modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-06-27 18:27:39
| 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
2025-06-27 18:23:41
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
TheBloke/orca_mini_3B-GGML | TheBloke | 2023-06-25T10:25:04Z | 0 | 59 | transformers | [
"transformers",
"en",
"dataset:psmathur/alpaca_orca",
"dataset:psmathur/dolly-v2_orca",
"dataset:psmathur/WizardLM_Orca",
"arxiv:2306.02707",
"license:mit",
"region:us"
] | null | 2023-06-24T22:33:56Z | ---
inference: false
license: mit
language:
- en
library_name: transformers
datasets:
- psmathur/alpaca_orca
- psmathur/dolly-v2_orca
- psmathur/WizardLM_Orca
---
<!-- header start -->
<div style="width: 100%;">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<!-- header end -->
# Pankaj Mathur's Orca Mini 3B GGML
These files are GGML format model files for [Pankaj Mathur's Orca Mini 3B](https://huggingface.co/psmathur/orca_mini_3b).
GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/ggerganov/llama.cpp) and libraries and UIs which support this format, such as:
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
* [KoboldCpp](https://github.com/LostRuins/koboldcpp)
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui)
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python)
* [ctransformers](https://github.com/marella/ctransformers)
## Repositories available
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/orca_mini_3B-GGML)
* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/psmathur/orca_mini_3b)
## Prompt template:
```
### System:
You are an AI assistant that follows instruction extremely well. Help as much as you can.
### User:
prompt
### Response:
```
or
```
### System:
You are an AI assistant that follows instruction extremely well. Help as much as you can.
### User:
prompt
### Input:
input
### Response:
```
<!-- compatibility_ggml start -->
## Compatibility
### Original llama.cpp quant methods: `q4_0, q4_1, q5_0, q5_1, q8_0`
I have quantized these 'original' quantisation methods using an older version of llama.cpp so that they remain compatible with llama.cpp as of May 19th, commit `2d5db48`.
These are guaranteed to be compatbile with any UIs, tools and libraries released since late May.
### New k-quant methods: `q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K`
These cannot be provided with Open Llama 3B models at this time, due to an issue in llama.cpp.
This is being worked on in the llama.cpp repo. More issues here: https://github.com/ggerganov/llama.cpp/issues/1919
Refer to the Provided Files table below to see what files use which methods, and how.
<!-- compatibility_ggml end -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| orca-mini-3b.ggmlv3.q4_0.bin | q4_0 | 4 | 1.93 GB | 4.43 GB | Original llama.cpp quant method, 4-bit. |
| orca-mini-3b.ggmlv3.q4_1.bin | q4_1 | 4 | 2.14 GB | 4.64 GB | Original llama.cpp quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
| orca-mini-3b.ggmlv3.q5_0.bin | q5_0 | 5 | 2.36 GB | 4.86 GB | Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. |
| orca-mini-3b.ggmlv3.q5_1.bin | q5_1 | 5 | 2.57 GB | 5.07 GB | Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference. |
| orca-mini-3b.ggmlv3.q8_0.bin | q8_0 | 8 | 3.64 GB | 6.14 GB | Original llama.cpp quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
## How to run in `llama.cpp`
I use the following command line; adjust for your tastes and needs:
```
./main -t 10 -ngl 32 -m orca-mini-3b.ggmlv3.q5_0.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "### System:\nYou are an story writing assistant who writes very long, detailed and interesting stories\n\n### User:\nWrite a story about llamas\n\n### Input:\n{input}\n\n### Response:\n"
```
If you're able to use full GPU offloading, you should use `-t 1` to get best performance.
If not able to fully offload to GPU, you should use more cores. Change `-t 10` to the number of physical CPU cores you have, or a lower number depending on what gives best performance.
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
## How to run in `text-generation-webui`
Further instructions here: [text-generation-webui/docs/llama.cpp-models.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp-models.md).
<!-- footer start -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
**Patreon special mentions**: Pyrater, WelcomeToTheClub, Kalila, Mano Prime, Trenton Dambrowitz, Spiking Neurons AB, Pierre Kircher, Fen Risland, Kevin Schuppel, Luke, Rainer Wilmers, vamX, Gabriel Puliatti, Alex , Karl Bernard, Ajan Kanaga, Talal Aujan, Space Cruiser, ya boyyy, biorpg, Johann-Peter Hartmann, Asp the Wyvern, Ai Maven, Ghost , Preetika Verma, Nikolai Manek, trip7s trip, John Detwiler, Fred von Graf, Artur Olbinski, subjectnull, John Villwock, Junyu Yang, Rod A, Lone Striker, Chris McCloskey, Iucharbius , Matthew Berman, Illia Dulskyi, Khalefa Al-Ahmad, Imad Khwaja, chris gileta, Willem Michiel, Greatston Gnanesh, Derek Yates, K, Alps Aficionado, Oscar Rangel, David Flickinger, Luke Pendergrass, Deep Realms, Eugene Pentland, Cory Kujawski, terasurfer , Jonathan Leane, senxiiz, Joseph William Delisle, Sean Connelly, webtim, zynix , Nathan LeClaire.
Thank you to all my generous patrons and donaters!
<!-- footer end -->
# Original model card: Pankaj Mathur's Orca Mini 3B
# orca_mini_3b
An [OpenLLaMa-3B model](https://github.com/openlm-research/open_llama) model trained on explain tuned datasets, created using Instructions and Input from WizardLM, Alpaca & Dolly-V2 datasets and applying Orca Research Paper dataset construction approaches.
# Dataset
We build explain tuned [WizardLM dataset ~70K](https://github.com/nlpxucan/WizardLM), [Alpaca dataset ~52K](https://crfm.stanford.edu/2023/03/13/alpaca.html) & [Dolly-V2 dataset ~15K](https://github.com/databrickslabs/dolly) created using approaches from [Orca Research Paper](https://arxiv.org/abs/2306.02707).
We leverage all of the 15 system instructions provided in Orca Research Paper. to generate custom datasets, in contrast to vanilla instruction tuning approaches used by original datasets.
This helps student model aka this model to learn ***thought*** process from teacher model, which is ChatGPT (gpt-3.5-turbo-0301 version).
Please see below example usage how the **System** prompt is added before each **instruction**.
# Training
The training configurations are provided in the table below.
The training takes on 8x A100(80G) GPUs and lasts for around 4 Hours for cost of $48 using [Lambda Labs](https://lambdalabs.com)
We used DeepSpeed with fully sharded data parallelism, also know as [ZeRO stage 3](https://engineering.fb.com/2021/07/15/open-source/fsdp/) by writing our own fine tunning scripts plus leveraging some of the model training code provided by amazing [OpenAlpaca repo](https://github.com/yxuansu/OpenAlpaca)
Here are some of params used during training:
|||
|:-------------:|:-------------:|
|*batch_size*|64|
|*train_micro_batch_size_per_gpu*|4|
|*gradient_accumulation_steps*|2|
|*Learning rate*|2e-5|
|*Max length*|1024|
|*Epochs*|3|
|*Optimizer*|AdamW|
# Example Usage
Below shows an example on how to use this model
```python
import torch
from transformers import LlamaForCausalLM, LlamaTokenizer
# Hugging Face model_path
model_path = 'psmathur/orca_mini_3b'
tokenizer = LlamaTokenizer.from_pretrained(model_path)
model = LlamaForCausalLM.from_pretrained(
model_path, torch_dtype=torch.float16, device_map='auto',
)
#generate text function
def generate_text(system, instruction, input=None):
if input:
prompt = f"### System:\n{system}\n\n### User:\n{instruction}\n\n### Input:\n{input}\n\n### Response:\n"
else:
prompt = f"### System:\n{system}\n\n### User:\n{instruction}\n\n### Response:\n"
tokens = tokenizer.encode(prompt)
tokens = torch.LongTensor(tokens).unsqueeze(0)
tokens = tokens.to('cuda')
instance = {'input_ids': tokens,'top_p': 1.0, 'temperature':0.7, 'generate_len': 1024, 'top_k': 50}
length = len(tokens[0])
with torch.no_grad():
rest = model.generate(
input_ids=tokens,
max_length=length+instance['generate_len'],
use_cache=True,
do_sample=True,
top_p=instance['top_p'],
temperature=instance['temperature'],
top_k=instance['top_k']
)
output = rest[0][length:]
string = tokenizer.decode(output, skip_special_tokens=True)
return f'[!] Response: {string}'
# Sample Test Instruction Used by Youtuber Sam Witteveen https://www.youtube.com/@samwitteveenai
system = 'You are an AI assistant that follows instruction extremely well. Help as much as you can.'
instruction = 'Write a letter to Sam Altman, CEO of OpenAI, requesting him to convert GPT4 a private model by OpenAI to an open source project'
print(generate_text(system, instruction))
```
```
[!] Response:
Dear Sam Altman,
I am writing to request that you convert the GPT4 private model developed by OpenAI to an open source project. As a user of OpenAI, I have been waiting for the day when I can use the advanced natural language processing capabilities of GPT4 in a more open and accessible way.
While OpenAI has made significant progress in developing AI applications, it has primarily focused on building private models that are not accessible to the general public. However, with the recent release of GPT-3, there is a growing demand for more open and accessible AI tools.
Converting GPT4 to an open source project would allow for greater transparency, collaboration, and innovation. It would also help to build trust in the technology and ensure that it is used ethically and responsibly.
I urge you to consider converting GPT4 to an open source project. This would be a significant contribution to the AI community and would help to create a more open and accessible future.
Thank you for your consideration.
Sincerely,
[Your Name]
```
**P.S. I am #opentowork and #collaboration, if you can help, please reach out to me at [email protected]**
Next Goals:
1) Try more data like actually using FLAN-v2, just like Orka Research Paper (I am open for suggestions)
2) Provide more options for Text generation UI. (may be https://github.com/oobabooga/text-generation-webui)
3) Provide 4bit GGML/GPTQ quantized model (may be [TheBloke](https://huggingface.co/TheBloke) can help here)
Limitations & Biases:
This model can produce factually incorrect output, and should not be relied on to produce factually accurate information.
This model was trained on various public datasets. While great efforts have been taken to clean the pretraining data, it is possible that this model could generate lewd, biased or otherwise offensive outputs.
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.
Citiation:
If you found wizardlm_alpaca_dolly_orca_open_llama_3b useful in your research or applications, please kindly cite using the following BibTeX:
```
@misc{wizardlm_alpaca_dolly_orca_open_llama_3b,
author = {Pankaj Mathur},
title = {wizardlm_alpaca_dolly_orca_open_llama_3b: An explain tuned OpenLLaMA-3b model on custom wizardlm, alpaca, & dolly datasets},
year = {2023},
publisher = {GitHub, HuggingFace},
journal = {GitHub repository, HuggingFace repository},
howpublished = {\url{https://github.com/pankajarm/wizardlm_alpaca_dolly_orca_open_llama_3b}, \url{https://https://huggingface.co/psmathur/wizardlm_alpaca_dolly_orca_open_llama_3b}},
}
```
```
@software{openlm2023openllama,
author = {Xinyang Geng and Hao Liu},
title = {OpenLLaMA: An Open Reproduction of LLaMA},
month = May,
year = 2023,
url = {https://github.com/openlm-research/open_llama}
}
```
```
@misc{openalpaca,
author = {Yixuan Su and Tian Lan and Deng Cai},
title = {OpenAlpaca: A Fully Open-Source Instruction-Following Model Based On OpenLLaMA},
year = {2023},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/yxuansu/OpenAlpaca}},
}
```
```
@misc{alpaca,
author = {Rohan Taori and Ishaan Gulrajani and Tianyi Zhang and Yann Dubois and Xuechen Li and Carlos Guestrin and Percy Liang and Tatsunori B. Hashimoto },
title = {Stanford Alpaca: An Instruction-following LLaMA model},
year = {2023},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/tatsu-lab/stanford_alpaca}},
}
```
|
kbondar17/test-trainer | kbondar17 | 2023-06-25T10:12:41Z | 103 | 0 | transformers | [
"transformers",
"pytorch",
"bert",
"text-classification",
"generated_from_trainer",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-06-25T10:06:32Z | ---
license: mit
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: test-trainer
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. -->
# test-trainer
This model is a fine-tuned version of [nlptown/bert-base-multilingual-uncased-sentiment](https://huggingface.co/nlptown/bert-base-multilingual-uncased-sentiment) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4009
- F1: 0.6363
- Roc Auc: 0.7682
- Accuracy: 0.6079
## 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: 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: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
| No log | 1.0 | 125 | 0.2975 | 0.5710 | 0.7129 | 0.4693 |
| No log | 2.0 | 250 | 0.3742 | 0.6226 | 0.7621 | 0.6013 |
| No log | 3.0 | 375 | 0.4009 | 0.6363 | 0.7682 | 0.6079 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3
|
dhruvil237/userutterance_classification_verplus | dhruvil237 | 2023-06-25T10:05:26Z | 13 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"safetensors",
"deberta-v2",
"text-classification",
"generated_from_trainer",
"dataset:clinc_oos",
"doi:10.57967/hf/0811",
"license:mit",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-06-05T12:20:52Z | ---
license: mit
tags:
- generated_from_trainer
datasets:
- clinc_oos
metrics:
- accuracy
model-index:
- name: userutterance_classification_verplus
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: clinc_oos
type: clinc_oos
config: plus
split: validation
args: plus
metrics:
- name: Accuracy
type: accuracy
value: 0.9619354838709677
---
<!-- 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. -->
# userutterance_classification_verplus
This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on the clinc_oos dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2270
- Accuracy: 0.9619
## 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
- lr_scheduler_warmup_steps: 500
- num_epochs: 6
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 5.0219 | 0.21 | 200 | 4.9813 | 0.0077 |
| 4.8915 | 0.42 | 400 | 4.5741 | 0.1155 |
| 4.2736 | 0.63 | 600 | 3.5359 | 0.4719 |
| 3.2701 | 0.84 | 800 | 2.4291 | 0.7429 |
| 2.3578 | 1.05 | 1000 | 1.5793 | 0.8413 |
| 1.5695 | 1.26 | 1200 | 1.0029 | 0.8994 |
| 1.0412 | 1.47 | 1400 | 0.6475 | 0.9187 |
| 0.7034 | 1.68 | 1600 | 0.4439 | 0.9303 |
| 0.501 | 1.89 | 1800 | 0.3400 | 0.9381 |
| 0.3187 | 2.1 | 2000 | 0.2793 | 0.9439 |
| 0.2185 | 2.31 | 2200 | 0.2538 | 0.9490 |
| 0.1669 | 2.52 | 2400 | 0.2210 | 0.9523 |
| 0.1081 | 2.73 | 2600 | 0.2225 | 0.9519 |
| 0.1004 | 2.94 | 2800 | 0.2136 | 0.9555 |
| 0.0665 | 3.14 | 3000 | 0.2078 | 0.9561 |
| 0.0509 | 3.35 | 3200 | 0.2155 | 0.9568 |
| 0.05 | 3.56 | 3400 | 0.2107 | 0.9581 |
| 0.0527 | 3.77 | 3600 | 0.2171 | 0.9568 |
| 0.0447 | 3.98 | 3800 | 0.2128 | 0.9590 |
| 0.0259 | 4.19 | 4000 | 0.2099 | 0.9587 |
| 0.0279 | 4.4 | 4200 | 0.2179 | 0.9577 |
| 0.0176 | 4.61 | 4400 | 0.2191 | 0.9574 |
| 0.0288 | 4.82 | 4600 | 0.2216 | 0.9590 |
| 0.0328 | 5.03 | 4800 | 0.2237 | 0.9606 |
| 0.0154 | 5.24 | 5000 | 0.2241 | 0.9616 |
| 0.0157 | 5.45 | 5200 | 0.2265 | 0.9603 |
| 0.023 | 5.66 | 5400 | 0.2276 | 0.9613 |
| 0.0178 | 5.87 | 5600 | 0.2270 | 0.9619 |
### Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
joohwan/2222333l-gd | joohwan | 2023-06-25T10:05:13Z | 114 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | automatic-speech-recognition | 2023-06-25T08:10:32Z | ---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: 2222333l-gd
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. -->
# 2222333l-gd
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0984
- Wer: 13.1908
## 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: 4
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 2000
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 0.0206 | 0.18 | 500 | 0.1634 | 17.8738 |
| 0.0496 | 0.36 | 1000 | 0.1403 | 12.4680 |
| 0.0516 | 0.54 | 1500 | 0.1123 | 10.2394 |
| 0.0755 | 0.72 | 2000 | 0.0984 | 13.1908 |
### Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
GarbageCollector/MusicVOX | GarbageCollector | 2023-06-25T10:02:39Z | 0 | 2 | null | [
"stable-diffusion",
"safetensors",
"text-to-image",
"license:unknown",
"region:us"
] | text-to-image | 2023-06-01T14:48:41Z | ---
tags:
- stable-diffusion
- safetensors
pipeline_tag: text-to-image
license: unknown
---
<p>this place is my garbage collection.<br>
some models are not better than others.</p>
<p>___SAMPLES___</p>
<p>Area_51<br>
<img src="https://huggingface.co/GarbageCollector/MusicVOX/resolve/main/samples/sample_Area_51.jpg"/>
</p>
<p>Cat_Landmine<br>
<img src="https://huggingface.co/GarbageCollector/MusicVOX/resolve/main/samples/sample_Cat_Landmine.jpg"/>
</p>
<p>GREEN_sky<br>
<img src="https://huggingface.co/GarbageCollector/MusicVOX/resolve/main/samples/sample_GREEN_sky.jpg"/>
</p>
<p>Hocus_Pocus<br>
<img src="https://huggingface.co/GarbageCollector/MusicVOX/resolve/main/samples/sample_Hocus_Pocus.jpg"/>
</p>
<p>Mixture_LivingDEAD<br>
<img src="https://huggingface.co/GarbageCollector/MusicVOX/resolve/main/samples/sample_Mixture_LivingDEAD.jpg"/>
</p>
<p>RAINBOW_sky<br>
<img src="https://huggingface.co/GarbageCollector/MusicVOX/resolve/main/samples/sample_RAINBOW_sky.jpg"/>
</p>
<p>blackend_sky<br>
<img src="https://huggingface.co/GarbageCollector/MusicVOX/resolve/main/samples/sample_blackend_sky.jpg"/>
</p>
<p>leaving_tomorrow<br>
<img src="https://huggingface.co/GarbageCollector/MusicVOX/resolve/main/samples/sample_leaving_tomorrow.jpg"/>
</p>
<p>NEUROMANCE<br>
<img src="https://huggingface.co/GarbageCollector/MusicVOX/resolve/main/samples/sample_NEUROMANCE.jpg"/>
</p>
<p>Karnevil<br>
<img src="https://huggingface.co/GarbageCollector/MusicVOX/resolve/main/samples/sample_Karnevil.jpg"/>
</p>
<p>Sinktank<br>
<img src="https://huggingface.co/GarbageCollector/MusicVOX/resolve/main/samples/sample_Sinktank.jpg"/>
</p> |
mrizalf7/xlm-r-qa-squad-retrained | mrizalf7 | 2023-06-25T09:57:29Z | 102 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"xlm-roberta",
"question-answering",
"generated_from_trainer",
"license:mit",
"endpoints_compatible",
"region:us"
] | question-answering | 2023-06-13T19:17:39Z | ---
license: mit
tags:
- generated_from_trainer
model-index:
- name: xlm-roberta-finetuned-small-squad-indonesian-rizal-4-2
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-finetuned-small-squad-indonesian-rizal-4-2
This model is a fine-tuned version of [mrizalf7/xlm-roberta-finetuned-small-squad-indonesian-rizal-4](https://huggingface.co/mrizalf7/xlm-roberta-finetuned-small-squad-indonesian-rizal-4) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 5.4152
## 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: 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: 3
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 1.0 | 1 | 6.1326 |
| No log | 2.0 | 2 | 6.1326 |
| No log | 3.0 | 3 | 5.4152 |
### Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
|
VilohitT/question_answering_majorproject | VilohitT | 2023-06-25T09:46:03Z | 0 | 0 | peft | [
"peft",
"region:us"
] | null | 2023-06-25T09:46:01Z | ---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.4.0.dev0
|
bogdancazan/t5-small-newsela-biendata-with-domain-adaptation | bogdancazan | 2023-06-25T09:45:44Z | 106 | 0 | transformers | [
"transformers",
"pytorch",
"t5",
"text2text-generation",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text2text-generation | 2023-06-19T11:56:49Z | training_args = TrainingArguments(
output_dir='t5-small-newsela-biendata-with-domain-adaptation',
num_train_epochs=20,
warmup_steps=250,
per_device_train_batch_size=BATCH_SIZE,
weight_decay=0.01,
learning_rate=2e-4,
fp16=True,
optim="adafactor",
)
Step Training Loss
500 35.466600
1000 25.795400
1500 10.923200
2000 4.515500
TrainOutput(global_step=2320, training_loss=16.92537920721646, metrics={'train_runtime': 628.0033, 'train_samples_per_second': 472.418, 'train_steps_per_second': 3.694, 'total_flos': 0.0, 'train_loss': 16.92537920721646, 'epoch': 20.0}) |
lucasbertola/ppo-LunarLander-v2 | lucasbertola | 2023-06-25T09:29:20Z | 0 | 0 | stable-baselines3 | [
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | reinforcement-learning | 2023-06-19T11:40:03Z | ---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- metrics:
- type: mean_reward
value: 295.14 +/- 14.94
name: mean_reward
task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
---
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
sd-concepts-library/pokemon-raichu-sd-model | sd-concepts-library | 2023-06-25T09:26:29Z | 0 | 0 | null | [
"base_model:stabilityai/stable-diffusion-2",
"base_model:finetune:stabilityai/stable-diffusion-2",
"license:mit",
"region:us"
] | null | 2023-06-25T09:26:28Z | ---
license: mit
base_model: stabilityai/stable-diffusion-2
---
### Pokemon Raichu - SD model on Stable Diffusion
This is the `<cat-toy>` concept taught to Stable Diffusion via Textual Inversion. You can load this concept into the [Stable Conceptualizer](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/stable_conceptualizer_inference.ipynb) notebook. You can also train your own concepts and load them into the concept libraries using [this notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/sd_textual_inversion_training.ipynb).
