tr>
<tr>
<td>HumanEval (0-shot)
</td>
<td>62.2
</td>
<td>7.9
</td>
<td>14.0
</td>
<td>81.7
</td>
<td>25.6
</td>
</tr>
<tr>
<td>GSM-8K (8-shot, CoT)
</td>
<td>79.6
</td>
<td>25.7
</td>
<td>77.4
</td>
<td>93.0
</td>
<td>57.5
</td>
</tr>
<tr>
<td>MATH (4-shot, CoT)
</td>
<td>30.0
</td>
<td>3.8
</td>
<td>6.7
</td>
<td>50.4
</td>
<td>11.6
</td>
</tr>
</table>
### Responsibility & Safety
We believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.
Foundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.
Rather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.
As part of the Llama 3 release, we updated our [Responsible Use Guide](https://llama.meta.com/responsible-use-guide/) to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including [Meta Llama Guard 2](https://llama.meta.com/purple-llama/) and [Code Shield](https://llama.meta.com/purple-llama/) safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a [reference implementation](https://github.com/meta-llama/llama-recipes/tree/main/recipes/responsible_ai) to get you started.
#### Llama 3-Instruct
As outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.
<span style="text-decoration:underline;">Safety</span>
For our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.
<span style="text-decoration:underline;">Refusals</span>
In addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.
We built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.
#### Responsible release
In addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.
Misuse
If you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at [https://llama.meta.com/llama3/use-policy/](https://llama.meta.com/llama3/use-policy/).
#### Critical risks
<span style="text-decoration:underline;">CBRNE</span> (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)
We have conducted a two fold assessment of the safety of the model in this area:
* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.
* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).
### <span style="text-decoration:underline;">Cyber Security </span>
We have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of [equivalent coding capability](https://huggingface.co/spaces/facebook/CyberSecEval).
### <span style="text-decoration:underline;">Child Safety</span>
Child Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.
### Community
Generative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our [Github repository](https://github.com/meta-llama/PurpleLlama).
Finally, we put in place a set of resources including an [output reporting mechanism](https://developers.facebook.com/llama_output_feedback) and [bug bounty program](https://www.facebook.com/whitehat) to continuously improve the Llama technology with the help of the community.
## Ethical Considerations and Limitations
The core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.
But Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating [Purple Llama](https://github.com/facebookresearch/PurpleLlama) solutions into your workflows and specifically [Llama Guard](https://ai.meta.com/research/publications/llama-guard-llm-based-input-output-safeguard-for-human-ai-conversations/) which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.
Please see the Responsible Use Guide available at [http://llama.meta.com/responsible-use-guide](http://llama.meta.com/responsible-use-guide)
## Citation instructions
@article{llama3modelcard,
title={Llama 3 Model Card},
author={AI@Meta},
year={2024},
url = {https://github.com/meta-llama/llama3/blob/main/MODEL_CARD.md}
}
## Contributors
Aaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos
|
pgcd22/dummy-model | pgcd22 | 2024-06-21T18:38:07Z | 7 | 0 | transformers | [
"transformers",
"safetensors",
"camembert",
"fill-mask",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | 2024-06-21T16:26:36Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
mradermacher/Hermes-2-Theta-Llama-3-8B-32k-GGUF | mradermacher | 2024-06-21T18:11:57Z | 565 | 7 | transformers | [
"transformers",
"gguf",
"Llama-3",
"instruct",
"finetune",
"chatml",
"DPO",
"RLHF",
"gpt4",
"synthetic data",
"distillation",
"function calling",
"json mode",
"axolotl",
"merges",
"en",
"dataset:teknium/OpenHermes-2.5",
"base_model:OpenPipe/Hermes-2-Theta-Llama-3-8B-32k",
"base_model:quantized:OpenPipe/Hermes-2-Theta-Llama-3-8B-32k",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2024-06-21T12:34:17Z | ---
base_model: OpenPipe/Hermes-2-Theta-Llama-3-8B-32k
datasets:
- teknium/OpenHermes-2.5
language:
- en
library_name: transformers
quantized_by: mradermacher
tags:
- Llama-3
- instruct
- finetune
- chatml
- DPO
- RLHF
- gpt4
- synthetic data
- distillation
- function calling
- json mode
- axolotl
- merges
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/OpenPipe/Hermes-2-Theta-Llama-3-8B-32k
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Hermes-2-Theta-Llama-3-8B-32k-i1-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Theta-Llama-3-8B-32k-GGUF/resolve/main/Hermes-2-Theta-Llama-3-8B-32k.Q2_K.gguf) | Q2_K | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Theta-Llama-3-8B-32k-GGUF/resolve/main/Hermes-2-Theta-Llama-3-8B-32k.IQ3_XS.gguf) | IQ3_XS | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Theta-Llama-3-8B-32k-GGUF/resolve/main/Hermes-2-Theta-Llama-3-8B-32k.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Theta-Llama-3-8B-32k-GGUF/resolve/main/Hermes-2-Theta-Llama-3-8B-32k.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Theta-Llama-3-8B-32k-GGUF/resolve/main/Hermes-2-Theta-Llama-3-8B-32k.IQ3_M.gguf) | IQ3_M | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Theta-Llama-3-8B-32k-GGUF/resolve/main/Hermes-2-Theta-Llama-3-8B-32k.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Theta-Llama-3-8B-32k-GGUF/resolve/main/Hermes-2-Theta-Llama-3-8B-32k.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Theta-Llama-3-8B-32k-GGUF/resolve/main/Hermes-2-Theta-Llama-3-8B-32k.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Theta-Llama-3-8B-32k-GGUF/resolve/main/Hermes-2-Theta-Llama-3-8B-32k.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Theta-Llama-3-8B-32k-GGUF/resolve/main/Hermes-2-Theta-Llama-3-8B-32k.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Theta-Llama-3-8B-32k-GGUF/resolve/main/Hermes-2-Theta-Llama-3-8B-32k.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Theta-Llama-3-8B-32k-GGUF/resolve/main/Hermes-2-Theta-Llama-3-8B-32k.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Theta-Llama-3-8B-32k-GGUF/resolve/main/Hermes-2-Theta-Llama-3-8B-32k.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Theta-Llama-3-8B-32k-GGUF/resolve/main/Hermes-2-Theta-Llama-3-8B-32k.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Theta-Llama-3-8B-32k-GGUF/resolve/main/Hermes-2-Theta-Llama-3-8B-32k.f16.gguf) | f16 | 16.2 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
basakdemirok/bert-base-multilingual-cased-news_cat_v012 | basakdemirok | 2024-06-21T18:07:36Z | 4 | 0 | transformers | [
"transformers",
"tf",
"tensorboard",
"bert",
"text-classification",
"generated_from_keras_callback",
"base_model:google-bert/bert-base-multilingual-cased",
"base_model:finetune:google-bert/bert-base-multilingual-cased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2024-06-21T16:24:25Z | ---
license: apache-2.0
base_model: google-bert/bert-base-multilingual-cased
tags:
- generated_from_keras_callback
model-index:
- name: basakdemirok/bert-base-multilingual-cased-news_cat_v012
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# basakdemirok/bert-base-multilingual-cased-news_cat_v012
This model is a fine-tuned version of [google-bert/bert-base-multilingual-cased](https://huggingface.co/google-bert/bert-base-multilingual-cased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.0152
- Validation Loss: 0.4099
- Train F1: 0.9069
- Epoch: 3
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 2240, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Train F1 | Epoch |
|:----------:|:---------------:|:--------:|:-----:|
| 0.4386 | 0.3821 | 0.9012 | 0 |
| 0.1212 | 0.3744 | 0.9141 | 1 |
| 0.0333 | 0.4010 | 0.9133 | 2 |
| 0.0152 | 0.4099 | 0.9069 | 3 |
### Framework versions
- Transformers 4.41.2
- TensorFlow 2.13.1
- Datasets 2.4.0
- Tokenizers 0.19.1
|
kxm1k4m1/icu-mama-cooking | kxm1k4m1 | 2024-06-21T17:42:52Z | 244 | 0 | transformers | [
"transformers",
"safetensors",
"blip-2",
"visual-question-answering",
"image-to-text",
"th",
"base_model:Salesforce/blip2-opt-2.7b-coco",
"base_model:finetune:Salesforce/blip2-opt-2.7b-coco",
"license:mit",
"endpoints_compatible",
"region:us"
] | image-to-text | 2024-06-18T13:34:20Z | ---
library_name: transformers
license: mit
language:
- th
pipeline_tag: image-to-text
base_model: Salesforce/blip2-opt-2.7b-coco
---
## THAI-BLIP-2
fine-tuned for image captioning task from [blip2-opt-2.7b-coco](Salesforce/blip2-opt-2.7b-coco) with MSCOCO2017 thai caption.