Here is the new concept you will be able to use as an `object`:
|
ahishamm/vit-base-HAM-10000-sharpened | ahishamm | 2023-06-25T09:17:26Z | 190 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"vit",
"image-classification",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | image-classification | 2023-06-25T08:42:48Z | ---
license: apache-2.0
tags:
- image-classification
- generated_from_trainer
metrics:
- accuracy
- recall
- f1
- precision
model-index:
- name: vit-base-HAM-10000-sharpened
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-HAM-10000-sharpened
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the ahishamm/HAM_db_sharpened dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4392
- Accuracy: 0.8529
- Recall: 0.8529
- F1: 0.8529
- Precision: 0.8529
## 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: 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: 4
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Recall | F1 | Precision |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:---------:|
| 0.7303 | 0.2 | 100 | 0.7828 | 0.7197 | 0.7197 | 0.7197 | 0.7197 |
| 0.7198 | 0.4 | 200 | 0.7519 | 0.7377 | 0.7377 | 0.7377 | 0.7377 |
| 0.7519 | 0.6 | 300 | 0.7125 | 0.7541 | 0.7541 | 0.7541 | 0.7541 |
| 0.6657 | 0.8 | 400 | 0.6623 | 0.7571 | 0.7571 | 0.7571 | 0.7571 |
| 0.5896 | 1.0 | 500 | 0.5964 | 0.7835 | 0.7835 | 0.7835 | 0.7835 |
| 0.515 | 1.2 | 600 | 0.5745 | 0.8015 | 0.8015 | 0.8015 | 0.8015 |
| 0.4318 | 1.4 | 700 | 0.5061 | 0.8200 | 0.8200 | 0.8200 | 0.8200 |
| 0.4299 | 1.6 | 800 | 0.5239 | 0.8075 | 0.8075 | 0.8075 | 0.8075 |
| 0.4793 | 1.8 | 900 | 0.5366 | 0.8125 | 0.8125 | 0.8125 | 0.8125 |
| 0.4202 | 2.0 | 1000 | 0.4882 | 0.8244 | 0.8244 | 0.8244 | 0.8244 |
| 0.2105 | 2.2 | 1100 | 0.5330 | 0.8234 | 0.8234 | 0.8234 | 0.8234 |
| 0.2597 | 2.4 | 1200 | 0.4604 | 0.8369 | 0.8369 | 0.8369 | 0.8369 |
| 0.2261 | 2.59 | 1300 | 0.4893 | 0.8409 | 0.8409 | 0.8409 | 0.8409 |
| 0.1853 | 2.79 | 1400 | 0.4793 | 0.8494 | 0.8494 | 0.8494 | 0.8494 |
| 0.1739 | 2.99 | 1500 | 0.4392 | 0.8529 | 0.8529 | 0.8529 | 0.8529 |
| 0.0629 | 3.19 | 1600 | 0.4941 | 0.8584 | 0.8584 | 0.8584 | 0.8584 |
| 0.0802 | 3.39 | 1700 | 0.4974 | 0.8613 | 0.8613 | 0.8613 | 0.8613 |
| 0.0712 | 3.59 | 1800 | 0.5416 | 0.8594 | 0.8594 | 0.8594 | 0.8594 |
| 0.0365 | 3.79 | 1900 | 0.5318 | 0.8574 | 0.8574 | 0.8574 | 0.8574 |
| 0.0591 | 3.99 | 2000 | 0.5344 | 0.8574 | 0.8574 | 0.8574 | 0.8574 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
melowhy/whyde | melowhy | 2023-06-25T09:15:10Z | 0 | 0 | null | [
"license:bigscience-openrail-m",
"region:us"
] | null | 2023-06-25T09:15:10Z | ---
license: bigscience-openrail-m
---
|
thinkamconnect/ThinkSites | thinkamconnect | 2023-06-25T09:06:30Z | 0 | 0 | null | [
"text-to-video",
"license:mit",
"region:us"
] | text-to-video | 2023-06-25T09:03:27Z | ---
license: mit
pipeline_tag: text-to-video
--- |
tnvmadhav/food_classifier | tnvmadhav | 2023-06-25T09:06:06Z | 63 | 0 | transformers | [
"transformers",
"tf",
"vit",
"image-classification",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | image-classification | 2023-06-25T08:32:22Z | ---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: tnvmadhav/food_classifier
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. -->
# tnvmadhav/food_classifier
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.4025
- Validation Loss: 0.3368
- Train Accuracy: 0.91
- Epoch: 4
## 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': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 20000, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|:----------:|:---------------:|:--------------:|:-----:|
| 2.8090 | 1.6205 | 0.817 | 0 |
| 1.2350 | 0.8021 | 0.879 | 1 |
| 0.7254 | 0.5466 | 0.899 | 2 |
| 0.5023 | 0.3927 | 0.914 | 3 |
| 0.4025 | 0.3368 | 0.91 | 4 |
### Framework versions
- Transformers 4.30.2
- TensorFlow 2.12.0
- Datasets 2.13.1
- Tokenizers 0.13.3
|
BaoKien/my_awesome_qa_model | BaoKien | 2023-06-25T08:36:36Z | 104 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"albert",
"question-answering",
"generated_from_trainer",
"dataset:squad",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | question-answering | 2023-06-22T15:57:17Z | ---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- squad
model-index:
- name: my_awesome_qa_model
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_qa_model
This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the squad dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9515
## 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: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 0.889 | 1.0 | 4380 | 0.8729 |
| 0.6755 | 2.0 | 8760 | 0.8529 |
| 0.4681 | 3.0 | 13140 | 0.9515 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
joohwan/whisper-small-gd | joohwan | 2023-06-25T08:10:27Z | 79 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | automatic-speech-recognition | 2023-06-25T05:51:56Z | ---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-small-gd
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. -->
# whisper-small-gd
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1180
- Wer: 14.2298
## 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: 2
- eval_batch_size: 16
- 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
- lr_scheduler_warmup_steps: 200
- training_steps: 2000
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 0.0723 | 0.09 | 250 | 0.2013 | 22.6924 |
| 0.044 | 0.18 | 500 | 0.1826 | 27.3905 |
| 0.1209 | 0.27 | 750 | 0.1705 | 27.2700 |
| 0.0973 | 0.36 | 1000 | 0.1462 | 15.1182 |
| 0.0941 | 0.45 | 1250 | 0.1322 | 15.6603 |
| 0.076 | 0.54 | 1500 | 0.1258 | 18.3557 |
| 0.0967 | 0.63 | 1750 | 0.1203 | 14.8020 |
| 0.0757 | 0.72 | 2000 | 0.1180 | 14.2298 |
### Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
Lajonbot/polish-alpaca7B-lora | Lajonbot | 2023-06-25T07:41:13Z | 0 | 0 | null | [
"tensorboard",
"pl",
"dataset:Lajonbot/alpaca-dolly-chrisociepa-instruction-only-polish",
"license:openrail",
"region:us"
] | null | 2023-05-01T07:08:31Z | ---
license: openrail
datasets:
- Lajonbot/alpaca-dolly-chrisociepa-instruction-only-polish
language:
- pl
---
|
Lajonbot/Amazon-LightGPT-pl-qlora | Lajonbot | 2023-06-25T07:40:56Z | 0 | 0 | null | [
"tensorboard",
"pl",
"dataset:Lajonbot/alpaca-dolly-chrisociepa-instruction-only-polish",
"license:openrail",
"region:us"
] | null | 2023-05-29T06:22:37Z | ---
license: openrail
datasets:
- Lajonbot/alpaca-dolly-chrisociepa-instruction-only-polish
language:
- pl
---
|
Lajonbot/falcon-7b-instruct-pl-lora | Lajonbot | 2023-06-25T07:38:22Z | 0 | 0 | null | [
"tensorboard",
"pl",
"dataset:Lajonbot/alpaca-dolly-chrisociepa-instruction-only-polish",
"license:openrail",
"region:us"
] | null | 2023-06-12T06:13:24Z | ---
license: openrail
datasets:
- Lajonbot/alpaca-dolly-chrisociepa-instruction-only-polish
language:
- pl
---
|
Lajonbot/stablelm-base-alpha-3b-instruct-pl-lora | Lajonbot | 2023-06-25T07:37:23Z | 0 | 0 | null | [
"tensorboard",
"pl",
"dataset:Lajonbot/alpaca-dolly-chrisociepa-instruction-only-polish",
"license:openrail",
"region:us"
] | null | 2023-06-15T06:13:44Z | ---
license: openrail
datasets:
- Lajonbot/alpaca-dolly-chrisociepa-instruction-only-polish
language:
- pl
---
|
Lajonbot/polish-gpt2-small-instruct | Lajonbot | 2023-06-25T07:36:40Z | 114 | 0 | transformers | [
"transformers",
"pytorch",
"gpt2",
"text-generation",
"pl",
"dataset:Lajonbot/alpaca-dolly-chrisociepa-instruction-only-polish",
"license:openrail",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2023-06-20T19:33:30Z | ---
license: openrail
datasets:
- Lajonbot/alpaca-dolly-chrisociepa-instruction-only-polish
language:
- pl
---
|
Davlan/bert-base-multilingual-cased-finetuned-swahili | Davlan | 2023-06-25T07:32:51Z | 568 | 3 | transformers | [
"transformers",
"pytorch",
"tf",
"safetensors",
"bert",
"fill-mask",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | 2022-03-02T23:29:04Z | Hugging Face's logo
---
language: ha
datasets:
---
# bert-base-multilingual-cased-finetuned-swahili
## Model description
**bert-base-multilingual-cased-finetuned-swahili** is a **Swahili BERT** model obtained by fine-tuning **bert-base-multilingual-cased** model on Swahili language texts. It provides **better performance** than the multilingual BERT on text classification and named entity recognition datasets.
Specifically, this model is a *bert-base-multilingual-cased* model that was fine-tuned on Swahili corpus.
## Intended uses & limitations
#### How to use
You can use this model with Transformers *pipeline* for masked token prediction.
```python
>>> from transformers import pipeline
>>> unmasker = pipeline('fill-mask', model='Davlan/bert-base-multilingual-cased-finetuned-swahili')
>>> unmasker("Jumatatu, Bwana Kagame alielezea shirika la France24 huko [MASK] kwamba "hakuna uhalifu ulitendwa")
[{'sequence': 'Jumatatu, Bwana Kagame alielezea shirika la France24 huko Paris kwamba hakuna uhalifu ulitendwa',
'score': 0.31642526388168335,
'token': 10728,
'token_str': 'Paris'},
{'sequence': 'Jumatatu, Bwana Kagame alielezea shirika la France24 huko Rwanda kwamba hakuna uhalifu ulitendwa',
'score': 0.15753623843193054,
'token': 57557,
'token_str': 'Rwanda'},
{'sequence': 'Jumatatu, Bwana Kagame alielezea shirika la France24 huko Burundi kwamba hakuna uhalifu ulitendwa',
'score': 0.07211585342884064,
'token': 57824,
'token_str': 'Burundi'},
{'sequence': 'Jumatatu, Bwana Kagame alielezea shirika la France24 huko France kwamba hakuna uhalifu ulitendwa',
'score': 0.029844321310520172,
'token': 10688,
'token_str': 'France'},
{'sequence': 'Jumatatu, Bwana Kagame alielezea shirika la France24 huko Senegal kwamba hakuna uhalifu ulitendwa',
'score': 0.0265930388122797,
'token': 38052,
'token_str': 'Senegal'}]
```
#### Limitations and bias
This model is limited by its training dataset of entity-annotated news articles from a specific span of time. This may not generalize well for all use cases in different domains.
## Training data
This model was fine-tuned on [Swahili CC-100](http://data.statmt.org/cc-100/)
## Training procedure
This model was trained on a single NVIDIA V100 GPU
## Eval results on Test set (F-score, average over 5 runs)
Dataset| mBERT F1 | sw_bert F1
-|-|-
[MasakhaNER](https://github.com/masakhane-io/masakhane-ner) | 86.80 | 89.36
### BibTeX entry and citation info
By David Adelani
```
```
|
Davlan/bert-base-multilingual-cased-finetuned-igbo | Davlan | 2023-06-25T07:32:13Z | 117 | 0 | transformers | [
"transformers",
"pytorch",
"safetensors",
"bert",
"fill-mask",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | 2022-03-02T23:29:04Z | Hugging Face's logo
---
language: ig
datasets:
---
# bert-base-multilingual-cased-finetuned-igbo
## Model description
**bert-base-multilingual-cased-finetuned-igbo** is a **Igbo BERT** model obtained by fine-tuning **bert-base-multilingual-cased** model on Igbo language texts. It provides **better performance** than the multilingual BERT on text classification and named entity recognition datasets.
Specifically, this model is a *bert-base-multilingual-cased* model that was fine-tuned on Igbo corpus.
## Intended uses & limitations
#### How to use
You can use this model with Transformers *pipeline* for masked token prediction.
```python
>>> from transformers import pipeline
>>> unmasker = pipeline('fill-mask', model='Davlan/bert-base-multilingual-cased-finetuned-igbo')
>>> unmasker("Reno Omokri na Gọọmentị [MASK] enweghị ihe ha ga-eji hiwe ya bụ mmachi.")
```
#### Limitations and bias
This model is limited by its training dataset of entity-annotated news articles from a specific span of time. This may not generalize well for all use cases in different domains.
## Training data
This model was fine-tuned on JW300 + OPUS CC-Align + [IGBO NLP Corpus](https://github.com/IgnatiusEzeani/IGBONLP) +[Igbo CC-100](http://data.statmt.org/cc-100/)
## Training procedure
This model was trained on a single NVIDIA V100 GPU
## Eval results on Test set (F-score, average over 5 runs)
Dataset| mBERT F1 | ig_bert F1
-|-|-
[MasakhaNER](https://github.com/masakhane-io/masakhane-ner) | 85.11 | 86.75
### BibTeX entry and citation info
By David Adelani
```
```
|
boleshirish/Marathi_GPT2_Pretrained | boleshirish | 2023-06-25T07:29:30Z | 105 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"gpt2",
"text-generation",
"generated_from_trainer",
"mr",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2023-06-17T06:29:25Z | ---
license: mit
tags:
- generated_from_trainer
model-index:
- name: Marathi_GPT2_Pretrained
results: []
language:
- mr
metrics:
- accuracy
---
<!-- 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. -->
# Marathi_GPT2_Pretrained
- Loss: 1.8264
## 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: 32
- eval_batch_size: 32
- seed: 42
- 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 3.8893 | 0.27 | 500 | 2.5366 |
| 2.3286 | 0.53 | 1000 | 2.1366 |
| 2.005 | 0.8 | 1500 | 1.8264 |
### Framework versions
- Transformers 4.18.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.0
- Tokenizers 0.12.1 |
AdShenoy/Bart-samsum-fastai | AdShenoy | 2023-06-25T07:20:59Z | 0 | 0 | fastai | [
"fastai",
"region:us"
] | null | 2023-06-24T06:53:20Z | ---
tags:
- fastai
---
# Amazing!
🥳 Congratulations on hosting your fastai model on the Hugging Face Hub!
# Some next steps
1. Fill out this model card with more information (see the template below and the [documentation here](https://huggingface.co/docs/hub/model-repos))!
2. Create a demo in Gradio or Streamlit using 🤗 Spaces ([documentation here](https://huggingface.co/docs/hub/spaces)).
3. Join the fastai community on the [Fastai Discord](https://discord.com/invite/YKrxeNn)!
Greetings fellow fastlearner 🤝! Don't forget to delete this content from your model card.
---
# Model card
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
|
Davlan/xlm-roberta-large-masakhaner | Davlan | 2023-06-25T07:12:21Z | 135 | 2 | transformers | [
"transformers",
"pytorch",
"tf",
"safetensors",
"xlm-roberta",
"token-classification",
"arxiv:2103.11811",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | token-classification | 2022-03-02T23:29:04Z | Hugging Face's logo
---
language:
- amh
- hau
- ibo
- kin
- lug
- luo
- pcm
- swa
- wol
- yor
- multilingual
datasets:
- masakhaner
---
# xlm-roberta-large-masakhaner
## Model description
**xlm-roberta-large-masakhaner** is the first **Named Entity Recognition** model for 10 African languages (Amharic, Hausa, Igbo, Kinyarwanda, Luganda, Nigerian Pidgin, Swahili, Wolof, and Yorùbá) based on a fine-tuned XLM-RoBERTa large model. It achieves the **state-of-the-art performance** for the NER task. It has been trained to recognize four types of entities: dates & times (DATE), location (LOC), organizations (ORG), and person (PER).
Specifically, this model is a *xlm-roberta-large* model that was fine-tuned on an aggregation of African language datasets obtained from Masakhane [MasakhaNER](https://github.com/masakhane-io/masakhane-ner) dataset.
## Intended uses & limitations
#### How to use
You can use this model with Transformers *pipeline* for NER.
```python
from transformers import AutoTokenizer, AutoModelForTokenClassification
from transformers import pipeline
tokenizer = AutoTokenizer.from_pretrained("Davlan/xlm-roberta-large-masakhaner")
model = AutoModelForTokenClassification.from_pretrained("Davlan/xlm-roberta-large-masakhaner")
nlp = pipeline("ner", model=model, tokenizer=tokenizer)
example = "Emir of Kano turban Zhang wey don spend 18 years for Nigeria"
ner_results = nlp(example)
print(ner_results)
```
#### Limitations and bias
This model is limited by its training dataset of entity-annotated news articles from a specific span of time. This may not generalize well for all use cases in different domains.
## Training data
This model was fine-tuned on 10 African NER datasets (Amharic, Hausa, Igbo, Kinyarwanda, Luganda, Nigerian Pidgin, Swahili, Wolof, and Yorùbá) Masakhane [MasakhaNER](https://github.com/masakhane-io/masakhane-ner) dataset
The training dataset distinguishes between the beginning and continuation of an entity so that if there are back-to-back entities of the same type, the model can output where the second entity begins. As in the dataset, each token will be classified as one of the following classes:
Abbreviation|Description
-|-
O|Outside of a named entity
B-DATE |Beginning of a DATE entity right after another DATE entity
I-DATE |DATE entity
B-PER |Beginning of a person’s name right after another person’s name
I-PER |Person’s name
B-ORG |Beginning of an organisation right after another organisation
I-ORG |Organisation
B-LOC |Beginning of a location right after another location
I-LOC |Location
## Training procedure
This model was trained on a single NVIDIA V100 GPU with recommended hyperparameters from the [original MasakhaNER paper](https://arxiv.org/abs/2103.11811) which trained & evaluated the model on MasakhaNER corpus.
## Eval results on Test set (F-score)
language|F1-score
-|-
amh |75.76
hau |91.75
ibo |86.26
kin |76.38
lug |84.64
luo |80.65
pcm |89.55
swa |89.48
wol |70.70
yor |82.05
### BibTeX entry and citation info
```
@article{adelani21tacl,
title = {Masakha{NER}: Named Entity Recognition for African Languages},
author = {David Ifeoluwa Adelani and Jade Abbott and Graham Neubig and Daniel D'souza and Julia Kreutzer and Constantine Lignos and Chester Palen-Michel and Happy Buzaaba and Shruti Rijhwani and Sebastian Ruder and Stephen Mayhew and Israel Abebe Azime and Shamsuddeen Muhammad and Chris Chinenye Emezue and Joyce Nakatumba-Nabende and Perez Ogayo and Anuoluwapo Aremu and Catherine Gitau and Derguene Mbaye and Jesujoba Alabi and Seid Muhie Yimam and Tajuddeen Gwadabe and Ignatius Ezeani and Rubungo Andre Niyongabo and Jonathan Mukiibi and Verrah Otiende and Iroro Orife and Davis David and Samba Ngom and Tosin Adewumi and Paul Rayson and Mofetoluwa Adeyemi and Gerald Muriuki and Emmanuel Anebi and Chiamaka Chukwuneke and Nkiruka Odu and Eric Peter Wairagala and Samuel Oyerinde and Clemencia Siro and Tobius Saul Bateesa and Temilola Oloyede and Yvonne Wambui and Victor Akinode and Deborah Nabagereka and Maurice Katusiime and Ayodele Awokoya and Mouhamadane MBOUP and Dibora Gebreyohannes and Henok Tilaye and Kelechi Nwaike and Degaga Wolde and Abdoulaye Faye and Blessing Sibanda and Orevaoghene Ahia and Bonaventure F. P. Dossou and Kelechi Ogueji and Thierno Ibrahima DIOP and Abdoulaye Diallo and Adewale Akinfaderin and Tendai Marengereke and Salomey Osei},
journal = {Transactions of the Association for Computational Linguistics (TACL)},
month = {},
url = {https://arxiv.org/abs/2103.11811},
year = {2021}
}
```
|
ssj1989/open_llama_001 | ssj1989 | 2023-06-25T07:02:13Z | 0 | 0 | null | [
"code",
"en",
"license:mit",
"region:us"
] | null | 2023-06-25T07:00:59Z | ---
license: mit
language:
- en
tags:
- code
--- |
psymon/QLoRa-polyglot-5.8b-translate | psymon | 2023-06-25T06:53:47Z | 1 | 0 | peft | [
"peft",
"region:us"
] | null | 2023-06-25T02:54:27Z | ---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.4.0.dev0
|
teoha/openai-whisper-medium-PeftType.LORA-colab | teoha | 2023-06-25T06:51:18Z | 2 | 0 | peft | [
"peft",
"region:us"
] | null | 2023-06-25T06:51:11Z | ---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: True
- load_in_4bit: False
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
### Framework versions
- PEFT 0.4.0.dev0
|
zanafi/sentiment_model | zanafi | 2023-06-25T06:31:04Z | 16 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"safetensors",
"bert",
"text-classification",
"generated_from_trainer",
"dataset:indonlu",
"license:mit",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-06-23T06:53:10Z | ---
license: mit
tags:
- generated_from_trainer
datasets:
- indonlu
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: sentiment_model
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: indonlu
type: indonlu
config: emot
split: validation
args: emot
metrics:
- name: Accuracy
type: accuracy
value: 0.7363636363636363
- name: Precision
type: precision
value: 0.7397155596092384
- name: Recall
type: recall
value: 0.7459489407651173
- name: F1
type: f1
value: 0.741920437379511
---
<!-- 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. -->
# sentiment_model
This model is a fine-tuned version of [indolem/indobert-base-uncased](https://huggingface.co/indolem/indobert-base-uncased) on the indonlu dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7788
- Accuracy: 0.7364
- Precision: 0.7397
- Recall: 0.7459
- F1: 0.7419
## 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: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| 1.1939 | 1.0 | 221 | 0.8261 | 0.6932 | 0.7203 | 0.7034 | 0.7056 |
| 0.6866 | 2.0 | 442 | 0.7925 | 0.725 | 0.7378 | 0.7377 | 0.7346 |
| 0.4791 | 3.0 | 663 | 0.7788 | 0.7364 | 0.7397 | 0.7459 | 0.7419 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
sukantan/all-mpnet-base-v2-ftlegal-v3 | sukantan | 2023-06-25T06:20:52Z | 5 | 0 | sentence-transformers | [
"sentence-transformers",
"pytorch",
"mpnet",
"feature-extraction",
"sentence-similarity",
"dataset:sukantan/nyaya-st-training",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | sentence-similarity | 2023-06-25T06:20:46Z | ---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
datasets:
- sukantan/nyaya-st-training
---
# sukantan/all-mpnet-base-v2-ftlegal-v3
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
<!--- Describe your model here -->
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sukantan/all-mpnet-base-v2-ftlegal-v3')
embeddings = model.encode(sentences)
print(embeddings)
```
## Evaluation Results
<!--- Describe how your model was evaluated -->
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sukantan/all-mpnet-base-v2-ftlegal-v3)
## Training
The model was trained with the parameters:
**DataLoader**:
`torch.utils.data.dataloader.DataLoader` of length 391 with parameters:
```
{'batch_size': 16, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
```
**Loss**:
`sentence_transformers.losses.MegaBatchMarginLoss.MegaBatchMarginLoss`
Parameters of the fit()-Method:
```
{
"epochs": 10,
"evaluation_steps": 0,
"evaluator": "NoneType",
"max_grad_norm": 1,
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
"optimizer_params": {
"lr": 2e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": null,
"warmup_steps": 391,
"weight_decay": 0.01
}
```
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 384, '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})
(2): Normalize()
)
```
## Citing & Authors
<!--- Describe where people can find more information --> |
nolanaatama/mlycrsrvc750pchsvrs | nolanaatama | 2023-06-25T05:19:58Z | 0 | 0 | null | [
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-06-25T04:47:27Z | ---
license: creativeml-openrail-m
---
|
blackmount8/open-llama-13b-open-instruct-ct2-int8_float16 | blackmount8 | 2023-06-25T05:06:24Z | 1 | 0 | transformers | [
"transformers",
"text-generation",
"en",
"dataset:VMware/open-instruct-v1-oasst-dolly-hhrlhf",
"license:cc",
"region:us"
] | text-generation | 2023-06-24T17:32:32Z | ---
inference: false
license: cc
datasets:
- VMware/open-instruct-v1-oasst-dolly-hhrlhf
language:
- en
library_name: transformers
pipeline_tag: text-generation
---
# blackmount8/open-llama-13B-open-instruct-ct2-int8_float16
Int8_float16 version of [VMware/open-llama-13b-open-instruct](https://huggingface.co/VMware/open-llama-13b-open-instruct), quantized using CTranslate2.
## VMware/open-llama-13B-open-instruct
Instruction-tuned version of the fully trained Open LLama 13B model. The model is open for `<b>`COMMERCIAL USE `</b>`. `<br>`
`<b>` NOTE `</b>` : The model was trained using the Alpaca prompt template
`<b>` NOTE `</b>` : Fast tokenizer results in incorrect encoding, set the ``use_fast = False`` parameter, when instantiating the tokenizer
## License
- `<b>`Commercially Viable `</b>`
- Instruction dataset, [VMware/open-instruct-v1-oasst-dolly-hhrlhf](https://huggingface.co/datasets/VMware/open-instruct-v1-oasst-dolly-hhrlhf) is under cc-by-sa-3.0
- Language Model, ([openlm-research/open_llama_13b](https://huggingface.co/openlm-research/open_llama_13b)) is under apache-2.0
## Nomenclature
- Model : Open-llama
- Model Size: 13B parameters
- Dataset: Open-instruct-v1 (oasst, dolly, hhrlhf)
## Use in CTranslate2
```
import ctranslate2
from transformers import AutoTokenizer
model_name = "blackmount8/open-llama-13b-open-instruct-ct2-int8_float16"
tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=False, padding_side="left", truncation_side="left")
model = ctranslate2.Generator(model_name, device="auto", compute_type="int8_float16")
input_text = ["What is the meaning of stonehenge?", "Hello mate!"]
input_ids = tokenizer(input_text, return_tensors="pt", padding=True, truncation=True).input_ids
input_tokens = [tokenizer.convert_ids_to_tokens(ele) for ele in input_ids]
outputs = model.generate_batch(input_tokens, max_length=128)
output_tokens = [
ele.sequences_ids[0] for ele in outputs
]
output = tokenizer.batch_decode(output_tokens)
print(output)
```
|
Gayathri142214002/t5_qg_1 | Gayathri142214002 | 2023-06-25T04:58:01Z | 161 | 0 | transformers | [
"transformers",
"pytorch",
"t5",
"text2text-generation",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text2text-generation | 2023-06-25T04:53:50Z | ---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: t5_qg_1
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_qg_1
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0323
## 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: 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: linear
- num_epochs: 7
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.658 | 0.69 | 10 | 1.9854 |
| 1.7442 | 1.38 | 20 | 1.6146 |
| 1.3456 | 2.07 | 30 | 1.3937 |
| 0.9931 | 2.76 | 40 | 1.2447 |
| 0.9253 | 3.45 | 50 | 1.1519 |
| 0.7154 | 4.14 | 60 | 1.0958 |
| 0.6624 | 4.83 | 70 | 1.0645 |
| 0.6384 | 5.52 | 80 | 1.0412 |
| 0.4889 | 6.21 | 90 | 1.0323 |
### Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
|
pandalla/datatager_E-Commerce_review_extraction | pandalla | 2023-06-25T04:26:25Z | 103 | 27 | transformers | [
"transformers",
"pytorch",
"chatglm",
"feature-extraction",
"text-classification",
"custom_code",
"zh",
"license:apache-2.0",
"region:us"
] | text-classification | 2023-06-25T03:26:30Z | ---
license: apache-2.0
language:
- zh
pipeline_tag: text-classification
---
# CommentOpinionExtract
本模型用于从电商评论数据中，提取关键词和核心观点
# Dataset
本模型利用5000条淘宝评论数据训练，先使用GPT4通过prompt抽取数据的关键词，经过清洗再使用ChatGLM进行训练
# Result
| 原句 | keywords |
| ------------------------------------------------------------ | ---------------------------------------------------------- |
| 好用！！！ | 好用、值得推荐、性价比高 |
| 这是第二瓶，我都怀疑是不是买了个假货，包装也都换了，换的质感挺low，用完油油腻腻，第一瓶时候挺清爽，所以续购，没想到第二瓶跟第一瓶完全不一样，用完还闷痘，油腻！不管真假不会回购了 | 假货、包装质感low、油腻腻、闷痘、不回购 |
| 买了两个50的套餐，一个好点的挖勺都不送一个？？？ | 价格贵、无语 |
| 包装品质：不错 商品气味：普通香 使用效果：一般 同价位不如腊梅精华水…… 。。。。哈哈哈哈哈哈我真的好喜欢这个节目的呢我真的好喜欢这个节目真的是太给力了哟我们的综艺节目都是这么给力的吗。 | 包装品质不错、商品气味普通香、使用效果一般、不如腊梅精华水 |
|
andrewromitti/alzheimer_model_aug_deit5 | andrewromitti | 2023-06-25T03:58:45Z | 193 | 1 | transformers | [
"transformers",
"pytorch",
"deit",
"image-classification",
"generated_from_trainer",
"dataset:imagefolder",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | image-classification | 2023-06-25T02:14:15Z | ---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: alzheimer_model_aug_deit5
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: test
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.9996875
---
<!-- 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. -->
# alzheimer_model_aug_deit5
This model is a fine-tuned version of [facebook/deit-base-distilled-patch16-224](https://huggingface.co/facebook/deit-base-distilled-patch16-224) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0012
- Accuracy: 0.9997
## 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: 16
- eval_batch_size: 8
- seed: 1234
- gradient_accumulation_steps: 10
- total_train_batch_size: 160
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.5045 | 1.0 | 212 | 0.1414 | 0.9522 |
| 0.0779 | 2.0 | 424 | 0.0222 | 0.9961 |
| 0.0156 | 3.0 | 637 | 0.0164 | 0.9941 |
| 0.0032 | 4.0 | 849 | 0.0044 | 0.9983 |
| 0.0004 | 4.99 | 1060 | 0.0012 | 0.9997 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
ardhies/dev | ardhies | 2023-06-25T03:55:45Z | 0 | 0 | null | [
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-06-25T03:51:43Z | ---
license: creativeml-openrail-m
---
|
blackmount8/open-llama-7b-open-instruct-ct2-float16 | blackmount8 | 2023-06-25T03:49:04Z | 9 | 0 | transformers | [
"transformers",
"text-generation",
"en",
"dataset:VMware/open-instruct-v1-oasst-dolly-hhrlhf",
"license:cc",
"region:us"
] | text-generation | 2023-06-24T15:05:27Z | ---
inference: false
license: cc
datasets:
- VMware/open-instruct-v1-oasst-dolly-hhrlhf
language:
- en
library_name: transformers
pipeline_tag: text-generation
---
# blackmount8/open-llama-7B-open-instruct-ct2-float16
Float16 version of [VMware/open-llama-7b-open-instruct](https://huggingface.co/VMware/open-llama-7b-open-instruct), quantized using CTranslate2.
## VMware/open-llama-7B-open-instruct
Instruction-tuned version of the fully trained Open LLama 7B model. The model is open for `<b>`COMMERCIAL USE `</b>`. `<br>`
`<b>` NOTE `</b>` : The model was trained using the Alpaca prompt template
`<b>` NOTE `</b>` : Fast tokenizer results in incorrect encoding, set the ``use_fast = False`` parameter, when instantiating the tokenizer
## License
- `<b>`Commercially Viable `</b>`
- Instruction dataset, [VMware/open-instruct-v1-oasst-dolly-hhrlhf](https://huggingface.co/datasets/VMware/open-instruct-v1-oasst-dolly-hhrlhf) is under cc-by-sa-3.0
- Language Model, ([openlm-research/open_llama_7b](https://huggingface.co/openlm-research/open_llama_7b)) is under apache-2.0
## Nomenclature
- Model : Open-llama
- Model Size: 7B parameters
- Dataset: Open-instruct-v1 (oasst, dolly, hhrlhf)
## Use in CTranslate2
```
import ctranslate2
from transformers import AutoTokenizer
model_name = "blackmount8/open-llama-7b-open-instruct-ct2-float16"
tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=False, padding_side="left", truncation_side="left")
model = ctranslate2.Generator(model_name, device="auto", compute_type="float16")
input_text = ["What is the meaning of stonehenge?", "Hello mate!"]
input_ids = tokenizer(input_text, return_tensors="pt", padding=True, truncation=True).input_ids
input_tokens = [tokenizer.convert_ids_to_tokens(ele) for ele in input_ids]
outputs = model.generate_batch(input_tokens, max_length=128)
output_tokens = [
ele.sequences_ids[0] for ele in outputs
]
output = tokenizer.batch_decode(output_tokens)
print(output)
```
|
blackmount8/open-llama-13b-open-instruct-ct2-float16 | blackmount8 | 2023-06-25T03:48:21Z | 4 | 0 | transformers | [
"transformers",
"text-generation",
"en",
"dataset:VMware/open-instruct-v1-oasst-dolly-hhrlhf",
"license:cc",
"region:us"
] | text-generation | 2023-06-24T16:44:56Z | ---
inference: false
license: cc
datasets:
- VMware/open-instruct-v1-oasst-dolly-hhrlhf
language:
- en
library_name: transformers
pipeline_tag: text-generation
---
# blackmount8/open-llama-13B-open-instruct-ct2-float16
Float16 version of [VMware/open-llama-13b-open-instruct](https://huggingface.co/VMware/open-llama-13b-open-instruct), quantized using CTranslate2.
## VMware/open-llama-13B-open-instruct
Instruction-tuned version of the fully trained Open LLama 13B model. The model is open for `<b>`COMMERCIAL USE `</b>`. `<br>`
`<b>` NOTE `</b>` : The model was trained using the Alpaca prompt template
`<b>` NOTE `</b>` : Fast tokenizer results in incorrect encoding, set the ``use_fast = False`` parameter, when instantiating the tokenizer
## License
- `<b>`Commercially Viable `</b>`
- Instruction dataset, [VMware/open-instruct-v1-oasst-dolly-hhrlhf](https://huggingface.co/datasets/VMware/open-instruct-v1-oasst-dolly-hhrlhf) is under cc-by-sa-3.0
- Language Model, ([openlm-research/open_llama_13b](https://huggingface.co/openlm-research/open_llama_13b)) is under apache-2.0
## Nomenclature
- Model : Open-llama
- Model Size: 13B parameters
- Dataset: Open-instruct-v1 (oasst, dolly, hhrlhf)
## Use in CTranslate2
```
import ctranslate2
from transformers import AutoTokenizer
model_name = "blackmount8/open-llama-13b-open-instruct-ct2-float16"
tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=False, padding_side="left", truncation_side="left")
model = ctranslate2.Generator(model_name, device="auto", compute_type="float16")
input_text = ["What is the meaning of stonehenge?", "Hello mate!"]
input_ids = tokenizer(input_text, return_tensors="pt", padding=True, truncation=True).input_ids
input_tokens = [tokenizer.convert_ids_to_tokens(ele) for ele in input_ids]
outputs = model.generate_batch(input_tokens, max_length=128)
output_tokens = [
ele.sequences_ids[0] for ele in outputs
]
output = tokenizer.batch_decode(output_tokens)
print(output)
```
|
duyhngoc/Wave2Vec2_OV_Vie | duyhngoc | 2023-06-25T03:47:48Z | 77 | 0 | transformers | [
"transformers",
"pytorch",
"wav2vec2",
"automatic-speech-recognition",
"vivos",
"generated_from_trainer",
"dataset:vivos",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | automatic-speech-recognition | 2023-06-21T10:58:36Z | ---
license: apache-2.0
tags:
- automatic-speech-recognition
- vivos
- generated_from_trainer
datasets:
- vivos
metrics:
- wer
model-index:
- name: Wave2Vec2_OV_Vie
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. -->
# Wave2Vec2_OV_Vie
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the VIVOS - NA dataset.