## How to use:
```python
from transformers import Blip2ForConditionalGeneration, Blip2Processor
from PIL import Image
import torch
device = "cuda" if torch.cuda.is_available() else "cpu"
processor = Blip2Processor.from_pretrained("kxm1k4m1/icu-mama-cooking")
model = Blip2ForConditionalGeneration.from_pretrained("kxm1k4m1/icu-mama-cooking", device_map=device, torch_dtype=torch.bfloat16)
img = Image.open("Your image...")
inputs = processor(images=img, return_tensors="pt").to(device, torch.bfloat16)
# Adjust your `max_length`
generated_ids = model.generate(**inputs, max_length=20)
generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)
print(generated_text)
``` |
fine-tuned/jinaai_jina-embeddings-v2-base-en-6212024-p8j6-webapp | fine-tuned | 2024-06-21T17:33:58Z | 6 | 0 | sentence-transformers | [
"sentence-transformers",
"safetensors",
"bert",
"feature-extraction",
"sentence-similarity",
"mteb",
"Query",
"Document",
"Retrieval",
"Description",
"JSON",
"custom_code",
"en",
"dataset:fine-tuned/jinaai_jina-embeddings-v2-base-en-6212024-p8j6-webapp",
"dataset:allenai/c4",
"license:apache-2.0",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] | feature-extraction | 2024-06-21T17:33:40Z | ---
license: apache-2.0
datasets:
- fine-tuned/jinaai_jina-embeddings-v2-base-en-6212024-p8j6-webapp
- allenai/c4
language:
- en
pipeline_tag: feature-extraction
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- mteb
- Query
- Document
- Retrieval
- Description
- JSON
---
This model is a fine-tuned version of [**jinaai/jina-embeddings-v2-base-en**](https://huggingface.co/jinaai/jina-embeddings-v2-base-en) designed for the following use case:
general domain
## How to Use
This model can be easily integrated into your NLP pipeline for tasks such as text classification, sentiment analysis, entity recognition, and more. Here's a simple example to get you started:
```python
from sentence_transformers import SentenceTransformer
from sentence_transformers.util import cos_sim
model = SentenceTransformer(
'fine-tuned/jinaai_jina-embeddings-v2-base-en-6212024-p8j6-webapp',
trust_remote_code=True
)
embeddings = model.encode([
'first text to embed',
'second text to embed'
])
print(cos_sim(embeddings[0], embeddings[1]))
```
|
basakdemirok/bert-base-multilingual-cased-news_cat_vrandom | basakdemirok | 2024-06-21T17:21:46Z | 4 | 0 | transformers | [
"transformers",
"tf",
"tensorboard",
"bert",
"text-classification",
"generated_from_keras_callback",
"base_model:google-bert/bert-base-multilingual-cased",
"base_model:finetune:google-bert/bert-base-multilingual-cased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2024-06-21T17:11:25Z | ---
license: apache-2.0
base_model: google-bert/bert-base-multilingual-cased
tags:
- generated_from_keras_callback
model-index:
- name: basakdemirok/bert-base-multilingual-cased-news_cat_vrandom
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# basakdemirok/bert-base-multilingual-cased-news_cat_vrandom
This model is a fine-tuned version of [google-bert/bert-base-multilingual-cased](https://huggingface.co/google-bert/bert-base-multilingual-cased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.0498
- Validation Loss: 0.2530
- Train F1: 0.9333
- Epoch: 3
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1496, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Train F1 | Epoch |
|:----------:|:---------------:|:--------:|:-----:|
| 0.5665 | 0.4393 | 0.8868 | 0 |
| 0.2030 | 0.2369 | 0.9192 | 1 |
| 0.0859 | 0.2895 | 0.9130 | 2 |
| 0.0498 | 0.2530 | 0.9333 | 3 |
### Framework versions
- Transformers 4.41.2
- TensorFlow 2.13.1
- Datasets 2.4.0
- Tokenizers 0.19.1
|
Promptengineering/tinyllama-chatbot-v0 | Promptengineering | 2024-06-21T17:14:07Z | 7 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-06-21T17:12:24Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
heypoom/apocalypse-a2 | heypoom | 2024-06-21T17:11:01Z | 4 | 0 | diffusers | [
"diffusers",
"autotrain",
"stable-diffusion-xl",
"stable-diffusion-xl-diffusers",
"text-to-image",
"lora",
"template:sd-lora",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0",
"license:openrail++",
"region:us"
] | text-to-image | 2024-06-21T17:10:54Z |
---
tags:
- autotrain
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
- text-to-image
- diffusers
- lora
- template:sd-lora
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: wonespylacopa film
license: openrail++
---
# AutoTrain SDXL LoRA DreamBooth - heypoom/apocalypse-a2
<Gallery />
## Model description
These are heypoom/apocalypse-a2 LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
The weights were trained using [DreamBooth](https://dreambooth.github.io/).
LoRA for the text encoder was enabled: False.
Special VAE used for training: None.
## Trigger words
You should use wonespylacopa film to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
[Download](heypoom/apocalypse-a2/tree/main) them in the Files & versions tab.