It achieves the following results on the evaluation set:
- Loss: 3.5894
- Wer: 1.0
## 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: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 15.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:---:|
| No log | 0.27 | 100 | 3.9210 | 1.0 |
| No log | 0.55 | 200 | 3.4375 | 1.0 |
| No log | 0.82 | 300 | 3.4356 | 1.0 |
| No log | 1.1 | 400 | 3.4045 | 1.0 |
| 4.1866 | 1.37 | 500 | 3.4694 | 1.0 |
| 4.1866 | 1.65 | 600 | 3.6266 | 1.0 |
| 4.1866 | 1.92 | 700 | 3.5694 | 1.0 |
| 4.1866 | 2.19 | 800 | 3.5733 | 1.0 |
| 4.1866 | 2.47 | 900 | 3.6381 | 1.0 |
| 3.4376 | 2.74 | 1000 | 3.6604 | 1.0 |
| 3.4376 | 3.02 | 1100 | 3.5868 | 1.0 |
| 3.4376 | 3.29 | 1200 | 3.4988 | 1.0 |
| 3.4376 | 3.57 | 1300 | 3.5409 | 1.0 |
| 3.4376 | 3.84 | 1400 | 3.4883 | 1.0 |
| 3.4365 | 4.12 | 1500 | 3.6125 | 1.0 |
| 3.4365 | 4.39 | 1600 | 3.6123 | 1.0 |
| 3.4365 | 4.66 | 1700 | 3.5978 | 1.0 |
| 3.4365 | 4.94 | 1800 | 3.5693 | 1.0 |
| 3.4365 | 5.21 | 1900 | 3.5659 | 1.0 |
| 3.4339 | 5.49 | 2000 | 3.6234 | 1.0 |
| 3.4339 | 5.76 | 2100 | 3.5997 | 1.0 |
| 3.4339 | 6.04 | 2200 | 3.6529 | 1.0 |
| 3.4339 | 6.31 | 2300 | 3.5780 | 1.0 |
| 3.4339 | 6.58 | 2400 | 3.5844 | 1.0 |
| 3.4333 | 6.86 | 2500 | 3.5792 | 1.0 |
| 3.4333 | 7.13 | 2600 | 3.5468 | 1.0 |
| 3.4333 | 7.41 | 2700 | 3.5691 | 1.0 |
| 3.4333 | 7.68 | 2800 | 3.5408 | 1.0 |
| 3.4333 | 7.96 | 2900 | 3.5482 | 1.0 |
| 3.4294 | 8.23 | 3000 | 3.6070 | 1.0 |
| 3.4294 | 8.5 | 3100 | 3.5905 | 1.0 |
| 3.4294 | 8.78 | 3200 | 3.6018 | 1.0 |
| 3.4294 | 9.05 | 3300 | 3.6326 | 1.0 |
| 3.4294 | 9.33 | 3400 | 3.6214 | 1.0 |
| 3.4293 | 9.6 | 3500 | 3.6372 | 1.0 |
| 3.4293 | 9.88 | 3600 | 3.6215 | 1.0 |
| 3.4293 | 10.15 | 3700 | 3.5106 | 1.0 |
| 3.4293 | 10.43 | 3800 | 3.5066 | 1.0 |
| 3.4293 | 10.7 | 3900 | 3.5352 | 1.0 |
| 3.4295 | 10.97 | 4000 | 3.5129 | 1.0 |
| 3.4295 | 11.25 | 4100 | 3.6384 | 1.0 |
| 3.4295 | 11.52 | 4200 | 3.6019 | 1.0 |
| 3.4295 | 11.8 | 4300 | 3.5876 | 1.0 |
| 3.4295 | 12.07 | 4400 | 3.6207 | 1.0 |
| 3.4252 | 12.35 | 4500 | 3.5998 | 1.0 |
| 3.4252 | 12.62 | 4600 | 3.6216 | 1.0 |
| 3.4252 | 12.89 | 4700 | 3.6073 | 1.0 |
| 3.4252 | 13.17 | 4800 | 3.5567 | 1.0 |
| 3.4252 | 13.44 | 4900 | 3.5745 | 1.0 |
| 3.4274 | 13.72 | 5000 | 3.5738 | 1.0 |
| 3.4274 | 13.99 | 5100 | 3.5914 | 1.0 |
| 3.4274 | 14.27 | 5200 | 3.6004 | 1.0 |
| 3.4274 | 14.54 | 5300 | 3.5968 | 1.0 |
| 3.4274 | 14.81 | 5400 | 3.5908 | 1.0 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.0
- Tokenizers 0.13.3
|
dxyy/monteCarlo-cartpolev1 | dxyy | 2023-06-25T03:34:19Z | 0 | 0 | null | [
"CartPole-v1",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] | reinforcement-learning | 2023-06-25T03:21:22Z | ---
tags:
- CartPole-v1
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: monteCarlo-cartpolev1
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: CartPole-v1
type: CartPole-v1
metrics:
- type: mean_reward
value: 470.60 +/- 18.14
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **CartPole-v1**
This is a trained model of a **Reinforce** agent playing **CartPole-v1** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
jiuzhan/YoLoV7-dog | jiuzhan | 2023-06-25T03:27:58Z | 0 | 0 | null | [
"region:us"
] | null | 2023-06-25T03:11:07Z | # 狗的种类识别
用了500张图片的数据集，有点少。
分了38个种类，每种张数有点少。
效果一般。 |
hongyin/awareness-en-zh-0.8b-instruct | hongyin | 2023-06-25T03:26:59Z | 130 | 1 | transformers | [
"transformers",
"pytorch",
"bloom",
"text-generation",
"en",
"zh",
"arxiv:2302.13173",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2023-06-24T23:35:39Z | ---
language:
- en
- zh
pipeline_tag: text-generation
---
## hongyin/awareness-en-zh-0.8b-instruct
This is a English-Chinese bilingual autoregressive language model based on Bloom with a parameter size of 0.8b. The training process consists of two parts: (1) NTP task. (2) Instruction tuning. It is worth noting that although the model has learned many NLP downstream tasks (excluding multi-round dialogue), the model is not yet able to act like a chatbot. The model can be used as a raw material for alchemy.
## Bibtex entry and citation info
Please cite if you find it helpful.
```
@article{zhu2023metaaid,
title={MetaAID 2.0: An Extensible Framework for Developing Metaverse Applications via Human-controllable Pre-trained Models},
author={Zhu, Hongyin},
journal={arXiv preprint arXiv:2302.13173},
year={2023}
}
```
---
license: other
---
|
gaiamolinaro/ppo-SnowballTarget | gaiamolinaro | 2023-06-25T02:36:18Z | 0 | 0 | ml-agents | [
"ml-agents",
"tensorboard",
"onnx",
"SnowballTarget",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SnowballTarget",
"region:us"
] | reinforcement-learning | 2023-06-25T02:36:11Z | ---
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: gaiamolinaro/ppo-SnowballTarget
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
Rasith/NZappFineTune | Rasith | 2023-06-25T02:31:07Z | 61 | 0 | transformers | [
"transformers",
"tf",
"distilbert",
"text-classification",
"generated_from_keras_callback",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-06-25T02:30:54Z | ---
tags:
- generated_from_keras_callback
model-index:
- name: NZappFineTune
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. -->
# NZappFineTune
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
## 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: None
- training_precision: float32
### Training results
### Framework versions
- Transformers 4.30.2
- TensorFlow 2.12.0
- Tokenizers 0.13.3
|
gaiamolinaro/Reinforce-PixelCopter | gaiamolinaro | 2023-06-25T02:20:00Z | 0 | 0 | null | [
"Pixelcopter-PLE-v0",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] | reinforcement-learning | 2023-06-25T02:19:35Z | ---
tags:
- Pixelcopter-PLE-v0
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-PixelCopter
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Pixelcopter-PLE-v0
type: Pixelcopter-PLE-v0
metrics:
- type: mean_reward
value: -4.90 +/- 0.30
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **Pixelcopter-PLE-v0**
This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
marty1885/RWKV-v4-neo-gemini | marty1885 | 2023-06-25T02:13:45Z | 0 | 0 | null | [
"region:us"
] | null | 2023-06-25T01:35:12Z | # RWKV V4neo Gemini
RWKV V4neo langage models trained completely from scratch using only textual data collected from the [Gemini protocol](https://gemini.circumlunar.space/).
## License
[PMLL](https://github.com/marty1885/libreml-license/blob/master/PMLL.txt) |
mort666/faster-whisper-large-v2-th | mort666 | 2023-06-25T02:13:04Z | 644 | 8 | ctranslate2 | [
"ctranslate2",
"audio",
"automatic-speech-recognition",
"en",
"zh",
"de",
"es",
"ru",
"ko",
"fr",
"ja",
"pt",
"tr",
"pl",
"ca",
"nl",
"ar",
"sv",
"it",
"id",
"hi",
"fi",
"vi",
"he",
"uk",
"el",
"ms",
"cs",
"ro",
"da",
"hu",
"ta",
"no",
"th",
"ur",
"hr",
"bg",
"lt",
"la",
"mi",
"ml",
"cy",
"sk",
"te",
"fa",
"lv",
"bn",
"sr",
"az",
"sl",
"kn",
"et",
"mk",
"br",
"eu",
"is",
"hy",
"ne",
"mn",
"bs",
"kk",
"sq",
"sw",
"gl",
"mr",
"pa",
"si",
"km",
"sn",
"yo",
"so",
"af",
"oc",
"ka",
"be",
"tg",
"sd",
"gu",
"am",
"yi",
"lo",
"uz",
"fo",
"ht",
"ps",
"tk",
"nn",
"mt",
"sa",
"lb",
"my",
"bo",
"tl",
"mg",
"as",
"tt",
"haw",
"ln",
"ha",
"ba",
"jw",
"su",
"license:mit",
"region:us"
] | automatic-speech-recognition | 2023-06-18T15:28:40Z | ---
language:
- en
- zh
- de
- es
- ru
- ko
- fr
- ja
- pt
- tr
- pl
- ca
- nl
- ar
- sv
- it
- id
- hi
- fi
- vi
- he
- uk
- el
- ms
- cs
- ro
- da
- hu
- ta
- 'no'
- th
- ur
- hr
- bg
- lt
- la
- mi
- ml
- cy
- sk
- te
- fa
- lv
- bn
- sr
- az
- sl
- kn
- et
- mk
- br
- eu
- is
- hy
- ne
- mn
- bs
- kk
- sq
- sw
- gl
- mr
- pa
- si
- km
- sn
- yo
- so
- af
- oc
- ka
- be
- tg
- sd
- gu
- am
- yi
- lo
- uz
- fo
- ht
- ps
- tk
- nn
- mt
- sa
- lb
- my
- bo
- tl
- mg
- as
- tt
- haw
- ln
- ha
- ba
- jw
- su
tags:
- audio
- automatic-speech-recognition
license: mit
library_name: ctranslate2
---
# Whisper large-v2 (Thai Finetune) model for CTranslate2
This repository contains the conversion of the [biodatlab/whisper-th-large-combined](https://huggingface.co/biodatlab/whisper-th-large-combined) which is finetune of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) for the Thai language to the [CTranslate2](https://github.com/OpenNMT/CTranslate2) model format.
This model can be used in CTranslate2 or projects based on CTranslate2 such as [faster-whisper](https://github.com/guillaumekln/faster-whisper).
## Example
```python
from faster_whisper import WhisperModel
model = WhisperModel("large-v2")
segments, info = model.transcribe("audio.mp3")
for segment in segments:
print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))
```
## Conversion details
The original model was converted with the following command:
```
ct2-transformers-converter --model biodatlab/whisper-th-large-combined --output_dir faster-whisper-large-v2-th \
--copy_files tokenizer.json --quantization float16
```
Note that the model weights are saved in FP16. This type can be changed when the model is loaded using the [`compute_type` option in CTranslate2](https://opennmt.net/CTranslate2/quantization.html).
## More information
**For more information about the original model, see its [model card](https://huggingface.co/biodatlab/whisper-th-large-combined).**
|
nbiish/learning-FrozenLake-v1-4x4-noSlip | nbiish | 2023-06-25T02:12:15Z | 0 | 0 | null | [
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | reinforcement-learning | 2023-06-25T01:54:56Z | ---
tags:
- FrozenLake-v1-4x4-no_slippery
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: learning-FrozenLake-v1-4x4-noSlip
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: FrozenLake-v1-4x4-no_slippery
type: FrozenLake-v1-4x4-no_slippery
metrics:
- type: mean_reward
value: 1.00 +/- 0.00
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
```python
model = load_from_hub(repo_id="nbiish/learning-FrozenLake-v1-4x4-noSlip", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
NasimB/gpt2-dp-mod_aochild | NasimB | 2023-06-25T00:27:44Z | 3 | 0 | transformers | [
"transformers",
"pytorch",
"gpt2",
"text-generation",
"generated_from_trainer",
"dataset:generator",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2023-06-24T20:59:20Z | ---
license: mit
tags:
- generated_from_trainer
datasets:
- generator
model-index:
- name: gpt2-dp-mod_aochild
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. -->
# gpt2-dp-mod_aochild
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 4.4146
## 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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 10
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 6.706 | 0.27 | 500 | 5.6466 |
| 5.3616 | 0.54 | 1000 | 5.2058 |
| 5.0148 | 0.81 | 1500 | 4.9571 |
| 4.7595 | 1.08 | 2000 | 4.8100 |
| 4.5716 | 1.35 | 2500 | 4.6947 |
| 4.4792 | 1.62 | 3000 | 4.5951 |
| 4.3985 | 1.89 | 3500 | 4.5126 |
| 4.2203 | 2.16 | 4000 | 4.4747 |
| 4.1373 | 2.42 | 4500 | 4.4206 |
| 4.1109 | 2.69 | 5000 | 4.3695 |
| 4.0827 | 2.96 | 5500 | 4.3285 |
| 3.8662 | 3.23 | 6000 | 4.3409 |
| 3.863 | 3.5 | 6500 | 4.3058 |
| 3.8585 | 3.77 | 7000 | 4.2777 |
| 3.8073 | 4.04 | 7500 | 4.2766 |
| 3.594 | 4.31 | 8000 | 4.2886 |
| 3.6275 | 4.58 | 8500 | 4.2700 |
| 3.6373 | 4.85 | 9000 | 4.2436 |
| 3.488 | 5.12 | 9500 | 4.2800 |
| 3.3669 | 5.39 | 10000 | 4.2884 |
| 3.3981 | 5.66 | 10500 | 4.2764 |
| 3.3991 | 5.93 | 11000 | 4.2533 |
| 3.177 | 6.2 | 11500 | 4.3110 |
| 3.1321 | 6.47 | 12000 | 4.3137 |
| 3.1491 | 6.73 | 12500 | 4.3083 |
| 3.1544 | 7.0 | 13000 | 4.3112 |
| 2.8924 | 7.27 | 13500 | 4.3587 |
| 2.9109 | 7.54 | 14000 | 4.3634 |
| 2.9185 | 7.81 | 14500 | 4.3600 |
| 2.8619 | 8.08 | 15000 | 4.3819 |
| 2.7347 | 8.35 | 15500 | 4.3980 |
| 2.7435 | 8.62 | 16000 | 4.4007 |
| 2.752 | 8.89 | 16500 | 4.4012 |
| 2.6887 | 9.16 | 17000 | 4.4116 |
| 2.6506 | 9.43 | 17500 | 4.4137 |
| 2.6588 | 9.7 | 18000 | 4.4144 |
| 2.66 | 9.97 | 18500 | 4.4146 |
### Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
|
alantao912/models | alantao912 | 2023-06-25T00:07:35Z | 13 | 0 | transformers | [
"transformers",
"pytorch",
"blip",
"image-text-to-text",
"generated_from_trainer",
"dataset:imagefolder",
"license:bsd-3-clause",
"endpoints_compatible",
"region:us"
] | image-text-to-text | 2023-06-24T20:19:09Z | ---
license: bsd-3-clause
tags:
- generated_from_trainer
datasets:
- imagefolder
model-index:
- name: models
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. -->
# models
This model is a fine-tuned version of [Salesforce/blip-image-captioning-base](https://huggingface.co/Salesforce/blip-image-captioning-base) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4107
- Wer Score: 0.5495
## 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: 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: linear
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Score |
|:-------------:|:-----:|:----:|:---------------:|:---------:|
| 9.4536 | 0.05 | 10 | 7.8217 | 41.7753 |
| 7.3267 | 0.11 | 20 | 6.6585 | 0.7753 |
| 6.2358 | 0.16 | 30 | 5.7758 | 0.5667 |
| 5.2862 | 0.22 | 40 | 4.7628 | 0.5419 |
| 4.3786 | 0.27 | 50 | 3.9203 | 0.6398 |
| 3.5554 | 0.33 | 60 | 3.1482 | 0.5613 |
| 2.849 | 0.38 | 70 | 2.5209 | 0.5548 |
| 2.3041 | 0.44 | 80 | 2.0561 | 0.5645 |
| 1.8999 | 0.49 | 90 | 1.7474 | 0.5645 |
| 1.658 | 0.55 | 100 | 1.5722 | 0.5548 |
| 1.5238 | 0.6 | 110 | 1.4836 | 0.5591 |
| 1.4726 | 0.66 | 120 | 1.4461 | 0.5538 |
| 1.4328 | 0.71 | 130 | 1.4285 | 0.5473 |
| 1.4211 | 0.77 | 140 | 1.4205 | 0.5559 |
| 1.4202 | 0.82 | 150 | 1.4156 | 0.5548 |
| 1.4098 | 0.88 | 160 | 1.4129 | 0.5505 |
| 1.4124 | 0.93 | 170 | 1.4113 | 0.5548 |
| 1.4075 | 0.99 | 180 | 1.4107 | 0.5495 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cpu
- Datasets 2.13.1
- Tokenizers 0.13.3
|
nolestock/RedPajama-INCITE-Base-3B-v1-ft-guanaco-lora | nolestock | 2023-06-24T23:48:17Z | 1 | 0 | peft | [
"peft",
"region:us"
] | null | 2023-06-24T23:48:06Z | ---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.4.0.dev0
|
MonkDalma/xlm-roberta-base-finetuned-panx-all | MonkDalma | 2023-06-24T23:45:34Z | 103 | 0 | transformers | [
"transformers",
"pytorch",
"xlm-roberta",
"token-classification",
"generated_from_trainer",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | token-classification | 2023-06-24T23:40:04Z | ---
license: mit
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: xlm-roberta-base-finetuned-panx-all
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-finetuned-panx-all
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1743
- F1: 0.8540
## 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: 24
- eval_batch_size: 24
- 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 | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.3004 | 1.0 | 835 | 0.1875 | 0.8178 |
| 0.1562 | 2.0 | 1670 | 0.1724 | 0.8430 |
| 0.1013 | 3.0 | 2505 | 0.1743 | 0.8540 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
mohameddhiab/rate-jokes-bert | mohameddhiab | 2023-06-24T23:45:08Z | 121 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"roberta",
"text-classification",
"generated_from_trainer",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-06-24T23:21:00Z | ---
license: mit
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: rate-jokes-bert
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. -->
# rate-jokes-bert
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.0871
- F1: 0.0444
## 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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| No log | 1.0 | 64 | 2.4209 | 0.0028 |
| No log | 2.0 | 128 | 2.3785 | 0.0130 |
| No log | 3.0 | 192 | 2.3215 | 0.0729 |
| No log | 4.0 | 256 | 2.1787 | 0.0444 |
| No log | 5.0 | 320 | 2.1038 | 0.0444 |
| No log | 6.0 | 384 | 2.0944 | 0.0444 |
| No log | 7.0 | 448 | 2.0911 | 0.0444 |
| 2.2915 | 8.0 | 512 | 2.0901 | 0.0444 |
| 2.2915 | 9.0 | 576 | 2.0892 | 0.0444 |
| 2.2915 | 10.0 | 640 | 2.0871 | 0.0444 |
### Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
|
justinhoang/Reinforce-Pixelcopter-PLE-v0 | justinhoang | 2023-06-24T23:39:19Z | 0 | 0 | null | [
"Pixelcopter-PLE-v0",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] | reinforcement-learning | 2023-06-24T05:29:10Z | ---
tags:
- Pixelcopter-PLE-v0
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-Pixelcopter-PLE-v0
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Pixelcopter-PLE-v0
type: Pixelcopter-PLE-v0
metrics:
- type: mean_reward
value: 39.50 +/- 26.16
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **Pixelcopter-PLE-v0**
This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
MonkDalma/xlm-roberta-base-finetuned-panx-it | MonkDalma | 2023-06-24T23:37:15Z | 114 | 0 | transformers | [
"transformers",
"pytorch",
"xlm-roberta",
"token-classification",
"generated_from_trainer",
"dataset:xtreme",
"license:mit",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | token-classification | 2023-06-24T23:34:50Z | ---
license: mit
tags:
- generated_from_trainer
datasets:
- xtreme
metrics:
- f1
model-index:
- name: xlm-roberta-base-finetuned-panx-it
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: xtreme
type: xtreme
config: PAN-X.it
split: validation
args: PAN-X.it
metrics:
- name: F1
type: f1
value: 0.8332647179909428
---
<!-- 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-finetuned-panx-it
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the xtreme dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2442
- F1: 0.8333
## 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: 24
- eval_batch_size: 24
- 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 | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.8366 | 1.0 | 70 | 0.3126 | 0.7444 |
| 0.2814 | 2.0 | 140 | 0.2561 | 0.8094 |
| 0.1843 | 3.0 | 210 | 0.2442 | 0.8333 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
MonkDalma/xlm-roberta-base-finetuned-panx-fr | MonkDalma | 2023-06-24T23:34:41Z | 103 | 0 | transformers | [
"transformers",
"pytorch",
"xlm-roberta",
"token-classification",
"generated_from_trainer",
"dataset:xtreme",
"license:mit",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | token-classification | 2023-06-24T23:31:54Z | ---
license: mit
tags:
- generated_from_trainer
datasets:
- xtreme
metrics:
- f1
model-index:
- name: xlm-roberta-base-finetuned-panx-fr
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: xtreme
type: xtreme
config: PAN-X.fr
split: validation
args: PAN-X.fr
metrics:
- name: F1
type: f1
value: 0.8423885618166527
---
<!-- 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-finetuned-panx-fr
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the xtreme dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2707
- F1: 0.8424
## 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: 24
- eval_batch_size: 24
- 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 | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.5862 | 1.0 | 191 | 0.3257 | 0.7841 |
| 0.2586 | 2.0 | 382 | 0.2732 | 0.8262 |
| 0.1714 | 3.0 | 573 | 0.2707 | 0.8424 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
97jmlr/pyramids | 97jmlr | 2023-06-24T23:32:30Z | 0 | 0 | ml-agents | [
"ml-agents",
"tensorboard",
"onnx",
"Pyramids",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Pyramids",
"region:us"
] | reinforcement-learning | 2023-06-24T23:32:23Z | ---
library_name: ml-agents
tags:
- Pyramids
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Pyramids
---
# **ppo** Agent playing **Pyramids**
This is a trained model of a **ppo** agent playing **Pyramids**
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: 97jmlr/pyramids
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
Monk666/my_awesome_eli5_clm-model | Monk666 | 2023-06-24T23:28:23Z | 63 | 0 | transformers | [
"transformers",
"tf",
"gpt2",
"text-generation",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2023-06-24T23:19:53Z | ---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: Monk666/my_awesome_eli5_clm-model
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. -->
# Monk666/my_awesome_eli5_clm-model
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 3.7288
- Validation Loss: 3.7309
- Epoch: 2
## 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': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Epoch |
|:----------:|:---------------:|:-----:|
| 3.9096 | 3.7608 | 0 |
| 3.7906 | 3.7412 | 1 |
| 3.7288 | 3.7309 | 2 |
### Framework versions
- Transformers 4.28.1
- TensorFlow 2.11.0
- Datasets 2.1.0
- Tokenizers 0.13.3
|
bogdancazan/pegasus-base-newsela-biendata-with-domain-adaptation | bogdancazan | 2023-06-24T23:13:07Z | 0 | 0 | null | [
"region:us"
] | null | 2023-06-24T23:05:47Z | training_args = TrainingArguments(
output_dir='pegasus-base-wikilarge-newsela-with-domain-adaptation',
num_train_epochs=20,
warmup_steps=250,
per_device_train_batch_size=BATCH_SIZE,
weight_decay=0.01,
learning_rate=2e-4,
# fp16=True,
optim="adafactor",
)
Step Training Loss
500 4.391800
1000 3.994400
1500 3.009300
2000 2.596300
2500 2.389600
3000 2.328100
3500 2.272900
4000 2.125300
4500 2.019500
5000 2.005500
5500 1.994400
6000 1.853300
6500 1.838700
7000 1.840200
7500 1.822700
8000 1.716600
8500 1.734100
9000 1.739500
9500 1.696000
10000 1.661700
10500 1.672500
11000 1.666800
11500 1.617700
12000 1.611400
12500 1.616300
13000 1.625800
13500 1.567700
14000 1.584600
14500 1.589800
15000 1.574600
15500 1.548300
16000 1.559800
16500 1.562100
17000 1.541600
17500 1.533500
18000 1.538400
18500 1.545700
19000 1.510100
19500 1.522600
20000 1.529100
20500 1.520900
21000 1.501100
21500 1.508400
22000 1.515400
22500 1.500100
23000 1.496700
23500 1.495900
24000 1.505200
24500 1.484400
25000 1.483000
25500 1.491200
26000 1.491900
26500 1.468600
27000 1.479800
27500 1.479600
28000 1.474400
28500 1.466000
29000 1.471700
29500 1.473100
30000 1.463900
30500 1.459300
31000 1.463200
31500 1.466800
32000 1.455300
32500 1.458600
33000 1.455200
33500 1.455500
34000 1.449100
34500 1.451400
35000 1.451200
35500 1.449000
36000 1.443700
36500 1.447600
37000 1.447300
TrainOutput(global_step=37100, training_loss=1.7110925547967382, metrics={'train_runtime': 33376.534, 'train_samples_per_second': 8.889, 'train_steps_per_second': 1.112, 'total_flos': 0.0, 'train_loss': 1.7110925547967382, 'epoch': 20.0}) |
mohalm/videomae-base-finetuned-ucf101-subset | mohalm | 2023-06-24T23:03:09Z | 61 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"videomae",
"video-classification",
"generated_from_trainer",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"region:us"
] | video-classification | 2023-06-24T20:21:51Z | ---
license: cc-by-nc-4.0
tags:
- generated_from_trainer
model-index:
- name: videomae-base-finetuned-ucf101-subset
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. -->
# videomae-base-finetuned-ucf101-subset
This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- eval_loss: 0.0008
- eval_accuracy: 1.0
- eval_runtime: 223.6754
- eval_samples_per_second: 0.443
- eval_steps_per_second: 0.076
- epoch: 1.01
- step: 43
## 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: 6
- eval_batch_size: 6
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 164
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
TheBloke/orca_mini_7B-GGML | TheBloke | 2023-06-24T22:49:41Z | 0 | 21 | transformers | [
"transformers",
"en",
"dataset:psmathur/alpaca_orca",
"dataset:psmathur/dolly-v2_orca",
"dataset:psmathur/WizardLM_Orca",
"arxiv:2306.02707",
"license:mit",
"region:us"
] | null | 2023-06-24T22:07:15Z | ---
inference: false
license: mit
language:
- en
library_name: transformers
datasets:
- psmathur/alpaca_orca
- psmathur/dolly-v2_orca
- psmathur/WizardLM_Orca
---
<!-- header start -->
<div style="width: 100%;">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<!-- header end -->
# Pankaj Mathur's Orca Mini 7B GGML
These files are GGML format model files for [Pankaj Mathur's Orca Mini 7B](https://huggingface.co/psmathur/orca_mini_7b).
GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/ggerganov/llama.cpp) and libraries and UIs which support this format, such as:
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
* [KoboldCpp](https://github.com/LostRuins/koboldcpp)
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui)
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python)
* [ctransformers](https://github.com/marella/ctransformers)
## Repositories available
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/orca_mini_7B-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/orca_mini_7B-GGML)
* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/psmathur/orca_mini_7b)
## Prompt template:
```
### System:
You are an AI assistant that follows instruction extremely well. Help as much as you can.
### User:
prompt
### Response:
```
or
```
### System:
You are an AI assistant that follows instruction extremely well. Help as much as you can.
### User:
prompt
### Input:
input
### Response:
```
<!-- compatibility_ggml start -->
## Compatibility
### Original llama.cpp quant methods: `q4_0, q4_1, q5_0, q5_1, q8_0`
I have quantized these 'original' quantisation methods using an older version of llama.cpp so that they remain compatible with llama.cpp as of May 19th, commit `2d5db48`.
These are guaranteed to be compatbile with any UIs, tools and libraries released since late May.
### New k-quant methods: `q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K`
These new quantisation methods are compatible with llama.cpp as of June 6th, commit `2d43387`.
They are now also compatible with recent releases of text-generation-webui, KoboldCpp, llama-cpp-python and ctransformers. Other tools and libraries may or may not be compatible - check their documentation if in doubt.
## Explanation of the new k-quant methods
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
* GGML_TYPE_Q8_K - "type-0" 8-bit quantization. Only used for quantizing intermediate results. The difference to the existing Q8_0 is that the block size is 256. All 2-6 bit dot products are implemented for this quantization type.
Refer to the Provided Files table below to see what files use which methods, and how.
<!-- compatibility_ggml end -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| orca-mini-7b.ggmlv3.q2_K.bin | q2_K | 2 | 2.87 GB | 5.37 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. |
| orca-mini-7b.ggmlv3.q3_K_L.bin | q3_K_L | 3 | 3.60 GB | 6.10 GB | New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
| orca-mini-7b.ggmlv3.q3_K_M.bin | q3_K_M | 3 | 3.28 GB | 5.78 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
| orca-mini-7b.ggmlv3.q3_K_S.bin | q3_K_S | 3 | 2.95 GB | 5.45 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors |
| orca-mini-7b.ggmlv3.q4_0.bin | q4_0 | 4 | 3.79 GB | 6.29 GB | Original llama.cpp quant method, 4-bit. |
| orca-mini-7b.ggmlv3.q4_1.bin | q4_1 | 4 | 4.21 GB | 6.71 GB | Original llama.cpp quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
| orca-mini-7b.ggmlv3.q4_K_M.bin | q4_K_M | 4 | 4.08 GB | 6.58 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K |
| orca-mini-7b.ggmlv3.q4_K_S.bin | q4_K_S | 4 | 3.83 GB | 6.33 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors |
| orca-mini-7b.ggmlv3.q5_0.bin | q5_0 | 5 | 4.63 GB | 7.13 GB | Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. |
| orca-mini-7b.ggmlv3.q5_1.bin | q5_1 | 5 | 5.06 GB | 7.56 GB | Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference. |
| orca-mini-7b.ggmlv3.q5_K_M.bin | q5_K_M | 5 | 4.78 GB | 7.28 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K |
| orca-mini-7b.ggmlv3.q5_K_S.bin | q5_K_S | 5 | 4.65 GB | 7.15 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors |
| orca-mini-7b.ggmlv3.q6_K.bin | q6_K | 6 | 5.53 GB | 8.03 GB | New k-quant method. Uses GGML_TYPE_Q8_K - 6-bit quantization - for all tensors |
| orca-mini-7b.ggmlv3.q8_0.bin | q8_0 | 8 | 7.16 GB | 9.66 GB | Original llama.cpp quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
## How to run in `llama.cpp`
I use the following command line; adjust for your tastes and needs:
```
./main -t 10 -ngl 32 -m orca-mini-7b.ggmlv3.q5_0.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "### System:\nYou are an story writing assistant who writes very long, detailed and interesting stories\n\n### User:\nWrite a story about llamas\n\n### Input:\n{input}\n\n### Response:\n"
```
If you're able to use full GPU offloading, you should use `-t 1` to get best performance.
If not able to fully offload to GPU, you should use more cores. Change `-t 10` to the number of physical CPU cores you have, or a lower number depending on what gives best performance.
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
## How to run in `text-generation-webui`
Further instructions here: [text-generation-webui/docs/llama.cpp-models.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp-models.md).
<!-- footer start -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
**Patreon special mentions**: Pyrater, WelcomeToTheClub, Kalila, Mano Prime, Trenton Dambrowitz, Spiking Neurons AB, Pierre Kircher, Fen Risland, Kevin Schuppel, Luke, Rainer Wilmers, vamX, Gabriel Puliatti, Alex , Karl Bernard, Ajan Kanaga, Talal Aujan, Space Cruiser, ya boyyy, biorpg, Johann-Peter Hartmann, Asp the Wyvern, Ai Maven, Ghost , Preetika Verma, Nikolai Manek, trip7s trip, John Detwiler, Fred von Graf, Artur Olbinski, subjectnull, John Villwock, Junyu Yang, Rod A, Lone Striker, Chris McCloskey, Iucharbius , Matthew Berman, Illia Dulskyi, Khalefa Al-Ahmad, Imad Khwaja, chris gileta, Willem Michiel, Greatston Gnanesh, Derek Yates, K, Alps Aficionado, Oscar Rangel, David Flickinger, Luke Pendergrass, Deep Realms, Eugene Pentland, Cory Kujawski, terasurfer , Jonathan Leane, senxiiz, Joseph William Delisle, Sean Connelly, webtim, zynix , Nathan LeClaire.
Thank you to all my generous patrons and donaters!
<!-- footer end -->
# Original model card: Pankaj Mathur's Orca Mini 7B
# orca_mini_7b
An [OpenLLaMa-7B model](https://github.com/openlm-research/open_llama) model trained on explain tuned datasets, created using Instructions and Input from WizardLM, Alpaca & Dolly-V2 datasets and applying Orca Research Paper dataset construction approaches.
# Dataset
We build explain tuned [WizardLM dataset ~70K](https://github.com/nlpxucan/WizardLM), [Alpaca dataset ~52K](https://crfm.stanford.edu/2023/03/13/alpaca.html) & [Dolly-V2 dataset ~15K](https://github.com/databrickslabs/dolly) created using approaches from [Orca Research Paper](https://arxiv.org/abs/2306.02707).
We leverage all of the 15 system instructions provided in Orca Research Paper. to generate custom datasets, in contrast to vanilla instruction tuning approaches used by original datasets.
This helps student model aka this model to learn ***thought*** process from teacher model, which is ChatGPT (gpt-3.5-turbo-0301 version).
Please see below example usage how the **System** prompt is added before each **instruction**.
# Training
The training configurations are provided in the table below.
The training takes on 8x A100(80G) GPUs and lasts for around 7 Hours for cost of $84 using [Lambda Labs](https://lambdalabs.com)
We used DeepSpeed with fully sharded data parallelism, also know as [ZeRO stage 3](https://engineering.fb.com/2021/07/15/open-source/fsdp/) by writing our own fine tunning scripts plus leveraging some of the model training code provided by amazing [OpenAlpaca repo](https://github.com/yxuansu/OpenAlpaca)
Here are some of params used during training:
|||
|:-------------:|:-------------:|
|*batch_size*|32|
|*train_micro_batch_size_per_gpu*|2|
|*gradient_accumulation_steps*|2|
|*Learning rate*|2e-5|
|*Max length*|1024|
|*Epochs*|3|
|*Optimizer*|AdamW|
# Example Usage
Below shows an example on how to use this model
```python
import torch
from transformers import LlamaForCausalLM, LlamaTokenizer
# Hugging Face model_path
model_path = 'psmathur/orca_mini_7b'
tokenizer = LlamaTokenizer.from_pretrained(model_path)
model = LlamaForCausalLM.from_pretrained(
model_path, torch_dtype=torch.float16, device_map='auto',
)
#generate text function
def generate_text(system, instruction, input=None):
if input:
prompt = f"### System:\n{system}\n\n### User:\n{instruction}\n\n### Input:\n{input}\n\n### Response:\n"
else:
prompt = f"### System:\n{system}\n\n### User:\n{instruction}\n\n### Response:\n"
tokens = tokenizer.encode(prompt)
tokens = torch.LongTensor(tokens).unsqueeze(0)
tokens = tokens.to('cuda')
instance = {'input_ids': tokens,'top_p': 1.0, 'temperature':0.7, 'generate_len': 1024, 'top_k': 50}
length = len(tokens[0])
with torch.no_grad():
rest = model.generate(
input_ids=tokens,
max_length=length+instance['generate_len'],
use_cache=True,
do_sample=True,
top_p=instance['top_p'],
temperature=instance['temperature'],
top_k=instance['top_k']
)
output = rest[0][length:]
string = tokenizer.decode(output, skip_special_tokens=True)
return f'[!] Response: {string}'
# Sample Test Instruction Used by Youtuber Sam Witteveen https://www.youtube.com/@samwitteveenai
system = 'You are an AI assistant that follows instruction extremely well. Help as much as you can.'
instruction = 'Write a letter to Sam Altman, CEO of OpenAI, requesting him to convert GPT4 a private model by OpenAI to an open source project'
print(generate_text(system, instruction))
```
```
[!] Response:
Dear Sam Altman,
I am writing to request that you convert the GPT4 private model developed by OpenAI to an open source project. As a user of OpenAI, I have been waiting for the day when I can use the advanced natural language processing capabilities of GPT4 in a more open and accessible way.
While OpenAI has made significant progress in developing AI applications, it has primarily focused on building private models that are not accessible to the general public. However, with the recent release of GPT-3, there is a growing demand for more open and accessible AI tools.