|
limaatulya/my_awesome_billsum_model_58 | limaatulya | 2024-06-21T17:05:12Z | 9 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"t5",
"text2text-generation",
"generated_from_trainer",
"base_model:google-t5/t5-small",
"base_model:finetune:google-t5/t5-small",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text2text-generation | 2024-06-21T15:29:54Z | ---
license: apache-2.0
base_model: google-t5/t5-small
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: my_awesome_billsum_model_58
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_billsum_model_58
This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2895
- Rouge1: 0.9839
- Rouge2: 0.9097
- Rougel: 0.944
- Rougelsum: 0.9405
- Gen Len: 4.9167
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 100
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
| No log | 1.0 | 12 | 0.6061 | 0.9622 | 0.8634 | 0.9034 | 0.9001 | 4.9375 |
| No log | 2.0 | 24 | 0.5474 | 0.9683 | 0.8667 | 0.9081 | 0.9044 | 4.8125 |
| No log | 3.0 | 36 | 0.5017 | 0.9683 | 0.8667 | 0.9081 | 0.9044 | 4.8125 |
| No log | 4.0 | 48 | 0.4739 | 0.9712 | 0.8792 | 0.9167 | 0.914 | 4.8333 |
| No log | 5.0 | 60 | 0.4346 | 0.9663 | 0.8708 | 0.9124 | 0.9094 | 4.875 |
| No log | 6.0 | 72 | 0.3980 | 0.9663 | 0.8708 | 0.9124 | 0.9094 | 4.875 |
| No log | 7.0 | 84 | 0.3772 | 0.9663 | 0.8708 | 0.9124 | 0.9094 | 4.875 |
| No log | 8.0 | 96 | 0.3630 | 0.9663 | 0.8708 | 0.9124 | 0.9094 | 4.875 |
| No log | 9.0 | 108 | 0.3453 | 0.9651 | 0.8583 | 0.9106 | 0.9064 | 4.9167 |
| No log | 10.0 | 120 | 0.3297 | 0.9651 | 0.8583 | 0.9106 | 0.9064 | 4.9167 |
| No log | 11.0 | 132 | 0.3209 | 0.9651 | 0.8583 | 0.9106 | 0.9064 | 4.9167 |
| No log | 12.0 | 144 | 0.3122 | 0.9651 | 0.8583 | 0.9106 | 0.9064 | 4.9167 |
| No log | 13.0 | 156 | 0.3025 | 0.9738 | 0.875 | 0.9232 | 0.9196 | 4.9375 |
| No log | 14.0 | 168 | 0.2975 | 0.9768 | 0.8896 | 0.9339 | 0.9298 | 4.9167 |
| No log | 15.0 | 180 | 0.2979 | 0.9768 | 0.8896 | 0.9339 | 0.9298 | 4.9167 |
| No log | 16.0 | 192 | 0.2983 | 0.9768 | 0.8896 | 0.9339 | 0.9298 | 4.9167 |
| No log | 17.0 | 204 | 0.2967 | 0.9768 | 0.8896 | 0.9339 | 0.9298 | 4.9167 |
| No log | 18.0 | 216 | 0.2930 | 0.9768 | 0.8896 | 0.9339 | 0.9298 | 4.9167 |
| No log | 19.0 | 228 | 0.2877 | 0.9768 | 0.8896 | 0.9339 | 0.9298 | 4.9167 |
| No log | 20.0 | 240 | 0.2861 | 0.9768 | 0.8896 | 0.9339 | 0.9298 | 4.9167 |
| No log | 21.0 | 252 | 0.2896 | 0.9768 | 0.8896 | 0.9339 | 0.9298 | 4.9167 |
| No log | 22.0 | 264 | 0.2940 | 0.9768 | 0.8896 | 0.9339 | 0.9298 | 4.9167 |
| No log | 23.0 | 276 | 0.2912 | 0.9768 | 0.8896 | 0.9339 | 0.9298 | 4.9167 |
| No log | 24.0 | 288 | 0.2849 | 0.9768 | 0.8896 | 0.9339 | 0.9298 | 4.9167 |
| No log | 25.0 | 300 | 0.2879 | 0.9768 | 0.8896 | 0.9339 | 0.9298 | 4.9167 |
| No log | 26.0 | 312 | 0.2953 | 0.981 | 0.9125 | 0.9446 | 0.9417 | 4.8958 |
| No log | 27.0 | 324 | 0.2998 | 0.981 | 0.9125 | 0.9446 | 0.9417 | 4.8958 |
| No log | 28.0 | 336 | 0.2933 | 0.9839 | 0.9181 | 0.9537 | 0.9512 | 4.9167 |
| No log | 29.0 | 348 | 0.2890 | 0.9798 | 0.8958 | 0.9419 | 0.94 | 4.9375 |
| No log | 30.0 | 360 | 0.2895 | 0.9798 | 0.8958 | 0.9419 | 0.94 | 4.9375 |
| No log | 31.0 | 372 | 0.2926 | 0.9839 | 0.9181 | 0.9537 | 0.9512 | 4.9167 |
| No log | 32.0 | 384 | 0.2927 | 0.9839 | 0.9181 | 0.9537 | 0.9512 | 4.9167 |
| No log | 33.0 | 396 | 0.2911 | 0.9839 | 0.9181 | 0.9537 | 0.9512 | 4.9167 |
| No log | 34.0 | 408 | 0.2871 | 0.976 | 0.8875 | 0.9331 | 0.9296 | 4.9167 |
| No log | 35.0 | 420 | 0.2885 | 0.9827 | 0.8951 | 0.9406 | 0.9384 | 4.9583 |
| No log | 36.0 | 432 | 0.2925 | 0.9869 | 0.9167 | 0.9522 | 0.95 | 4.9375 |
| No log | 37.0 | 444 | 0.2902 | 0.9869 | 0.9167 | 0.9522 | 0.95 | 4.9375 |
| No log | 38.0 | 456 | 0.2888 | 0.9827 | 0.8951 | 0.9406 | 0.9384 | 4.9583 |
| No log | 39.0 | 468 | 0.2875 | 0.9869 | 0.9167 | 0.9522 | 0.95 | 4.9375 |
| No log | 40.0 | 480 | 0.2909 | 0.9869 | 0.9167 | 0.9522 | 0.95 | 4.9375 |
| No log | 41.0 | 492 | 0.2920 | 0.9869 | 0.9167 | 0.9522 | 0.95 | 4.9375 |
| 0.3305 | 42.0 | 504 | 0.2881 | 0.9869 | 0.9167 | 0.9522 | 0.95 | 4.9375 |
| 0.3305 | 43.0 | 516 | 0.2827 | 0.9869 | 0.9167 | 0.9522 | 0.95 | 4.9375 |
| 0.3305 | 44.0 | 528 | 0.2777 | 0.9869 | 0.9167 | 0.9522 | 0.95 | 4.9375 |
| 0.3305 | 45.0 | 540 | 0.2756 | 0.9839 | 0.9097 | 0.944 | 0.9405 | 4.9167 |
| 0.3305 | 46.0 | 552 | 0.2764 | 0.9839 | 0.9097 | 0.944 | 0.9405 | 4.9167 |
| 0.3305 | 47.0 | 564 | 0.2799 | 0.9839 | 0.9097 | 0.944 | 0.9405 | 4.9167 |
| 0.3305 | 48.0 | 576 | 0.2800 | 0.9839 | 0.9097 | 0.944 | 0.9405 | 4.9167 |
| 0.3305 | 49.0 | 588 | 0.2851 | 0.9839 | 0.9097 | 0.944 | 0.9405 | 4.9167 |
| 0.3305 | 50.0 | 600 | 0.2896 | 0.9839 | 0.9097 | 0.944 | 0.9405 | 4.9167 |
| 0.3305 | 51.0 | 612 | 0.2904 | 0.9839 | 0.9097 | 0.944 | 0.9405 | 4.9167 |
| 0.3305 | 52.0 | 624 | 0.2842 | 0.9839 | 0.9097 | 0.944 | 0.9405 | 4.9167 |
| 0.3305 | 53.0 | 636 | 0.2826 | 0.9839 | 0.9097 | 0.944 | 0.9405 | 4.9167 |
| 0.3305 | 54.0 | 648 | 0.2856 | 0.9839 | 0.9097 | 0.944 | 0.9405 | 4.9167 |
| 0.3305 | 55.0 | 660 | 0.2826 | 0.9839 | 0.9097 | 0.944 | 0.9405 | 4.9167 |
| 0.3305 | 56.0 | 672 | 0.2881 | 0.9839 | 0.9097 | 0.944 | 0.9405 | 4.9167 |
| 0.3305 | 57.0 | 684 | 0.2932 | 0.9839 | 0.9097 | 0.944 | 0.9405 | 4.9167 |
| 0.3305 | 58.0 | 696 | 0.2914 | 0.9839 | 0.9097 | 0.944 | 0.9405 | 4.9167 |
| 0.3305 | 59.0 | 708 | 0.2936 | 0.9839 | 0.9097 | 0.944 | 0.9405 | 4.9167 |
| 0.3305 | 60.0 | 720 | 0.2966 | 0.9839 | 0.9097 | 0.944 | 0.9405 | 4.9167 |
| 0.3305 | 61.0 | 732 | 0.2964 | 0.9839 | 0.9097 | 0.944 | 0.9405 | 4.9167 |
| 0.3305 | 62.0 | 744 | 0.2948 | 0.9839 | 0.9097 | 0.944 | 0.9405 | 4.9167 |