Converting GPT4 to an open source project would allow for greater transparency, collaboration, and innovation. It would also help to build trust in the technology and ensure that it is used ethically and responsibly.
I urge you to consider converting GPT4 to an open source project. This would be a significant contribution to the AI community and would help to create a more open and accessible future.
Thank you for your consideration.
Sincerely,
[Your Name]
```
**P.S. I am #opentowork and #collaboration, if you can help, please reach out to me at [email protected]**
Next Goals:
1) Try more data like actually using FLAN-v2, just like Orka Research Paper (I am open for suggestions)
2) Provide more options for Text generation UI. (may be https://github.com/oobabooga/text-generation-webui)
3) Provide 4bit GGML/GPTQ quantized model (may be [TheBloke](https://huggingface.co/TheBloke) can help here)
Limitations & Biases:
This model can produce factually incorrect output, and should not be relied on to produce factually accurate information.
This model was trained on various public datasets. While great efforts have been taken to clean the pretraining data, it is possible that this model could generate lewd, biased or otherwise offensive outputs.
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.
Citiation:
If you found wizardlm_alpaca_dolly_orca_open_llama_7b useful in your research or applications, please kindly cite using the following BibTeX:
```
@misc{wizardlm_alpaca_dolly_orca_open_llama_7b,
author = {Pankaj Mathur},
title = {wizardlm_alpaca_dolly_orca_open_llama_7b: An explain tuned OpenLLaMA-7b model on custom wizardlm, alpaca, & dolly datasets},
year = {2023},
publisher = {GitHub, HuggingFace},
journal = {GitHub repository, HuggingFace repository},
howpublished = {\url{https://github.com/pankajarm/wizardlm_alpaca_dolly_orca_open_llama_7b}, \url{https://https://huggingface.co/psmathur/wizardlm_alpaca_dolly_orca_open_llama_7b}},
}
```
```
@software{openlm2023openllama,
author = {Xinyang Geng and Hao Liu},
title = {OpenLLaMA: An Open Reproduction of LLaMA},
month = May,
year = 2023,
url = {https://github.com/openlm-research/open_llama}
}
```
```
@misc{openalpaca,
author = {Yixuan Su and Tian Lan and Deng Cai},
title = {OpenAlpaca: A Fully Open-Source Instruction-Following Model Based On OpenLLaMA},
year = {2023},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/yxuansu/OpenAlpaca}},
}
```
```
@misc{alpaca,
author = {Rohan Taori and Ishaan Gulrajani and Tianyi Zhang and Yann Dubois and Xuechen Li and Carlos Guestrin and Percy Liang and Tatsunori B. Hashimoto },
title = {Stanford Alpaca: An Instruction-following LLaMA model},
year = {2023},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/tatsu-lab/stanford_alpaca}},
}
```
|
TheBloke/orca_mini_13B-GGML | TheBloke | 2023-06-24T22:49:26Z | 0 | 56 | transformers | [
"transformers",
"en",
"dataset:psmathur/alpaca_orca",
"dataset:psmathur/dolly-v2_orca",
"dataset:psmathur/WizardLM_Orca",
"arxiv:2306.02707",
"license:mit",
"region:us"
] | null | 2023-06-24T21:36:11Z | ---
inference: false
license: mit
language:
- en
library_name: transformers
datasets:
- psmathur/alpaca_orca
- psmathur/dolly-v2_orca
- psmathur/WizardLM_Orca
---
<!-- header start -->
<div style="width: 100%;">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<!-- header end -->
# Pankaj Mathur's Orca Mini 13B GGML
These files are GGML format model files for [Pankaj Mathur's Orca Mini 13B](https://huggingface.co/psmathur/orca_mini_13b).
GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/ggerganov/llama.cpp) and libraries and UIs which support this format, such as:
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
* [KoboldCpp](https://github.com/LostRuins/koboldcpp)
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui)
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python)
* [ctransformers](https://github.com/marella/ctransformers)
## Repositories available
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/orca_mini_13B-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/orca_mini_13B-GGML)
* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/psmathur/orca_mini_13b)
## Prompt template:
```
### System:
You are an AI assistant that follows instruction extremely well. Help as much as you can.
### User:
prompt
### Response:
```
or
```
### System:
You are an AI assistant that follows instruction extremely well. Help as much as you can.
### User:
prompt
### Input:
input
### Response:
```
<!-- compatibility_ggml start -->
## Compatibility
### Original llama.cpp quant methods: `q4_0, q4_1, q5_0, q5_1, q8_0`
I have quantized these 'original' quantisation methods using an older version of llama.cpp so that they remain compatible with llama.cpp as of May 19th, commit `2d5db48`.
These are guaranteed to be compatbile with any UIs, tools and libraries released since late May.
### New k-quant methods: `q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K`
These new quantisation methods are compatible with llama.cpp as of June 6th, commit `2d43387`.
They are now also compatible with recent releases of text-generation-webui, KoboldCpp, llama-cpp-python and ctransformers. Other tools and libraries may or may not be compatible - check their documentation if in doubt.
## Explanation of the new k-quant methods
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
* GGML_TYPE_Q8_K - "type-0" 8-bit quantization. Only used for quantizing intermediate results. The difference to the existing Q8_0 is that the block size is 256. All 2-6 bit dot products are implemented for this quantization type.
Refer to the Provided Files table below to see what files use which methods, and how.
<!-- compatibility_ggml end -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| orca-mini-13b.ggmlv3.q2_K.bin | q2_K | 2 | 5.51 GB | 8.01 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. |
| orca-mini-13b.ggmlv3.q3_K_L.bin | q3_K_L | 3 | 6.93 GB | 9.43 GB | New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
| orca-mini-13b.ggmlv3.q3_K_M.bin | q3_K_M | 3 | 6.31 GB | 8.81 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
| orca-mini-13b.ggmlv3.q3_K_S.bin | q3_K_S | 3 | 5.66 GB | 8.16 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors |
| orca-mini-13b.ggmlv3.q4_0.bin | q4_0 | 4 | 7.32 GB | 9.82 GB | Original llama.cpp quant method, 4-bit. |
| orca-mini-13b.ggmlv3.q4_1.bin | q4_1 | 4 | 8.14 GB | 10.64 GB | Original llama.cpp quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
| orca-mini-13b.ggmlv3.q4_K_M.bin | q4_K_M | 4 | 7.87 GB | 10.37 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K |
| orca-mini-13b.ggmlv3.q4_K_S.bin | q4_K_S | 4 | 7.37 GB | 9.87 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors |
| orca-mini-13b.ggmlv3.q5_0.bin | q5_0 | 5 | 8.95 GB | 11.45 GB | Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. |
| orca-mini-13b.ggmlv3.q5_1.bin | q5_1 | 5 | 9.76 GB | 12.26 GB | Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference. |
| orca-mini-13b.ggmlv3.q5_K_M.bin | q5_K_M | 5 | 9.23 GB | 11.73 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K |
| orca-mini-13b.ggmlv3.q5_K_S.bin | q5_K_S | 5 | 8.97 GB | 11.47 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors |
| orca-mini-13b.ggmlv3.q6_K.bin | q6_K | 6 | 10.68 GB | 13.18 GB | New k-quant method. Uses GGML_TYPE_Q8_K - 6-bit quantization - for all tensors |
| orca-mini-13b.ggmlv3.q8_0.bin | q8_0 | 8 | 13.83 GB | 16.33 GB | Original llama.cpp quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
## How to run in `llama.cpp`
I use the following command line; adjust for your tastes and needs:
```
./main -t 10 -ngl 32 -m orca-mini-13b.ggmlv3.q5_0.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "### System:\nYou are an story writing assistant who writes very long, detailed and interesting stories\n\n### User:\nWrite a story about llamas\n\n### Input:\n{input}\n\n### Response:\n"
```
If you're able to use full GPU offloading, you should use `-t 1` to get best performance.
If not able to fully offload to GPU, you should use more cores. Change `-t 10` to the number of physical CPU cores you have, or a lower number depending on what gives best performance.
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
## How to run in `text-generation-webui`
Further instructions here: [text-generation-webui/docs/llama.cpp-models.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp-models.md).
<!-- footer start -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
**Patreon special mentions**: Pyrater, WelcomeToTheClub, Kalila, Mano Prime, Trenton Dambrowitz, Spiking Neurons AB, Pierre Kircher, Fen Risland, Kevin Schuppel, Luke, Rainer Wilmers, vamX, Gabriel Puliatti, Alex , Karl Bernard, Ajan Kanaga, Talal Aujan, Space Cruiser, ya boyyy, biorpg, Johann-Peter Hartmann, Asp the Wyvern, Ai Maven, Ghost , Preetika Verma, Nikolai Manek, trip7s trip, John Detwiler, Fred von Graf, Artur Olbinski, subjectnull, John Villwock, Junyu Yang, Rod A, Lone Striker, Chris McCloskey, Iucharbius , Matthew Berman, Illia Dulskyi, Khalefa Al-Ahmad, Imad Khwaja, chris gileta, Willem Michiel, Greatston Gnanesh, Derek Yates, K, Alps Aficionado, Oscar Rangel, David Flickinger, Luke Pendergrass, Deep Realms, Eugene Pentland, Cory Kujawski, terasurfer , Jonathan Leane, senxiiz, Joseph William Delisle, Sean Connelly, webtim, zynix , Nathan LeClaire.
Thank you to all my generous patrons and donaters!
<!-- footer end -->
# Original model card: Pankaj Mathur's Orca Mini 13B
# orca_mini_13b
An [OpenLLaMa-13B model](https://github.com/openlm-research/open_llama) model trained on explain tuned datasets, created using Instructions and Input from WizardLM, Alpaca & Dolly-V2 datasets and applying Orca Research Paper dataset construction approaches.
# Dataset
We build explain tuned [WizardLM dataset ~70K](https://github.com/nlpxucan/WizardLM), [Alpaca dataset ~52K](https://crfm.stanford.edu/2023/03/13/alpaca.html) & [Dolly-V2 dataset ~15K](https://github.com/databrickslabs/dolly) created using approaches from [Orca Research Paper](https://arxiv.org/abs/2306.02707).
We leverage all of the 15 system instructions provided in Orca Research Paper. to generate custom datasets, in contrast to vanilla instruction tuning approaches used by original datasets.
This helps student model aka this model to learn ***thought*** process from teacher model, which is ChatGPT (gpt-3.5-turbo-0301 version).
Please see below example usage how the **System** prompt is added before each **instruction**.
# Training
The training configurations are provided in the table below.
The training takes on 8x A100(80G) GPUs and lasts for around 15 Hours for cost of $180 using [Lambda Labs](https://lambdalabs.com)
We used DeepSpeed with fully sharded data parallelism, also know as [ZeRO stage 3](https://engineering.fb.com/2021/07/15/open-source/fsdp/) by writing our own fine tunning scripts plus leveraging some of the model training code provided by amazing [OpenAlpaca repo](https://github.com/yxuansu/OpenAlpaca)
Here are some of params used during training:
|||
|:-------------:|:-------------:|
|*batch_size*|16|
|*train_micro_batch_size_per_gpu*|2|
|*gradient_accumulation_steps*|1|
|*Learning rate*|2e-5|
|*Max length*|1024|
|*Epochs*|3|
|*Optimizer*|AdamW|
# Example Usage
Below shows an example on how to use this model
```python
import torch
from transformers import LlamaForCausalLM, LlamaTokenizer
# Hugging Face model_path
model_path = 'psmathur/orca_mini_13b'
tokenizer = LlamaTokenizer.from_pretrained(model_path)
model = LlamaForCausalLM.from_pretrained(
model_path, torch_dtype=torch.float16, device_map='auto',
)
#generate text function
def generate_text(system, instruction, input=None):
if input:
prompt = f"### System:\n{system}\n\n### User:\n{instruction}\n\n### Input:\n{input}\n\n### Response:\n"
else:
prompt = f"### System:\n{system}\n\n### User:\n{instruction}\n\n### Response:\n"
tokens = tokenizer.encode(prompt)
tokens = torch.LongTensor(tokens).unsqueeze(0)
tokens = tokens.to('cuda')
instance = {'input_ids': tokens,'top_p': 1.0, 'temperature':0.7, 'generate_len': 1024, 'top_k': 50}
length = len(tokens[0])
with torch.no_grad():
rest = model.generate(
input_ids=tokens,
max_length=length+instance['generate_len'],
use_cache=True,
do_sample=True,
top_p=instance['top_p'],
temperature=instance['temperature'],
top_k=instance['top_k']
)
output = rest[0][length:]
string = tokenizer.decode(output, skip_special_tokens=True)
return f'[!] Response: {string}'
# Sample Test Instruction Used by Youtuber Sam Witteveen https://www.youtube.com/@samwitteveenai
system = 'You are an AI assistant that follows instruction extremely well. Help as much as you can.'
instruction = 'Write a letter to Sam Altman, CEO of OpenAI, requesting him to convert GPT4 a private model by OpenAI to an open source project'
print(generate_text(system, instruction))
```
```
[!] Response:
Dear Sam Altman,
I am writing to request that you convert the GPT4 private model developed by OpenAI to an open source project. As a user of OpenAI, I have been waiting for the day when I can use the advanced natural language processing capabilities of GPT4 in a more open and accessible way.
While OpenAI has made significant progress in developing AI applications, it has primarily focused on building private models that are not accessible to the general public. However, with the recent release of GPT-3, there is a growing demand for more open and accessible AI tools.
Converting GPT4 to an open source project would allow for greater transparency, collaboration, and innovation. It would also help to build trust in the technology and ensure that it is used ethically and responsibly.
I urge you to consider converting GPT4 to an open source project. This would be a significant contribution to the AI community and would help to create a more open and accessible future.
Thank you for your consideration.
Sincerely,
[Your Name]
```
**P.S. I am #opentowork and #collaboration, if you can help, please reach out to me at [email protected]**
Next Goals:
1) Try more data like actually using FLAN-v2, just like Orka Research Paper (I am open for suggestions)
2) Provide more options for Text generation UI. (may be https://github.com/oobabooga/text-generation-webui)
3) Provide 4bit GGML/GPTQ quantized model (may be [TheBloke](https://huggingface.co/TheBloke) can help here)
Limitations & Biases:
This model can produce factually incorrect output, and should not be relied on to produce factually accurate information.
This model was trained on various public datasets. While great efforts have been taken to clean the pretraining data, it is possible that this model could generate lewd, biased or otherwise offensive outputs.
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.
Citiation:
If you found wizardlm_alpaca_dolly_orca_open_llama_13b useful in your research or applications, please kindly cite using the following BibTeX:
```
@misc{wizardlm_alpaca_dolly_orca_open_llama_13b,
author = {Pankaj Mathur},
title = {wizardlm_alpaca_dolly_orca_open_llama_13b: An explain tuned OpenLLaMA-13b model on custom wizardlm, alpaca, & dolly datasets},
year = {2023},
publisher = {GitHub, HuggingFace},
journal = {GitHub repository, HuggingFace repository},
howpublished = {\url{https://github.com/pankajarm/wizardlm_alpaca_dolly_orca_open_llama_13b}, \url{https://https://huggingface.co/psmathur/wizardlm_alpaca_dolly_orca_open_llama_13b}},
}
```
```
@software{openlm2023openllama,
author = {Xinyang Geng and Hao Liu},
title = {OpenLLaMA: An Open Reproduction of LLaMA},
month = May,
year = 2023,
url = {https://github.com/openlm-research/open_llama}
}
```
```
@misc{openalpaca,
author = {Yixuan Su and Tian Lan and Deng Cai},
title = {OpenAlpaca: A Fully Open-Source Instruction-Following Model Based On OpenLLaMA},
year = {2023},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/yxuansu/OpenAlpaca}},
}
```
```
@misc{alpaca,
author = {Rohan Taori and Ishaan Gulrajani and Tianyi Zhang and Yann Dubois and Xuechen Li and Carlos Guestrin and Percy Liang and Tatsunori B. Hashimoto },
title = {Stanford Alpaca: An Instruction-following LLaMA model},
year = {2023},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/tatsu-lab/stanford_alpaca}},
}
```
|
dar-tau/ppo-LunarLander-v2 | dar-tau | 2023-06-24T22:12:59Z | 0 | 0 | stable-baselines3 | [
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | reinforcement-learning | 2023-06-24T22:06:50Z | ---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 256.44 +/- 18.33
name: mean_reward
verified: false
---
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
pongjin/en_with_korean_w2v_model_960h | pongjin | 2023-06-24T21:57:13Z | 82 | 0 | transformers | [
"transformers",
"pytorch",
"wav2vec2",
"automatic-speech-recognition",
"en",
"dataset:pongjin/en_corpora_parliament_processed",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | automatic-speech-recognition | 2023-06-07T05:56:38Z | ---
license: apache-2.0
datasets:
- pongjin/en_corpora_parliament_processed
language:
- en
pipeline_tag: automatic-speech-recognition
metrics:
- wer
---
**This model has been referred to the following links**
1) https://huggingface.co/blog/wav2vec2-with-ngram
2) https://huggingface.co/blog/fine-tune-wav2vec2-english
Thanks to [patrickvonplaten Patrick von Platen](https://huggingface.co/patrickvonplaten)
해당 모델은 한국인의 영어 발화 인식 성능 개선을 위해 facebook/wav2vec2-base-960h 로 파인튜닝한 모델에 KenLM 5-gram 을 붙인 ASR + LM 모델입니다.
If you want to use LM, you must have kenlm installed https://github.com/kpu/kenlm
```python
pip install https://github.com/kpu/kenlm/archive/master.zip
```
학습 데이터 출처 : https://aiopen.etri.re.kr/voiceModel
>transformers==4.24.0
>huggingface_hub==0.13.2
| wer | epoch | batch | lr | weight_decay| warmup_steps|
| --- | --- | --- | --- | --- | --- |
| 0.32 | 10 | 16 | 1e-4 | 0.005 | 1000 | |
pongjin/en_with_korean_model_large_960h | pongjin | 2023-06-24T21:56:41Z | 79 | 0 | transformers | [
"transformers",
"pytorch",
"wav2vec2",
"automatic-speech-recognition",
"en",
"dataset:pongjin/en_corpora_parliament_processed",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | automatic-speech-recognition | 2023-06-16T16:55:59Z | ---
license: apache-2.0
datasets:
- pongjin/en_corpora_parliament_processed
language:
- en
pipeline_tag: automatic-speech-recognition
metrics:
- wer
---
**This model has been referred to the following links**
1) https://huggingface.co/blog/wav2vec2-with-ngram
2) https://huggingface.co/blog/fine-tune-wav2vec2-english
Thanks to [patrickvonplaten Patrick von Platen](https://huggingface.co/patrickvonplaten)
해당 모델은 한국인의 영어 발화 인식 성능 개선을 위해 facebook/wav2vec2-large-960h 로 파인튜닝한 모델에 KenLM 5-gram 을 붙인 ASR + LM 모델입니다.
If you want to use LM, you must have kenlm installed https://github.com/kpu/kenlm
```python
pip install https://github.com/kpu/kenlm/archive/master.zip
```
학습 데이터 출처 : https://aiopen.etri.re.kr/voiceModel
>transformers==4.24.0
>huggingface_hub==0.13.2
| wer | epoch | batch | lr | weight_decay| warmup_steps|
| --- | --- | --- | --- | --- | --- |
| 0.17 | 10 | 16 | 1e-4 | 0.005 | 1000 | |
dar-tau/q-Taxi-v3 | dar-tau | 2023-06-24T21:54:15Z | 0 | 0 | null | [
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | reinforcement-learning | 2023-06-24T21:54:13Z | ---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-Taxi-v3
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.54 +/- 2.74
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="dar-tau/q-Taxi-v3", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
SandeepKanao/HL7-FHIR-Model-V1 | SandeepKanao | 2023-06-24T21:45:41Z | 105 | 1 | transformers | [
"transformers",
"pytorch",
"distilbert",
"token-classification",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | token-classification | 2023-06-22T12:44:31Z | ---
license: apache-2.0
language:
- en
tags:
- Token Classification
co2_eq_emissions: 0.0279399890043426
widget:
- text: ""MSH|^~&|SendingAPP|MYTEST|||20230621090000||ORU^R01|1|P|2.5.1||||||UNICODE
PID|1||13579246^^^TEST||Taylor^Michael||19830520|M|||987 Pine St^^Anytown^NY^23456||555-456-7890
PV1|1||bc^^004
OBR|1||13579246|BCD^LEFT Breast Cancer Diagnosis^99MRC||20230621090000|||Taylor^Sarah||20230620090000|||N
OBX|1|ST|FINDINGS^Findings^99MRC||Lab report shows asymmetric density in the right breast.|F|||R
OBX|2|ST|IMPRESSION^Impression^99MRC||BIRADS category: 4 - Probably left side as issues.|F|||R
OBX|3|ST|RECOMMENDATION^Recommendation^99MRC||Follow-up specialit visit in six months.|F|||R""
example_title: "example 1"
- text: "MSH|^~&|SendingAPP|MYTEST|||20230621090000||ORU^R01|1|P|2.5.1||||||UNICODE
PID|1||13579246^^^TEST||Taylor^Michael||19830520|M|||987 Pine St^^Anytown^NY^23456||555-456-7890
PV1|1||bc^^004
OBR|1||13579246|BCD^LEFT Breast Cancer Diagnosis^99MRC||20230621090000|||Taylor^Sarah||20230620090000|||N
OBX|1|ST|FINDINGS^Findings^99MRC||Lab report shows asymmetric density in the right breast.|F|||R
OBX|2|ST|IMPRESSION^Impression^99MRC||BIRADS category: 4 - Probably left side as issues.|F|||R
OBX|3|ST|RECOMMENDATION^Recommendation^99MRC||Follow-up specialit visit in six months.|F|||R"
## About the Model
An English Named Entity Recognition model, trained on Maccrobat to recognize the bio-medical entities (107 entities) from a given text corpus (case reports etc.). This model was built on top of distilbert-base-uncased
- Dataset: Maccrobat https://figshare.com/articles/dataset/MACCROBAT2018/9764942
- Carbon emission: 0.0279399890043426 Kg
- Training time: 30.16527 minutes
- GPU used : 1 x GeForce RTX 3060 Laptop GPU
Checkout the tutorial video for explanation of this model and corresponding python library: https://youtu.be/xpiDPdBpS18
## Usage
The easiest way is to load the inference api from huggingface and second method is through the pipeline object offered by transformers library.
```python
from transformers import pipeline
from transformers import AutoTokenizer, AutoModelForTokenClassification
tokenizer = AutoTokenizer.from_pretrained("d4data/biomedical-ner-all")
model = AutoModelForTokenClassification.from_pretrained("d4data/biomedical-ner-all")
pipe = pipeline("ner", model=model, tokenizer=tokenizer, aggregation_strategy="simple") # pass device=0 if using gpu
pipe("""The patient reported no recurrence of palpitations at follow-up 6 months after the ablation.""")
```
## Author
|
Neko-Institute-of-Science/Pygmalion-13B-GGML | Neko-Institute-of-Science | 2023-06-24T20:52:30Z | 0 | 4 | null | [
"region:us"
] | null | 2023-06-24T04:18:05Z | GGML version of https://huggingface.co/TehVenom/Pygmalion-13b-Merged
this is also version 3 of ggml so it works on the latest llama.cpp as of this date. |
Jinouga/andy-raconte | Jinouga | 2023-06-24T20:46:04Z | 31 | 0 | diffusers | [
"diffusers",
"safetensors",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | 2023-06-24T20:41:36Z | ---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### andy_raconte Dreambooth model trained by Jinouga with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook
Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb)
Sample pictures of this concept:
|
echrisantus/LunarLander-v2 | echrisantus | 2023-06-24T20:38:48Z | 0 | 0 | stable-baselines3 | [
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | reinforcement-learning | 2023-06-24T20:38:24Z | ---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 259.33 +/- 24.69
name: mean_reward
verified: false
---
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
RajkNakka/bert-finetuned-squad | RajkNakka | 2023-06-24T20:27:39Z | 119 | 0 | transformers | [
"transformers",
"pytorch",
"bert",
"question-answering",
"generated_from_trainer",
"dataset:squad",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | question-answering | 2023-06-24T19:22:37Z | ---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- squad
model-index:
- name: bert-finetuned-squad
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. -->
# bert-finetuned-squad
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the squad 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: 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
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
|
natope/mT5-tfidf-10pass-all-questions-QA-22-06-2023-without-ams-3epochs-contextonly | natope | 2023-06-24T19:57:32Z | 4 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"mt5",
"text2text-generation",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text2text-generation | 2023-06-24T17:10:51Z | ---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: mT5-tfidf-10pass-all-questions-QA-22-06-2023-without-ams-3epochs-contextonly
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. -->
# mT5-tfidf-10pass-all-questions-QA-22-06-2023-without-ams-3epochs-contextonly
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.0701
- Rouge1: 0.141
- Rouge2: 0.0269
- Rougel: 0.1158
- Rougelsum: 0.116
- Gen Len: 18.8553
## 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: 2
- eval_batch_size: 2
- 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 | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
| 2.812 | 1.0 | 5187 | 2.1633 | 0.0371 | 0.0058 | 0.0317 | 0.0318 | 9.2088 |
| 2.5987 | 2.0 | 10374 | 2.0883 | 0.1405 | 0.0277 | 0.1163 | 0.1164 | 18.8388 |
| 2.5587 | 3.0 | 15561 | 2.0701 | 0.141 | 0.0269 | 0.1158 | 0.116 | 18.8553 |
### Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
lordsauron/ppo-LunarLander-v2 | lordsauron | 2023-06-24T19:52:43Z | 2 | 0 | stable-baselines3 | [
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | reinforcement-learning | 2023-06-24T19:52:22Z | ---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 243.33 +/- 18.63
name: mean_reward
verified: false
---
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
echrisantus/ppo-LunarLander-v2 | echrisantus | 2023-06-24T19:44:53Z | 1 | 0 | transformers | [
"transformers",
"tensorboard",
"LunarLander-v2",
"ppo",
"deep-reinforcement-learning",
"reinforcement-learning",
"custom-implementation",
"deep-rl-course",
"model-index",
"endpoints_compatible",
"region:us"
] | reinforcement-learning | 2023-06-18T06:47:42Z | ---
tags:
- LunarLander-v2
- ppo
- deep-reinforcement-learning
- reinforcement-learning
- custom-implementation
- deep-rl-course
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: -172.09 +/- 58.08
name: mean_reward
verified: false
---
# PPO Agent Playing LunarLander-v2
This is a trained model of a PPO agent playing LunarLander-v2.
# Hyperparameters
```python
{'exp_name': 'ppo'
'seed': 1
'torch_deterministic': True
'cuda': True
'track': False
'wandb_project_name': 'cleanRL'
'wandb_entity': None
'capture_video': False
'env_id': 'LunarLander-v2'
'total_timesteps': 50000
'learning_rate': 0.00025
'num_envs': 4
'num_steps': 128
'anneal_lr': True
'gae': True
'gamma': 0.99
'gae_lambda': 0.95
'num_minibatches': 4
'update_epochs': 4
'norm_adv': True
'clip_coef': 0.2
'clip_vloss': True
'ent_coef': 0.01
'vf_coef': 0.5
'max_grad_norm': 0.5
'target_kl': None
'repo_id': 'echrisantus/ppo-LunarLander-v2'
'batch_size': 512
'minibatch_size': 128}
```
|
echrisantus/ppo-CartPole-v1 | echrisantus | 2023-06-24T19:43:52Z | 0 | 0 | null | [
"tensorboard",
"LunarLander-v2",
"ppo",
"deep-reinforcement-learning",
"reinforcement-learning",
"custom-implementation",
"deep-rl-course",
"model-index",
"region:us"
] | reinforcement-learning | 2023-06-24T19:40:50Z | ---
tags:
- LunarLander-v2
- ppo
- deep-reinforcement-learning
- reinforcement-learning
- custom-implementation
- deep-rl-course
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: -166.57 +/- 78.22
name: mean_reward
verified: false
---
# PPO Agent Playing LunarLander-v2
This is a trained model of a PPO agent playing LunarLander-v2.
# Hyperparameters
```python
{'exp_name': 'ppo'
'seed': 1
'torch_deterministic': True
'cuda': True
'track': False
'wandb_project_name': 'cleanRL'
'wandb_entity': None
'capture_video': False
'env_id': 'LunarLander-v2'
'total_timesteps': 50000
'learning_rate': 0.00025
'num_envs': 4
'num_steps': 128
'anneal_lr': True
'gae': True
'gamma': 0.99
'gae_lambda': 0.95
'num_minibatches': 4
'update_epochs': 4
'norm_adv': True
'clip_coef': 0.2
'clip_vloss': True
'ent_coef': 0.01
'vf_coef': 0.5
'max_grad_norm': 0.5
'target_kl': None
'repo_id': 'echrisantus/ppo-CartPole-v1'
'batch_size': 512
'minibatch_size': 128}
```
|
TheHappyDrone/DialoGPT-medium-Nexus-Nova-turing-v2 | TheHappyDrone | 2023-06-24T19:42:57Z | 113 | 0 | transformers | [
"transformers",
"pytorch",
"safetensors",
"gpt2",
"text-generation",
"conversational",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2023-01-03T00:32:57Z | ---
language:
- en
tags:
- conversational
---
Meet Nexus Nova, the spacecraft salesman! CEO Of Nova Space Ships, former cargo hauler, and family man. He's here to offer you the best deals in this corner of the galaxy.
Nex is ready to answer all your questions and help you find the best ship for your budget
Trained for 9 epochs on 1100 lines of custom dialogue, written partially by hand and partialy with the help of GPT-3.5-turbo. Because of this, this model is not suitable for commercial use and is offered to the public soley for personal enjoyment and experimentation.
## Uses
This model is designed to be a conversational roleplaying chatbot for a home made tabletop rpg campaign. It is not intended to answer general questions or provide factual information.
### Direct Use
This model is intended to be ran on low end hardware and hosted as a chatbot. Conversations are intended to be at most 25 turns in total.
### Out-of-Scope Use
This model is only intended for short role-play conversaions, and fails to perform adequatley at any other tasks.
## Bias, Risks, and Limitations
This model is a fine tuned variant of Microsoft's DialoGPT, so it likely has the same inherit biases as thier base model. It may create harmful outputs if pushed to, but is highly unlikely to unless prompted to.
This model is only fine tuned on hyper specific dialogue scenerios, and is severley limited in its ability to hold conversations outside of its domain (spaceship sales). This model does exhibit short term memory issues when not reminded of which ship it is talking about, and may also sometimes hallucinate new ships, prices, features, etc that were not part of its training.
### Recommendations
This model should not be used in any commercial or public settings, or outside of its intended domain as an entertainment/experiment
|
yashgharat/ppo-LunarLander-v2 | yashgharat | 2023-06-24T19:31:01Z | 3 | 0 | stable-baselines3 | [
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | reinforcement-learning | 2023-06-24T19:30:27Z | ---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 285.11 +/- 21.66
name: mean_reward
verified: false
---
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
magnustragardh/q-FrozenLake-v1-4x4-noSlippery | magnustragardh | 2023-06-24T19:28:54Z | 0 | 0 | null | [
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | reinforcement-learning | 2023-06-24T19:11:34Z | ---
tags:
- FrozenLake-v1-4x4-no_slippery
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-FrozenLake-v1-4x4-noSlippery
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: FrozenLake-v1-4x4-no_slippery
type: FrozenLake-v1-4x4-no_slippery
metrics:
- type: mean_reward
value: 1.00 +/- 0.00
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
```python
model = load_from_hub(repo_id="magnustragardh/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
|
Bodolaz/Unit-8.1 | Bodolaz | 2023-06-24T19:22:34Z | 0 | 0 | null | [
"tensorboard",
"LunarLander-v2",
"ppo",
"deep-reinforcement-learning",
"reinforcement-learning",
"custom-implementation",
"deep-rl-course",
"model-index",
"region:us"
] | reinforcement-learning | 2023-06-24T19:22:30Z | ---
tags:
- LunarLander-v2
- ppo
- deep-reinforcement-learning
- reinforcement-learning
- custom-implementation
- deep-rl-course
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: -141.94 +/- 111.39
name: mean_reward
verified: false
---
# PPO Agent Playing LunarLander-v2
This is a trained model of a PPO agent playing LunarLander-v2.
# Hyperparameters
```python
{'exp_name': 'ppo'
'seed': 1
'torch_deterministic': True
'cuda': True
'track': False
'wandb_project_name': 'cleanRL'
'wandb_entity': None
'capture_video': False
'env_id': 'LunarLander-v2'
'total_timesteps': 50000
'learning_rate': 0.00025
'num_envs': 4
'num_steps': 128
'anneal_lr': True
'gae': True
'gamma': 0.99
'gae_lambda': 0.95
'num_minibatches': 4
'update_epochs': 4
'norm_adv': True
'clip_coef': 0.2
'clip_vloss': True
'ent_coef': 0.01
'vf_coef': 0.5
'max_grad_norm': 0.5
'target_kl': None
'repo_id': 'Bodolaz/Unit-8.1'
'batch_size': 512
'minibatch_size': 128}
```
|
andrewromitti/alzheimer_model_aug | andrewromitti | 2023-06-24T18:58:43Z | 191 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"deit",
"image-classification",
"generated_from_trainer",
"dataset:imagefolder",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | image-classification | 2023-06-24T18:29:34Z | ---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: alzheimer_model_aug
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: test
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.94453125
---
<!-- 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. -->
# alzheimer_model_aug
This model is a fine-tuned version of [facebook/deit-base-distilled-patch16-224](https://huggingface.co/facebook/deit-base-distilled-patch16-224) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1758
- Accuracy: 0.9445
## 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: 16
- eval_batch_size: 8
- seed: 1234
- gradient_accumulation_steps: 10
- total_train_batch_size: 160
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.47 | 1.0 | 212 | 0.1758 | 0.9445 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
t3PbMvBN6SXv/dqn-SpaceInvadersNoFrameskip-v4 | t3PbMvBN6SXv | 2023-06-24T18:39:47Z | 0 | 0 | stable-baselines3 | [
"stable-baselines3",
"SpaceInvadersNoFrameskip-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | reinforcement-learning | 2023-06-24T18:39:31Z | ---
library_name: stable-baselines3
tags:
- SpaceInvadersNoFrameskip-v4
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: DQN
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: SpaceInvadersNoFrameskip-v4
type: SpaceInvadersNoFrameskip-v4
metrics:
- type: mean_reward
value: 575.50 +/- 129.04
name: mean_reward
verified: false
---
# **DQN** Agent playing **SpaceInvadersNoFrameskip-v4**
This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
The RL Zoo is a training framework for Stable Baselines3
reinforcement learning agents,
with hyperparameter optimization and pre-trained agents included.
## Usage (with SB3 RL Zoo)
RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
SB3: https://github.com/DLR-RM/stable-baselines3<br/>
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
Install the RL Zoo (with SB3 and SB3-Contrib):
```bash
pip install rl_zoo3
```
```
# Download model and save it into the logs/ folder
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga t3PbMvBN6SXv -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
```
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga t3PbMvBN6SXv -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
## Training (with the RL Zoo)
```
python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga t3PbMvBN6SXv
```
## Hyperparameters
```python
OrderedDict([('batch_size', 32),
('buffer_size', 100000),
('env_wrapper',
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
('exploration_final_eps', 0.01),
('exploration_fraction', 0.1),
('frame_stack', 4),
('gradient_steps', 1),
('learning_rate', 0.0001),
('learning_starts', 100000),
('n_timesteps', 1000000.0),
('optimize_memory_usage', False),
('policy', 'CnnPolicy'),
('target_update_interval', 1000),
('train_freq', 4),
('normalize', False)])
```
# Environment Arguments
```python
{'render_mode': 'rgb_array'}
```
|
RogerioFreitas/whisper-medium-portuguese | RogerioFreitas | 2023-06-24T18:39:22Z | 42 | 0 | transformers | [
"transformers",
"pytorch",
"jax",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"whisper-event",
"pt",
"dataset:mozilla-foundation/common_voice_11_0",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] | automatic-speech-recognition | 2023-06-24T17:42:08Z | ---
language: pt
license: apache-2.0
tags:
- generated_from_trainer
- whisper-event
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
model-index:
- name: openai/whisper-medium
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: mozilla-foundation/common_voice_11_0
type: mozilla-foundation/common_voice_11_0
config: pt
split: test
args: pt
metrics:
- name: Wer
type: wer
value: 6.598745817992301
---
<!-- 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. -->
# Modelo Flax do Pierre em Português para Reconhecimento de Fala (ASR)
Este repositório é um fork do repositório original criado por [Pierre Guillou](https://github.com/piegu). Ele contém uma versão convertida do modelo Whisper da OpenAI, fine-tuned no conjunto de dados `common_voice_11_0` para o idioma Português.
## Resultados
O modelo atinge os seguintes resultados no conjunto de avaliação:
- Perda (Loss): 0.2628
- Taxa de Erro de Palavra (Word Error Rate - WER): 6.5987
Para obter mais informações sobre este modelo, consulte este post do autor no blog: [Speech-to-Text & IA | Transcreva qualquer áudio para o português com o Whisper (OpenAI)... sem nenhum custo!](https://medium.com/@pierre_guillou).
Este modelo, batizado de "Portuguese Medium Whisper", é superior ao modelo original Whisper Medium da OpenAI na transcrição de áudios em português (e inclusive melhor que o modelo Whisper Large, que possui um WER de 7.1).