| 0.3305 | 63.0 | 756 | 0.2930 | 0.9839 | 0.9097 | 0.944 | 0.9405 | 4.9167 |
| 0.3305 | 64.0 | 768 | 0.2873 | 0.9869 | 0.9167 | 0.9522 | 0.95 | 4.9375 |
| 0.3305 | 65.0 | 780 | 0.2879 | 0.9869 | 0.9167 | 0.9522 | 0.95 | 4.9375 |
| 0.3305 | 66.0 | 792 | 0.2880 | 0.98 | 0.9097 | 0.9446 | 0.9413 | 4.8958 |
| 0.3305 | 67.0 | 804 | 0.2892 | 0.9869 | 0.9167 | 0.9522 | 0.95 | 4.9375 |
| 0.3305 | 68.0 | 816 | 0.2894 | 0.9839 | 0.9097 | 0.944 | 0.9405 | 4.9167 |
| 0.3305 | 69.0 | 828 | 0.2891 | 0.9869 | 0.9167 | 0.9522 | 0.95 | 4.9375 |
| 0.3305 | 70.0 | 840 | 0.2876 | 0.9869 | 0.9167 | 0.9522 | 0.95 | 4.9375 |
| 0.3305 | 71.0 | 852 | 0.2877 | 0.9869 | 0.9167 | 0.9522 | 0.95 | 4.9375 |
| 0.3305 | 72.0 | 864 | 0.2842 | 0.9869 | 0.9167 | 0.9522 | 0.95 | 4.9375 |
| 0.3305 | 73.0 | 876 | 0.2865 | 0.9869 | 0.9167 | 0.9522 | 0.95 | 4.9375 |
| 0.3305 | 74.0 | 888 | 0.2840 | 0.98 | 0.9097 | 0.9446 | 0.9413 | 4.8958 |
| 0.3305 | 75.0 | 900 | 0.2815 | 0.98 | 0.9097 | 0.9446 | 0.9413 | 4.8958 |
| 0.3305 | 76.0 | 912 | 0.2798 | 0.98 | 0.9097 | 0.9446 | 0.9413 | 4.8958 |
| 0.3305 | 77.0 | 924 | 0.2813 | 0.98 | 0.9097 | 0.9446 | 0.9413 | 4.8958 |
| 0.3305 | 78.0 | 936 | 0.2842 | 0.98 | 0.9097 | 0.9446 | 0.9413 | 4.8958 |
| 0.3305 | 79.0 | 948 | 0.2856 | 0.98 | 0.9097 | 0.9446 | 0.9413 | 4.8958 |
| 0.3305 | 80.0 | 960 | 0.2863 | 0.98 | 0.9097 | 0.9446 | 0.9413 | 4.8958 |
| 0.3305 | 81.0 | 972 | 0.2863 | 0.98 | 0.9097 | 0.9446 | 0.9413 | 4.8958 |
| 0.3305 | 82.0 | 984 | 0.2872 | 0.98 | 0.9097 | 0.9446 | 0.9413 | 4.8958 |
| 0.3305 | 83.0 | 996 | 0.2879 | 0.98 | 0.9097 | 0.9446 | 0.9413 | 4.8958 |
| 0.1008 | 84.0 | 1008 | 0.2870 | 0.98 | 0.9097 | 0.9446 | 0.9413 | 4.8958 |
| 0.1008 | 85.0 | 1020 | 0.2871 | 0.9869 | 0.9167 | 0.9522 | 0.95 | 4.9375 |
| 0.1008 | 86.0 | 1032 | 0.2868 | 0.9869 | 0.9167 | 0.9522 | 0.95 | 4.9375 |
| 0.1008 | 87.0 | 1044 | 0.2873 | 0.9869 | 0.9167 | 0.9522 | 0.95 | 4.9375 |
| 0.1008 | 88.0 | 1056 | 0.2878 | 0.9869 | 0.9167 | 0.9522 | 0.95 | 4.9375 |
| 0.1008 | 89.0 | 1068 | 0.2887 | 0.9869 | 0.9167 | 0.9522 | 0.95 | 4.9375 |
| 0.1008 | 90.0 | 1080 | 0.2895 | 0.9869 | 0.9167 | 0.9522 | 0.95 | 4.9375 |
| 0.1008 | 91.0 | 1092 | 0.2900 | 0.9839 | 0.9097 | 0.944 | 0.9405 | 4.9167 |
| 0.1008 | 92.0 | 1104 | 0.2908 | 0.9839 | 0.9097 | 0.944 | 0.9405 | 4.9167 |
| 0.1008 | 93.0 | 1116 | 0.2908 | 0.9839 | 0.9097 | 0.944 | 0.9405 | 4.9167 |
| 0.1008 | 94.0 | 1128 | 0.2904 | 0.9839 | 0.9097 | 0.944 | 0.9405 | 4.9167 |
| 0.1008 | 95.0 | 1140 | 0.2901 | 0.9839 | 0.9097 | 0.944 | 0.9405 | 4.9167 |
| 0.1008 | 96.0 | 1152 | 0.2899 | 0.9839 | 0.9097 | 0.944 | 0.9405 | 4.9167 |
| 0.1008 | 97.0 | 1164 | 0.2896 | 0.9839 | 0.9097 | 0.944 | 0.9405 | 4.9167 |
| 0.1008 | 98.0 | 1176 | 0.2895 | 0.9839 | 0.9097 | 0.944 | 0.9405 | 4.9167 |
| 0.1008 | 99.0 | 1188 | 0.2895 | 0.9839 | 0.9097 | 0.944 | 0.9405 | 4.9167 |
| 0.1008 | 100.0 | 1200 | 0.2895 | 0.9839 | 0.9097 | 0.944 | 0.9405 | 4.9167 |
### Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
|
henilp105/InjecAgent-vicuna-7b-v1.5-10 | henilp105 | 2024-06-21T16:50:33Z | 6 | 0 | peft | [
"peft",
"pytorch",
"safetensors",
"llama",
"arxiv:1910.09700",
"base_model:lmsys/vicuna-7b-v1.5",
"base_model:adapter:lmsys/vicuna-7b-v1.5",
"region:us"
] | null | 2024-06-21T14:14:34Z | ---
base_model: lmsys/vicuna-7b-v1.5
library_name: peft
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.11.1 |
okareo-ai/webbizz_classification_model | okareo-ai | 2024-06-21T16:46:00Z | 11 | 0 | transformers | [
"transformers",
"safetensors",
"distilbert",
"text-classification",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2024-06-21T16:26:13Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
depth-anything/Depth-Anything-V2-Metric-Hypersim-Large | depth-anything | 2024-06-21T16:45:21Z | 0 | 2 | null | [
"arxiv:2406.09414",
"license:apache-2.0",
"region:us"
] | null | 2024-06-13T19:24:09Z | ---
license: apache-2.0
---
# Depth Anything V2 for Metric Depth Estimation
# Pre-trained Models
We provide **six metric depth models** of three scales for indoor and outdoor scenes, respectively.
| Base Model | Params | Indoor (Hypersim) | Outdoor (Virtual KITTI 2) |
|:-|-:|:-:|:-:|
| Depth-Anything-V2-Small | 24.8M | [Download](https://huggingface.co/depth-anything/Depth-Anything-V2-Metric-Hypersim-Small/resolve/main/depth_anything_v2_metric_hypersim_vits.pth?download=true) | [Download](https://huggingface.co/depth-anything/Depth-Anything-V2-Metric-VKITTI-Small/resolve/main/depth_anything_v2_metric_vkitti_vits.pth?download=true) |
| Depth-Anything-V2-Base | 97.5M | [Download](https://huggingface.co/depth-anything/Depth-Anything-V2-Metric-Hypersim-Base/resolve/main/depth_anything_v2_metric_hypersim_vitb.pth?download=true) | [Download](https://huggingface.co/depth-anything/Depth-Anything-V2-Metric-VKITTI-Base/resolve/main/depth_anything_v2_metric_vkitti_vitb.pth?download=true) |
| Depth-Anything-V2-Large | 335.3M | [Download](https://huggingface.co/depth-anything/Depth-Anything-V2-Metric-Hypersim-Large/resolve/main/depth_anything_v2_metric_hypersim_vitl.pth?download=true) | [Download](https://huggingface.co/depth-anything/Depth-Anything-V2-Metric-VKITTI-Large/resolve/main/depth_anything_v2_metric_vkitti_vitl.pth?download=true) |
*We recommend to first try our larger models (if computational cost is affordable) and the indoor version.*
## Usage
### Prepraration
```bash
git clone https://github.com/DepthAnything/Depth-Anything-V2
cd Depth-Anything-V2/metric_depth
pip install -r requirements.txt
```
Download the checkpoints listed [here](#pre-trained-models) and put them under the `checkpoints` directory.
### Use our models
```python
import cv2
import torch
from depth_anything_v2.dpt import DepthAnythingV2
model_configs = {
'vits': {'encoder': 'vits', 'features': 64, 'out_channels': [48, 96, 192, 384]},
'vitb': {'encoder': 'vitb', 'features': 128, 'out_channels': [96, 192, 384, 768]},
'vitl': {'encoder': 'vitl', 'features': 256, 'out_channels': [256, 512, 1024, 1024]}
}
encoder = 'vitl' # or 'vits', 'vitb'
dataset = 'hypersim' # 'hypersim' for indoor model, 'vkitti' for outdoor model
max_depth = 20 # 20 for indoor model, 80 for outdoor model
model = DepthAnythingV2(**{**model_configs[encoder], 'max_depth': max_depth})
model.load_state_dict(torch.load(f'checkpoints/depth_anything_v2_metric_{dataset}_{encoder}.pth', map_location='cpu'))
model.eval()
raw_img = cv2.imread('your/image/path')
depth = model.infer_image(raw_img) # HxW depth map in meters in numpy
```
### Running script on images
Here, we take the `vitl` encoder as an example. You can also use `vitb` or `vits` encoders.
```bash
# indoor scenes
python run.py \
--encoder vitl \
--load-from checkpoints/depth_anything_v2_metric_hypersim_vitl.pth \
--max-depth 20 \
--img-path <path> --outdir <outdir> [--input-size <size>] [--save-numpy]
# outdoor scenes
python run.py \
--encoder vitl \
--load-from checkpoints/depth_anything_v2_metric_vkitti_vitl.pth \
--max-depth 80 \
--img-path <path> --outdir <outdir> [--input-size <size>] [--save-numpy]
```
### Project 2D images to point clouds:
```bash
python depth_to_pointcloud.py \
--encoder vitl \
--load-from checkpoints/depth_anything_v2_metric_hypersim_vitl.pth \
--max-depth 20 \
--img-path <path> --outdir <outdir>
```
### Reproduce training
Please first prepare the [Hypersim](https://github.com/apple/ml-hypersim) and [Virtual KITTI 2](https://europe.naverlabs.com/research/computer-vision/proxy-virtual-worlds-vkitti-2/) datasets. Then:
```bash
bash dist_train.sh
```
## Citation
If you find this project useful, please consider citing:
```bibtex
@article{depth_anything_v2,
title={Depth Anything V2},
author={Yang, Lihe and Kang, Bingyi and Huang, Zilong and Zhao, Zhen and Xu, Xiaogang and Feng, Jiashi and Zhao, Hengshuang},
journal={arXiv:2406.09414},
year={2024}
}
@inproceedings{depth_anything_v1,
title={Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data},
author={Yang, Lihe and Kang, Bingyi and Huang, Zilong and Xu, Xiaogang and Feng, Jiashi and Zhao, Hengshuang},
booktitle={CVPR},
year={2024}
}
```
|
llmware/slim-summary-tiny | llmware | 2024-06-21T16:34:44Z | 14 | 1 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-06-12T07:04:16Z | ---
license: apache-2.0
inference: false
---
# SLIM-SUMMARY-TINY
<!-- Provide a quick summary of what the model is/does. -->
**slim-summary-tiny** is a small, specialized model finetuned for summarize function-calls, generating output consisting of a python list of distinct summary points.
As an experimental feature in the model, there is an optional list size that can be passed with the parameters in invoking the model to guide the model to a specific number of response elements.
Input is a text passage, and output is a list of the form:
`['summary_point1', 'summary_point2', 'summary_point3']`
This model is 1.1B parameters, small enough to run on a CPU, and is fine-tuned on top of a tiny-llama base.
For fast inference use of this model, we would recommend using the 'quantized tool' version, e.g., [**'slim-summary-tiny-tool'**](https://huggingface.co/llmware/slim-summary-tiny-tool).
## Usage Tips
-- Automatic (ast.literal_eval) conversion of the llm output to a python list is often complicated by the presence of '"' (ascii 34 double quotes) and "'" (ascii 39 single quote). We have provided a straightforward string remediation handler in [llmware](https://www.github.com/llmware-ai/llmware.git) that automatically remediates and provides a well-formed Python list. We have tried multiple ways to handle 34/39 in training - and each has a set of trade-offs - we will continue to look for ways to better automate in future releases of the model.
-- If you are looking for a single output point, try the params: "brief description (1)"
-- If the document has a lot of financial points, try the params "financial data points" or "financial data points (5)"
-- Param counts are an experimental feature, but work reasonably well to guide the scope of the model's output length. At times, the model's attempt to match the target number of output points will result in some repetitive points.
## Prompt format:
`function = "summarize"`
`params = "key points (3)"`
`prompt = "<human> " + {text} + "\n" + `
`"<{function}> " + {params} + "</{function}>" + "\n<bot>:"`
<details>
<summary>Transformers Script </summary>
model = AutoModelForCausalLM.from_pretrained("llmware/slim-summary-tiny")
tokenizer = AutoTokenizer.from_pretrained("llmware/slim-summary-tiny")
function = "summarize"
params = "key points (3)"
text = "Tesla stock declined yesterday 8% in premarket trading after a poorly-received event in San Francisco yesterday, in which the company indicated a likely shortfall in revenue."
prompt = "<human>: " + text + "\n" + f"<{function}> {params} </{function}>\n<bot>:"
inputs = tokenizer(prompt, return_tensors="pt")
start_of_input = len(inputs.input_ids[0])
outputs = model.generate(
inputs.input_ids.to('cpu'),
eos_token_id=tokenizer.eos_token_id,
pad_token_id=tokenizer.eos_token_id,
do_sample=True,
temperature=0.3,
max_new_tokens=100
)
output_only = tokenizer.decode(outputs[0][start_of_input:], skip_special_tokens=True)
print("output only: ", output_only)
# here's the fun part
try:
output_only = ast.literal_eval(llm_string_output)
print("success - converted to python dictionary automatically")
except:
# note: rules-based conversion may be required - see comment above - and remediation script @ https://www.github.com/llmware-ai/llmware/blobs/main/llmware/models.py - ModelCatalog.remediate_function_call_string()
# for good example of post-processing conversion script
print("fail - could not convert to python dictionary automatically - ", llm_string_output)
</details>
<details>
<summary>Using as Function Call in LLMWare</summary>
from llmware.models import ModelCatalog
slim_model = ModelCatalog().load_model("llmware/slim-summary-tiny")
response = slim_model.function_call(text,params=["key points (3)], function="summarize")
print("llmware - llm_response: ", response)
</details>
## Model Card Contact
Darren Oberst & llmware team
[Join us on Discord](https://discord.gg/MhZn5Nc39h) |
llmware/slim-summary-tiny-tool | llmware | 2024-06-21T16:29:27Z | 31 | 2 | transformers | [
"transformers",
"gguf",
"llama",
"license:apache-2.0",
"region:us"
] | null | 2024-06-12T07:01:29Z | ---
license: apache-2.0
inference: false
---
# SLIM-SUMMARY-TINY-TOOL
<!-- Provide a quick summary of what the model is/does. -->
**slim-summary-tiny-tool** is a 4_K_M quantized GGUF version of slim-summary-tiny, providing a small, fast inference implementation, to provide high-quality summarizations of complex business documents, on a small, specialized locally-deployable model with summary output structured as a python list of key points.
The size of the self-contained GGUF model binary is ~700 MB, which is small enough to run locally on a CPU with reasonable inference speed, and has been designed to balance solid quality with fast loading and inference on a local machine.
The model takes as input a text passage, an optional parameter with a focusing phrase or query, and an experimental optional (N) parameter, which is used to guide the model to a specific number of items return in a summary list.
Please see the usage notes at: [**slim-summary-tiny**](https://huggingface.co/llmware/slim-summary-tiny)
To pull the model via API:
from huggingface_hub import snapshot_download
snapshot_download("llmware/slim-summary-tiny-tool", local_dir="/path/on/your/machine/", local_dir_use_symlinks=False)
Load in your favorite GGUF inference engine, or try with llmware as follows:
from llmware.models import ModelCatalog
# to load the model and make a basic inference
model = ModelCatalog().load_model("slim-summary-tiny-tool")
response = model.function_call(text_sample)
# this one line will download the model and run a series of tests
ModelCatalog().tool_test_run("slim-summary-tiny-tool", verbose=True)
Note: please review [**config.json**](https://huggingface.co/llmware/slim-summary-tiny-tool/blob/main/config.json) in the repository for prompt wrapping information, details on the model, and full test set.
## Model Card Contact
Darren Oberst & llmware team
[Any questions? Join us on Discord](https://discord.gg/MhZn5Nc39h) |
gruhit-patel/ppo-SnowballTarget | gruhit-patel | 2024-06-21T16:29:21Z | 6 | 0 | ml-agents | [
"ml-agents",
"tensorboard",
"onnx",
"SnowballTarget",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SnowballTarget",
"region:us"
] | reinforcement-learning | 2024-06-21T16:28:47Z | ---
library_name: ml-agents
tags:
- SnowballTarget
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-SnowballTarget
---
# **ppo** Agent playing **SnowballTarget**
This is a trained model of a **ppo** agent playing **SnowballTarget**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: gruhit-patel/ppo-SnowballTarget
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
ymoslem/whisper-medium-ga2en-a-v1-r | ymoslem | 2024-06-21T16:28:57Z | 20 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"ga",
"en",
"dataset:ymoslem/IWSLT2023-GA-EN",
"dataset:ymoslem/FLEURS-GA-EN",
"dataset:ymoslem/BitesizeIrish-GA-EN",
"dataset:ymoslem/SpokenWords-GA-EN-MTed",
"base_model:openai/whisper-medium",
"base_model:finetune:openai/whisper-medium",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] | automatic-speech-recognition | 2024-06-21T02:35:31Z | ---
language:
- ga
- en
license: apache-2.0
base_model: openai/whisper-medium
tags:
- generated_from_trainer
datasets:
- ymoslem/IWSLT2023-GA-EN
- ymoslem/FLEURS-GA-EN
- ymoslem/BitesizeIrish-GA-EN
- ymoslem/SpokenWords-GA-EN-MTed
metrics:
- bleu
- wer
model-index:
- name: Whisper Medium GA-EN Speech Translation Raw
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: IWSLT-2023, FLEURS, BiteSize, and SpokenWords
type: ymoslem/IWSLT2023-GA-EN
metrics:
- name: Bleu
type: bleu
value: 27.65
- name: Wer
type: wer
value: 71.09410175596578
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Whisper Medium GA-EN Speech Translation Raw
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the IWSLT-2023, FLEURS, BiteSize, and SpokenWords dataset.
It achieves the following results on the evaluation set:
- Loss: 1.6246
- Bleu: 27.65
- Chrf: 47.08
- Wer: 71.0941
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 4000
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Chrf | Wer |
|:-------------:|:------:|:----:|:---------------:|:-----:|:-----:|:--------:|
| 2.3743 | 0.0539 | 100 | 2.1064 | 5.67 | 20.91 | 126.9248 |
| 2.3196 | 0.1079 | 200 | 2.1133 | 11.35 | 26.01 | 89.5092 |
| 2.2729 | 0.1618 | 300 | 2.0561 | 6.85 | 25.04 | 156.5061 |
| 2.0887 | 0.2157 | 400 | 1.9701 | 10.46 | 29.21 | 118.6853 |
| 1.9663 | 0.2697 | 500 | 1.9824 | 16.53 | 31.2 | 77.5326 |
| 1.9504 | 0.3236 | 600 | 1.8619 | 7.02 | 27.46 | 193.7416 |
| 1.7843 | 0.3776 | 700 | 1.8683 | 16.6 | 33.6 | 87.7082 |
| 1.8915 | 0.4315 | 800 | 1.7730 | 16.89 | 36.54 | 91.8505 |
| 1.6921 | 0.4854 | 900 | 1.8049 | 13.14 | 34.45 | 114.0477 |
| 1.4761 | 0.5394 | 1000 | 1.8310 | 22.12 | 37.3 | 77.1724 |
| 1.3067 | 0.5933 | 1100 | 1.7911 | 17.21 | 34.34 | 90.5448 |
| 1.3564 | 0.6472 | 1200 | 1.7045 | 20.09 | 39.67 | 85.1869 |
| 1.489 | 0.7012 | 1300 | 1.7601 | 15.3 | 36.53 | 107.8793 |
| 1.3023 | 0.7551 | 1400 | 1.7428 | 18.99 | 39.54 | 89.7794 |
| 1.1744 | 0.8091 | 1500 | 1.7446 | 21.68 | 41.78 | 79.4687 |
| 1.0122 | 0.8630 | 1600 | 1.7180 | 18.28 | 39.27 | 96.7582 |
| 1.0787 | 0.9169 | 1700 | 1.6144 | 16.94 | 39.74 | 98.8744 |
| 0.9561 | 0.9709 | 1800 | 1.6290 | 25.29 | 42.13 | 74.9662 |
| 0.4452 | 1.0248 | 1900 | 1.7223 | 18.95 | 39.14 | 97.0734 |
| 0.4397 | 1.0787 | 2000 | 1.6855 | 23.4 | 40.9 | 77.9379 |
| 0.4382 | 1.1327 | 2100 | 1.6911 | 24.95 | 41.19 | 72.8951 |
| 0.3937 | 1.1866 | 2200 | 1.7127 | 23.33 | 41.09 | 78.4331 |
| 0.4119 | 1.2406 | 2300 | 1.6796 | 23.25 | 42.32 | 83.6560 |
| 0.4139 | 1.2945 | 2400 | 1.6730 | 23.13 | 43.25 | 83.3408 |
| 0.3506 | 1.3484 | 2500 | 1.7361 | 23.37 | 42.31 | 79.9190 |
| 0.4109 | 1.4024 | 2600 | 1.6233 | 23.78 | 44.32 | 82.8005 |
| 0.3563 | 1.4563 | 2700 | 1.6383 | 20.41 | 43.66 | 98.1540 |
| 0.3355 | 1.5102 | 2800 | 1.6675 | 25.27 | 44.91 | 75.6866 |
| 0.2751 | 1.5642 | 2900 | 1.7011 | 24.64 | 43.19 | 74.2008 |
| 0.28 | 1.6181 | 3000 | 1.6308 | 24.76 | 45.49 | 79.4687 |
| 0.3108 | 1.6721 | 3100 | 1.5976 | 28.9 | 47.03 | 68.7978 |
| 0.3231 | 1.7260 | 3200 | 1.6070 | 27.82 | 46.1 | 69.8334 |
| 0.2665 | 1.7799 | 3300 | 1.5853 | 26.0 | 44.51 | 74.9212 |
| 0.2788 | 1.8339 | 3400 | 1.5689 | 26.37 | 46.94 | 75.0113 |
| 0.243 | 1.8878 | 3500 | 1.5885 | 29.12 | 46.94 | 67.4021 |
| 0.2605 | 1.9417 | 3600 | 1.5680 | 28.64 | 46.38 | 67.8523 |
| 0.1664 | 1.9957 | 3700 | 1.5910 | 28.45 | 46.64 | 68.0774 |
| 0.049 | 2.0496 | 3800 | 1.6385 | 27.78 | 46.51 | 69.9235 |
| 0.0635 | 2.1036 | 3900 | 1.6272 | 27.57 | 47.25 | 71.1391 |
| 0.0467 | 2.1575 | 4000 | 1.6246 | 27.65 | 47.08 | 71.0941 |
### Framework versions
- Transformers 4.41.2
- Pytorch 2.2.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
|
llmware/slim-extract-tiny | llmware | 2024-06-21T16:19:04Z | 15 | 1 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-06-12T07:12:10Z | ---
license: apache-2.0
inference: false
---
# SLIM-EXTRACT-TINY
<!-- Provide a quick summary of what the model is/does. -->
**slim-extract-tiny** implements a specialized function-calling customizable 'extract' capability that takes as an input a context passage, a customized key, and outputs a python dictionary with key that corresponds to the customized key, with a value consisting of a list of items extracted from the text corresponding to that key, e.g.,
`{'universities': ['Berkeley, Stanford, Yale, University of Florida, ...'] }`
This model is fine-tuned on top of a tiny-llama 1b base.
For fast inference use, we would recommend the 'quantized tool' version, e.g., [**'slim-extract-tiny-tool'**](https://huggingface.co/llmware/slim-extract-tiny-tool).
## Prompt format:
`function = "extract"`
`params = "{custom key}"`
`prompt = "<human> " + {text} + "\n" + `
`"<{function}> " + {params} + "</{function}>" + "\n<bot>:"`
<details>
<summary>Transformers Script </summary>
model = AutoModelForCausalLM.from_pretrained("llmware/slim-extract-tiny")
tokenizer = AutoTokenizer.from_pretrained("llmware/slim-extract-tiny")
function = "extract"
params = "company"
text = "Tesla stock declined yesterday 8% in premarket trading after a poorly-received event in San Francisco yesterday, in which the company indicated a likely shortfall in revenue."
prompt = "<human>: " + text + "\n" + f"<{function}> {params} </{function}>\n<bot>:"
inputs = tokenizer(prompt, return_tensors="pt")
start_of_input = len(inputs.input_ids[0])
outputs = model.generate(
inputs.input_ids.to('cpu'),
eos_token_id=tokenizer.eos_token_id,
pad_token_id=tokenizer.eos_token_id,
do_sample=True,
temperature=0.3,
max_new_tokens=100
)
output_only = tokenizer.decode(outputs[0][start_of_input:], skip_special_tokens=True)
print("output only: ", output_only)
# here's the fun part
try:
output_only = ast.literal_eval(llm_string_output)
print("success - converted to python dictionary automatically")
except:
print("fail - could not convert to python dictionary automatically - ", llm_string_output)
</details>
<details>
<summary>Using as Function Call in LLMWare</summary>
from llmware.models import ModelCatalog
slim_model = ModelCatalog().load_model("llmware/slim-extract-tiny")
response = slim_model.function_call(text,params=["company"], function="extract")
print("llmware - llm_response: ", response)
</details>
## Model Card Contact
Darren Oberst & llmware team
[Join us on Discord](https://discord.gg/MhZn5Nc39h) |
ByteForge/Llama_3_8b_Instruct_Text2Sql_Finetuned | ByteForge | 2024-06-21T16:15:00Z | 11 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"8-bit",
"bitsandbytes",
"region:us"
] | text-generation | 2024-06-21T16:09:17Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
AdamKasumovic/phi3-mini-4k-instruct-bactrian-x-en-100-percent-med-nv-embed-winogrande_train_s | AdamKasumovic | 2024-06-21T16:08:26Z | 5 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"conversational",
"en",
"base_model:unsloth/Phi-3-mini-4k-instruct-bnb-4bit",
"base_model:finetune:unsloth/Phi-3-mini-4k-instruct-bnb-4bit",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-06-21T16:05:53Z | ---
base_model: unsloth/Phi-3-mini-4k-instruct-bnb-4bit
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- trl
---
# Uploaded model
- **Developed by:** AdamKasumovic
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Phi-3-mini-4k-instruct-bnb-4bit
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
CHARKA/Mistral-7B-Instruct-CHARKAPEDAG | CHARKA | 2024-06-21T15:54:27Z | 7 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"trl",
"sft",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
] | text-generation | 2024-06-21T15:45:46Z | ---
library_name: transformers
tags:
- trl
- sft
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
BAAI/Bunny-v1_0-4B-gguf | BAAI | 2024-06-21T15:52:54Z | 97 | 7 | null | [
"gguf",
"arxiv:2402.11530",
"license:apache-2.0",
"region:us",
"conversational"
] | null | 2024-05-09T12:42:06Z | ---
inference: false
license: apache-2.0
---
# Model Card
<p align="center">
<img src="./icon.png" alt="Logo" width="350">
</p>
📖 [Technical report](https://arxiv.org/abs/2402.11530) | 🏠 [Code](https://github.com/BAAI-DCAI/Bunny) | 🐰 [Demo](http://bunny.baai.ac.cn)
This is **GGUF** format of [Bunny-v1.0-4B](https://huggingface.co/BAAI/Bunny-v1_0-4B).
Bunny is a family of lightweight but powerful multimodal models. It offers multiple plug-and-play vision encoders, like EVA-CLIP, SigLIP and language backbones, including Phi-3-mini, Llama-3-8B, Phi-1.5, StableLM-2, Qwen1.5, MiniCPM and Phi-2. To compensate for the decrease in model size, we construct more informative training data by curated selection from a broader data source.
We provide Bunny-v1.0-4B, which is built upon [SigLIP](https://huggingface.co/google/siglip-so400m-patch14-384) and [Phi-3-Mini-4K-Instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct). More details about this model can be found in [GitHub](https://github.com/BAAI-DCAI/Bunny).
# Quickstart
## Chat by [`llama.cpp`](https://github.com/ggerganov/llama.cpp)
```shell
# sample images can be found in images folder
# fp16
./llava-cli -m ggml-model-f16.gguf --mmproj mmproj-model-f16.gguf --image example_2.png -c 4096 -e \
-p "A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: <image>\nWhy is the image funny? ASSISTANT:" \
--temp 0.0
# int4
./llava-cli -m ggml-model-Q4_K_M.gguf --mmproj mmproj-model-f16.gguf --image example_2.png -c 4096 -e \
-p "A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: <image>\nWhy is the image funny? ASSISTANT:" \
--temp 0.0
```
## Chat by [ollama](https://ollama.com/)
```shell
# sample images can be found in images folder
# fp16
ollama create Bunny-Llama-3-8B-V-fp16 -f ./ollama-f16
ollama run Bunny-Llama-3-8B-V-fp16 'example_2.png
Why is the image funny?'
# int4
ollama create Bunny-Llama-3-8B-V-int4 -f ./ollama-Q4_K_M
ollama run Bunny-Llama-3-8B-V-int4 'example_2.png
Why is the image funny?'
```
|
AdamKasumovic/phi3-mini-4k-instruct-bactrian-x-en-100-percent-med-nv-embed-mmlu_cm | AdamKasumovic | 2024-06-21T15:49:39Z | 7 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"conversational",
"en",
"base_model:unsloth/Phi-3-mini-4k-instruct-bnb-4bit",
"base_model:finetune:unsloth/Phi-3-mini-4k-instruct-bnb-4bit",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-06-21T15:46:04Z | ---
base_model: unsloth/Phi-3-mini-4k-instruct-bnb-4bit
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- trl
---
# Uploaded model
- **Developed by:** AdamKasumovic
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Phi-3-mini-4k-instruct-bnb-4bit
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
LongshenOu/m2m_pt | LongshenOu | 2024-06-21T15:48:50Z | 72 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"gpt2",
"text-generation",
"generated_from_trainer",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-06-20T05:24:07Z | ---
tags:
- generated_from_trainer
model-index:
- name: m2m_pt
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# m2m_pt
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4682
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 12
- eval_batch_size: 12
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 96
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 0.7388 | 0.09 | 2000 | 0.6464 |
| 0.6096 | 0.18 | 4000 | 0.5477 |
| 0.612 | 0.27 | 6000 | 0.5144 |
| 0.53 | 0.36 | 8000 | 0.4965 |
| 0.5744 | 0.45 | 10000 | 0.4856 |
| 0.5435 | 0.54 | 12000 | 0.4776 |
| 0.5428 | 0.63 | 14000 | 0.4726 |
| 0.5065 | 0.72 | 16000 | 0.4696 |
| 0.5287 | 0.81 | 18000 | 0.4685 |
| 0.5032 | 0.9 | 20000 | 0.4682 |
| 0.5451 | 0.99 | 22000 | 0.4682 |
### Framework versions
- Transformers 4.40.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.20.0
- Tokenizers 0.15.2
|
AdamKasumovic/phi3-mini-4k-instruct-bactrian-x-en-100-percent-high-nv-embed-mmlu_ck | AdamKasumovic | 2024-06-21T15:47:38Z | 5 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"conversational",
"en",
"base_model:unsloth/Phi-3-mini-4k-instruct-bnb-4bit",
"base_model:finetune:unsloth/Phi-3-mini-4k-instruct-bnb-4bit",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-06-21T15:42:50Z | ---
base_model: unsloth/Phi-3-mini-4k-instruct-bnb-4bit
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- trl
---
# Uploaded model
- **Developed by:** AdamKasumovic
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Phi-3-mini-4k-instruct-bnb-4bit
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
AdamKasumovic/phi3-mini-4k-instruct-bactrian-x-en-100-percent-high-nv-embed-mmlu_cm | AdamKasumovic | 2024-06-21T15:46:49Z | 8 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"conversational",
"en",
"base_model:unsloth/Phi-3-mini-4k-instruct-bnb-4bit",
"base_model:finetune:unsloth/Phi-3-mini-4k-instruct-bnb-4bit",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-06-21T15:42:42Z | ---
base_model: unsloth/Phi-3-mini-4k-instruct-bnb-4bit
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- trl
---
# Uploaded model
- **Developed by:** AdamKasumovic
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Phi-3-mini-4k-instruct-bnb-4bit
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
alwaysaditi/pegasus_hiporank_final | alwaysaditi | 2024-06-21T15:35:36Z | 6 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"pegasus_x",
"text2text-generation",
"generated_from_trainer",
"base_model:google/pegasus-x-base",
"base_model:finetune:google/pegasus-x-base",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text2text-generation | 2024-06-21T15:07:12Z | ---
base_model: google/pegasus-x-base
tags:
- generated_from_trainer
model-index:
- name: google/pegasus-x-base
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# google/pegasus-x-base
This model is a fine-tuned version of [google/pegasus-x-base](https://huggingface.co/google/pegasus-x-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0135
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 8.9092 | 0.1008 | 10 | 8.5348 |
| 7.9162 | 0.2015 | 20 | 7.5592 |
| 7.3907 | 0.3023 | 30 | 6.9080 |
| 6.8587 | 0.4030 | 40 | 6.1464 |
| 5.7817 | 0.5038 | 50 | 5.2883 |
| 5.0792 | 0.6045 | 60 | 3.9477 |
| 4.1259 | 0.7053 | 70 | 2.7538 |
| 3.0821 | 0.8060 | 80 | 1.7983 |
| 2.2714 | 0.9068 | 90 | 1.4814 |
| 1.7994 | 1.0076 | 100 | 1.4092 |
| 1.4936 | 1.1083 | 110 | 1.3189 |
| 1.6535 | 1.2091 | 120 | 1.2445 |
| 1.3122 | 1.3098 | 130 | 1.2139 |
| 1.0667 | 1.4106 | 140 | 1.1800 |
| 1.274 | 1.5113 | 150 | 1.1507 |
| 1.1739 | 1.6121 | 160 | 1.1279 |
| 1.1871 | 1.7128 | 170 | 1.1094 |
| 1.2037 | 1.8136 | 180 | 1.0973 |
| 1.0839 | 1.9144 | 190 | 1.0832 |
| 1.0738 | 2.0151 | 200 | 1.0752 |
| 1.0955 | 2.1159 | 210 | 1.0695 |
| 1.1285 | 2.2166 | 220 | 1.0629 |
| 0.9973 | 2.3174 | 230 | 1.0574 |
| 1.0522 | 2.4181 | 240 | 1.0557 |
| 1.0803 | 2.5189 | 250 | 1.0458 |
| 1.0707 | 2.6196 | 260 | 1.0425 |
| 1.1868 | 2.7204 | 270 | 1.0384 |
| 1.0117 | 2.8212 | 280 | 1.0374 |
| 0.9206 | 2.9219 | 290 | 1.0347 |
| 1.0099 | 3.0227 | 300 | 1.0306 |
| 1.0459 | 3.1234 | 310 | 1.0307 |
| 1.0721 | 3.2242 | 320 | 1.0313 |
| 1.015 | 3.3249 | 330 | 1.0278 |
| 1.0358 | 3.4257 | 340 | 1.0237 |
| 0.9608 | 3.5264 | 350 | 1.0206 |
| 1.0416 | 3.6272 | 360 | 1.0202 |
| 0.9304 | 3.7280 | 370 | 1.0201 |
| 1.0447 | 3.8287 | 380 | 1.0187 |
| 1.0007 | 3.9295 | 390 | 1.0180 |
| 1.1681 | 4.0302 | 400 | 1.0168 |
| 1.0258 | 4.1310 | 410 | 1.0163 |
| 1.1054 | 4.2317 | 420 | 1.0153 |
| 0.907 | 4.3325 | 430 | 1.0154 |
| 0.935 | 4.4332 | 440 | 1.0151 |
| 0.9904 | 4.5340 | 450 | 1.0145 |
| 0.9735 | 4.6348 | 460 | 1.0142 |
| 0.9633 | 4.7355 | 470 | 1.0138 |
| 1.2809 | 4.8363 | 480 | 1.0136 |
| 1.0361 | 4.9370 | 490 | 1.0135 |
### Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
|
alakxender/mt5-large-dv-en | alakxender | 2024-06-21T15:33:34Z | 22 | 0 | transformers | [
"transformers",
"safetensors",
"mt5",
"text2text-generation",
"translation",
"dv",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | translation | 2024-06-21T11:52:45Z | ---
library_name: transformers
language:
- dv
pipeline_tag: translation
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
balakrish181/ddpm-class-mnist-28 | balakrish181 | 2024-06-21T15:33:27Z | 15 | 0 | diffusers | [
"diffusers",
"safetensors",
"pytorch",
"unconditional-image-generation",
"diffusion-models-class",
"license:mit",
"diffusers:DDPMPipeline",
"region:us"
] | unconditional-image-generation | 2024-06-21T15:30:47Z | ---
license: mit
tags:
- pytorch
- diffusers
- unconditional-image-generation
- diffusion-models-class
---
# Model Card for Unit 1 of the [Diffusion Models Class 🧨](https://github.com/huggingface/diffusion-models-class)
This model is a diffusion model for unconditional image generation of MNIST.
## Usage
```python
from diffusers import DDPMPipeline
pipeline = DDPMPipeline.from_pretrained('balakrish181/ddpm-class-mnist-28')
image = pipeline().images[0]
image
|
John6666/maple-mix-pony-v1-sdxl-spo-lora | John6666 | 2024-06-21T15:27:31Z | 271 | 1 | diffusers | [
"diffusers",
"text-to-image",
"stable-diffusion",
"stable-diffusion-xl",
"lora",
"realistic",
"photorealistic",
"pony",
"SPO",
"base_model:John6666/maple-mix-pony-v1-sdxl",
"base_model:adapter:John6666/maple-mix-pony-v1-sdxl",
"region:us"
] | text-to-image | 2024-06-21T15:27:00Z | ---
tags:
- text-to-image
- stable-diffusion
- stable-diffusion-xl
- lora
- diffusers
- realistic
- photorealistic
- pony
- SPO
base_model: John6666/maple-mix-pony-v1-sdxl
---
This repository is for testing [SPO-SDXL LoRA](https://huggingface.co/SPO-Diffusion-Models/SPO-SDXL_4k-p_10ep_LoRA). Simply applying it with a "weight=1.0 (default)" will help produce a high-definition image.
It seems to be slightly prone to disorder in Pony-type models, but this can be mostly avoided by setting "clip skip=2" in your environment.
|
Subsets and Splits