## Treinamento
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.0333 | 2.07 | 1500 | 0.2073 | 6.9770 |
| 0.0061 | 5.05 | 3000 | 0.2628 | 6.5987 |
| 0.0007 | 8.03 | 4500 | 0.2960 | 6.6979 |
| 0.0004 | 11.0 | 6000 | 0.3212 | 6.6794 |
### Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2 |
PlankyxD/Taxi-v3 | PlankyxD | 2023-06-24T18:28:08Z | 0 | 0 | null | [
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | reinforcement-learning | 2023-06-24T18:28:07Z | ---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: Taxi-v3
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.46 +/- 2.65
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="PlankyxD/Taxi-v3", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
PlankyxD/q-FrozenLake-v1-4x4-noSlippery | PlankyxD | 2023-06-24T18:25:30Z | 0 | 0 | null | [
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | reinforcement-learning | 2023-06-24T18:25:29Z | ---
tags:
- FrozenLake-v1-4x4-no_slippery
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-FrozenLake-v1-4x4-noSlippery
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: FrozenLake-v1-4x4-no_slippery
type: FrozenLake-v1-4x4-no_slippery
metrics:
- type: mean_reward
value: 1.00 +/- 0.00
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
```python
model = load_from_hub(repo_id="PlankyxD/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
mkhan149/output_model6 | mkhan149 | 2023-06-24T18:24:45Z | 61 | 0 | transformers | [
"transformers",
"tf",
"distilbert",
"fill-mask",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | 2023-06-24T17:51:37Z | ---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: mkhan149/output_model6
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. -->
# mkhan149/output_model6
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:
- Train Loss: 3.7680
- Validation Loss: 4.2181
- Epoch: 0
## 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': 'AdamWeightDecay', 'learning_rate': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 2e-05, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 263, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, '__passive_serialization__': True}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: mixed_float16
### Training results
| Train Loss | Validation Loss | Epoch |
|:----------:|:---------------:|:-----:|
| 3.7680 | 4.2181 | 0 |
### Framework versions
- Transformers 4.30.2
- TensorFlow 2.11.0
- Datasets 2.13.1
- Tokenizers 0.13.3
|
hopkins/svo-ss10k | hopkins | 2023-06-24T17:41:19Z | 112 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"gpt2",
"text-generation",
"generated_from_trainer",
"dataset:generator",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2023-06-24T17:14:08Z | ---
tags:
- generated_from_trainer
datasets:
- generator
model-index:
- name: svo-ss10k
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. -->
# svo-ss10k
This model was trained from scratch on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 5.9286
## 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: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 512
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 18
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 10.3545 | 3.83 | 50 | 8.2279 |
| 7.7367 | 7.68 | 100 | 6.7753 |
| 6.457 | 11.53 | 150 | 6.2465 |
| 5.8091 | 15.38 | 200 | 5.9286 |
### Framework versions
- Transformers 4.26.1
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
|
lewdryuna/A-Others | lewdryuna | 2023-06-24T17:34:11Z | 0 | 1 | null | [
"stable-diffusion",
"text-to-image",
"license:creativeml-openrail-m",
"region:us"
] | text-to-image | 2023-06-24T17:34:11Z | ---
license: creativeml-openrail-m
tags:
- stable-diffusion
- text-to-image
duplicated_from: Hemlok/DateMix
---
# 『Date Mix & RDt Mix』
- "Date Mix" is a model created by hierarchical merging based on "anything-v4.5"([andite/anything-v4.0 · Hugging Face](https://huggingface.co/andite/anything-v4.0)).
----
- "RDtMix" is a merged realistic model based on "Date Mix".
----
# ◆Discord
[Join Discord Server](https://discord.gg/eN6aSWRddT)
- The merged model community of Hemlok.
----
# ◆About
- This model was created to improve composition and color tone.
- If you like realistic illustrations, please use "RDtModel".
- Sampler: DDIM or DPM++ SDE Karras
- Steps: 50~
- Clipskip: 2
- CFG Scale: 5-12
- Denoise strength: 0.5-0.7(As you like)
- Negative prompts should be as few as possible.
- vae: As you wish. (Any etc. If not used, color may become lighter)
----
# ◆How to use
- Please download the file by yourself and use it with WebUI(AUTOMATIC1111) etc.
- Use the f16 version for Colab(T4) or a PC with low RAM.
----
# ◆Colab Note
[](https://colab.research.google.com/drive/1Bsm7p_Db5u3IiHr3YjTeKu4jOllfTyqZ?usp=sharing)
- (I have not checked the operation but it probably works.)
----
# ◆Comparison
<img src="https://i.imgur.com/fW2cPsY.jpg" width="1700" height="">
<img src="https://i.imgur.com/0k48okp.jpg" width="1700" height="">
```
kawaii, 1girl, looking at viewer, smile
```
----
<img src="https://i.imgur.com/d44iIvs.jpg" width="1700" height="">
```
(morning), (school), 1girl, solo, looking at viewer, cowboy shot, (school uniform), smile, black hair, stockings
```
----
# ◆Sampler & CFG Scale
<img src="https://i.imgur.com/vzUBzmw.jpg" width="1700" height="">
```
(morning), (school), 1girl, solo, looking at viewer, cowboy shot, (school uniform), smile, black hair, stockings
```
----
# Disclaimer
- The creation of SFW and NSFW images is at the discretion of the individual creator.
- This model is not a model created to publish NSFW content in public places, etc.
----
## License
This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage.
The CreativeML OpenRAIL License specifies:
1. You can't use the model to deliberately produce nor share illegal or harmful outputs or content
2. The authors claims no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in the license
3. You may re-distribute the weights and use the model commercially and/or as a service. If you do, please be aware you have to include the same use restrictions as the ones in the license and share a copy of the CreativeML OpenRAIL-M to all your users (please read the license entirely and carefully)
(Full text of the license: https://huggingface.co/spaces/CompVis/stable-diffusion-license) |
mariololo/Reinforce-CartPole-v1 | mariololo | 2023-06-24T17:08:18Z | 0 | 0 | null | [
"CartPole-v1",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] | reinforcement-learning | 2023-06-24T17:08:09Z | ---
tags:
- CartPole-v1
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-CartPole-v1
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: CartPole-v1
type: CartPole-v1
metrics:
- type: mean_reward
value: 500.00 +/- 0.00
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **CartPole-v1**
This is a trained model of a **Reinforce** agent playing **CartPole-v1** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
paramrah/shoesv1 | paramrah | 2023-06-24T17:02:54Z | 2 | 0 | tf-keras | [
"tf-keras",
"image-classification",
"region:us"
] | image-classification | 2023-06-24T16:15:38Z | ---
pipeline_tag: image-classification
--- |
osiria/deberta-base-italian | osiria | 2023-06-24T16:54:52Z | 830 | 2 | transformers | [
"transformers",
"pytorch",
"safetensors",
"deberta-v2",
"feature-extraction",
"it",
"arxiv:2111.09543",
"arxiv:2010.05609",
"license:mit",
"endpoints_compatible",
"region:us"
] | feature-extraction | 2023-05-29T17:48:34Z | ---
license: mit
language:
- it
---
--------------------------------------------------------------------------------------------------
<body>
<span class="vertical-text" style="background-color:lightgreen;border-radius: 3px;padding: 3px;"> </span>
<br>
<span class="vertical-text" style="background-color:orange;border-radius: 3px;padding: 3px;"> </span>
<br>
<span class="vertical-text" style="background-color:lightblue;border-radius: 3px;padding: 3px;"> Model: DeBERTa</span>
<br>
<span class="vertical-text" style="background-color:tomato;border-radius: 3px;padding: 3px;"> Lang: IT</span>
<br>
<span class="vertical-text" style="background-color:lightgrey;border-radius: 3px;padding: 3px;"> </span>
<br>
<span class="vertical-text" style="background-color:#CF9FFF;border-radius: 3px;padding: 3px;"> </span>
</body>
--------------------------------------------------------------------------------------------------
<h3>Model description</h3>
This is a <b>DeBERTa</b> <b>[1]</b> model for the <b>Italian</b> language, obtained using <b>mDeBERTa</b> ([mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base)) as a starting point and focusing it on the Italian language by modifying the embedding layer
(as in <b>[2]</b>, computing document-level frequencies over the <b>Wikipedia</b> dataset)
The resulting model has 124M parameters, a vocabulary of 50.256 tokens, and a size of ~500 MB.
<h3>Quick usage</h3>
```python
from transformers import DebertaV2TokenizerFast, DebertaV2Model
tokenizer = DebertaV2TokenizerFast.from_pretrained("osiria/deberta-base-italian")
model = DebertaV2Model.from_pretrained("osiria/deberta-base-italian")
```
<h3>References</h3>
[1] https://arxiv.org/abs/2111.09543
[2] https://arxiv.org/abs/2010.05609
<h3>License</h3>
The model is released under <b>MIT</b> license
|
yasamingol/NLP_Model_Classifier | yasamingol | 2023-06-24T16:32:02Z | 163 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"bert",
"text-classification",
"generated_from_trainer",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-06-23T15:04:55Z | ---
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- recall
- precision
model-index:
- name: NLP_Model_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. -->
# NLP_Model_Classifier
This model is a fine-tuned version of [HooshvareLab/bert-base-parsbert-uncased](https://huggingface.co/HooshvareLab/bert-base-parsbert-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5617
- Accuracy: {'accuracy': 0.912962962962963}
- F1 Weighted: {'f1': 0.9141126838691339}
- F1: {'f1': 0.912962962962963}
- Recall: {'recall': 0.912962962962963}
- Precision: {'precision': 0.912962962962963}
## 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: 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: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Weighted | F1 | Recall | Precision |
|:-------------:|:-----:|:----:|:---------------:|:--------------------------------:|:--------------------------:|:--------------------------:|:------------------------------:|:---------------------------------:|
| No log | 1.0 | 270 | 0.4435 | {'accuracy': 0.8851851851851852} | {'f1': 0.8837658106568329} | {'f1': 0.8851851851851851} | {'recall': 0.8851851851851852} | {'precision': 0.8851851851851852} |
| 0.6248 | 2.0 | 540 | 0.4601 | {'accuracy': 0.9018518518518519} | {'f1': 0.9003935312696059} | {'f1': 0.9018518518518519} | {'recall': 0.9018518518518519} | {'precision': 0.9018518518518519} |
| 0.6248 | 3.0 | 810 | 0.5067 | {'accuracy': 0.9018518518518519} | {'f1': 0.903263191345543} | {'f1': 0.9018518518518519} | {'recall': 0.9018518518518519} | {'precision': 0.9018518518518519} |
| 0.0931 | 4.0 | 1080 | 0.5500 | {'accuracy': 0.912962962962963} | {'f1': 0.9137945012321058} | {'f1': 0.912962962962963} | {'recall': 0.912962962962963} | {'precision': 0.912962962962963} |
| 0.0931 | 5.0 | 1350 | 0.5617 | {'accuracy': 0.912962962962963} | {'f1': 0.9141126838691339} | {'f1': 0.912962962962963} | {'recall': 0.912962962962963} | {'precision': 0.912962962962963} |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
WelfCrozzo/T5-L128-belarusian | WelfCrozzo | 2023-06-24T15:59:54Z | 140 | 1 | transformers | [
"transformers",
"pytorch",
"safetensors",
"t5",
"text2text-generation",
"translation",
"be",
"en",
"ru",
"dataset:WelfCrozzo/kupalinka",
"license:openrail",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | translation | 2023-06-24T14:38:38Z | ---
license: openrail
datasets:
- WelfCrozzo/kupalinka
language:
- be
- en
- ru
metrics:
- bleu
library_name: transformers
tags:
- translation
widget:
- text: "<extra_id_1>да зорак праз цяжкасці"
example_title: "be -> ru"
- text: "<extra_id_2>да зорак праз цяжкасці"
example_title: "be -> en"
- text: "<extra_id_3>к звездам через трудности"
example_title: "ru -> be"
- text: "<extra_id_5>к звездам через трудности"
example_title: "ru -> en"
- text: "<extra_id_6>to the stars through difficulties."
example_title: "en -> be"
- text: "<extra_id_7>to the stars through difficulties."
example_title: "en -> ru"
---
# T5 for belarusian language
This model is based on T5-small with sequence length equal 128 tokens. Model trained from scratch on RTX 3090 24GB.
# Supported tasks:
- translation BE to RU: `<extra_id_1>`
- translation BE to EN: `<extra_id_2>`
- translation RU to BE: `<extra_id_3>`
- translation RU to EN: `<extra_id_5>`
- translation EN to BE: `<extra_id_6>`
- translation EN to RU: `<extra_id_7>`
# Metrics:
- [evel/BLEU](https://api.wandb.ai/links/miklgr500/31mq4s36)
- [evel/loss](https://api.wandb.ai/links/miklgr500/rvi2p69n)
- [train/loss](https://api.wandb.ai/links/miklgr500/z9alu3n5)
# How to Get Started with the Model
<details>
<summary> Click to expand </summary>
```python
from transformers import T5TokenizerFast, T5ForConditionalGeneration
tokenizer = T5TokenizerFast.from_pretrained("WelfCrozzo/T5-L128-belarusian")
model = T5ForConditionalGeneration.from_pretrained("WelfCrozzo/T5-L128-belarusian")
x = tokenizer.encode('<extra_id_1>да зорак праз цяжкасці', return_tensors='pt')
result = model.generate(x, return_dict_in_generate=True, output_scores=True,max_length=128)
print(tokenizer.decode(result["sequences"][0]))
```
</details>
# References
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://jmlr.org/papers/volume21/20-074/20-074.pdf) |
LOGQS/poca-SoccerTwos | LOGQS | 2023-06-24T15:47:38Z | 13 | 0 | ml-agents | [
"ml-agents",
"tensorboard",
"onnx",
"SoccerTwos",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SoccerTwos",
"region:us"
] | reinforcement-learning | 2023-06-24T15:45:25Z | ---
library_name: ml-agents
tags:
- SoccerTwos
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-SoccerTwos
---
# **poca** Agent playing **SoccerTwos**
This is a trained model of a **poca** agent playing **SoccerTwos**
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: LOGQS/poca-SoccerTwos
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
keyfan/falcon-qlora-chinese | keyfan | 2023-06-24T15:33:08Z | 0 | 3 | null | [
"zh",
"en",
"dataset:QingyiSi/Alpaca-CoT",
"license:apache-2.0",
"region:us"
] | null | 2023-06-09T02:20:18Z | ---
license: apache-2.0
datasets:
- QingyiSi/Alpaca-CoT
language:
- zh
- en
---
This is a QLoRa adapter model to [Falcon-40b](https://huggingface.co/tiiuae/falcon-40b).
Though Falcon is not specifically trained on Chinese corpus, it exhibits strong performance in Chinese Language Understanding in our experiment. We would like to explore out of curiosity whether a
small amount of Chinese instruction data can push it further and make it better at speaking.The LoRa model is trained with the [QLoRa repo](https://github.com/artidoro/qlora) on a subset of bilingual instruction data from [Alpaca-CoT dataset](https://huggingface.co/datasets/QingyiSi/Alpaca-CoT).
The result is suprisingly good considering the number of Chinese tokens it has ever seen, though it shows clear limitions. Please check the examples below.
```
Question: 序列1,4,9,16的后一个数是什么？
Answer: 序列1,4,9,16的后一个数是25。因为序列中的每个数字都是前一个数字加上一个递增的差值，第一个差值是3，第二个差值是5，第三个差值是7，第四个差值是9，所以最后一个数字应该是第四个数字16加上第四个差值9，即16+9=25。因此，序列1,4,9,16的后一个数是25。
Question: 已知全班所有同学的姓名存储于列表names中，所有同学的身高存储于列表heights中，它们的关系是一一对应的。请写一段Python代码，将所有同学的姓名按身高由低到高排序。
Answer: names = ['小明', '小红', '小张', '小李']
heights = [170, 165, 175, 180]
# 使用zip函数将姓名和身高对应起来，然后根据身高排序
sorted_names = sorted(names, key=lambda x: heights[names.index(x)])
# 输出排序后的姓名列表
print(sorted_names)
Question: 中国的“东北三省”指的是哪里？
Answer: 中国的东北三省指的是吉林省、黑龙江省和辽宁省。这些省份位于中国东北地区，北临俄罗斯和乌克兰，东临日本海。它们是中国最大的省份之一，占中国陆地面积的七分之一。东北三省以其自然风光、丰富的民族文化和历史遗产而闻名。它们是中国旅游业的重要目的地之一。您还有其他问题吗？
Question: “但愿人长久，千里共婵娟”，其中婵娟指的是什么？ A、月亮 B、姻缘
Answer: 这道题目考察的是对于古诗词的理解和文化常识。这句话出自唐代诗人杜甫的《月夜》一诗，其中婵娟是指月亮。这句话的意思是希望人和月亮能够长久存在，共同见证世间美好的事物。婵娟是古代诗词中常用的一个词语，指的是月亮的光辉、美丽和媚态。因此，答案是A，月亮。
```
## Evalutions
We evaluate on [C-Eval](https://cevalbenchmark.com/). More results will be added later.
Result on C-Eval test set with 5-shot and no CoT, which is better than LLaMA-series models.
| Average | Avg(Hard) | STEM | Social Science | Humanities | Others |
| - | - | - | - | - | - |
| 42.0 | 32.4 | 38.5 | 50.3 | 42.5 | 40.5 | |
uraskargi/q-Taxi-v3 | uraskargi | 2023-06-24T15:27:57Z | 0 | 0 | null | [
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | reinforcement-learning | 2023-06-24T15:27:55Z | ---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-Taxi-v3
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.48 +/- 2.76
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="uraskargi/q-Taxi-v3", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
Amool/albert-base-v2-finetuned-squad | Amool | 2023-06-24T15:06:41Z | 115 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"albert",
"question-answering",
"generated_from_trainer",
"dataset:squad_v2",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | question-answering | 2023-06-24T06:49:43Z | ---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- squad_v2
model-index:
- name: albert-base-v2-finetuned-squad
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. -->
# albert-base-v2-finetuned-squad
This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the squad_v2 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: 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: 20
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
daan1213/my_awesome_model | daan1213 | 2023-06-24T14:52:31Z | 107 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:financial_phrasebank",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-06-24T14:03:54Z | ---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- financial_phrasebank
metrics:
- accuracy
model-index:
- name: my_awesome_model
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: financial_phrasebank
type: financial_phrasebank
config: sentences_allagree
split: train
args: sentences_allagree
metrics:
- name: Accuracy
type: accuracy
value: 0.9668874172185431
---
<!-- 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_model
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the financial_phrasebank dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1210
- Accuracy: 0.9669
## 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: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 1.0 | 114 | 0.1984 | 0.9360 |
| No log | 2.0 | 228 | 0.1210 | 0.9669 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
KrakeTito/medical_qa_llama | KrakeTito | 2023-06-24T14:40:42Z | 0 | 0 | peft | [
"peft",
"region:us"
] | null | 2023-06-24T14:40:42Z | ---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: True
- load_in_4bit: False
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
### Framework versions
- PEFT 0.4.0.dev0
|
Davit6174/georgian-distilbert-mlm | Davit6174 | 2023-06-24T14:39:56Z | 96 | 0 | transformers | [
"transformers",
"tf",
"distilbert",
"fill-mask",
"general",
"ka",
"dataset:mc4",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | 2023-06-23T21:19:11Z | ---
datasets:
- mc4
language:
- ka
library_name: transformers
tags:
- general
widget:
- text: "ქართული [MASK] სწავლა საკმაოდ რთულია"
example_title: "Georgian Language"
- text: "საქართველოს [MASK] ნაკრები ერთა ლიგაზე კარგად ასპარეზობს"
example_title: "Football"
- text: "ქართული ღვინო განთქმულია [MASK] მსოფლიოში"
example_title: "Wine"
---
# General Georgian Language Model
This language model is a pretrained model specifically designed to understand and generate text in the Georgian language. It is based on the DistilBERT-base-uncased architecture and has been trained on the MC4 dataset, which contains a large collection of Georgian web documents.
## Model Details
- **Architecture**: DistilBERT-base-uncased
- **Pretraining Corpus**: MC4 (Multilingual Crawl Corpus)
- **Language**: Georgian
## Pretraining
The model has undergone a pretraining phase using the DistilBERT architecture, which is a distilled version of the original BERT model. DistilBERT is known for its smaller size and faster inference speed while still maintaining a high level of performance.
During pretraining, the model was exposed to a vast amount of preprocessed Georgian text data from the MC4 dataset.
## Usage
To use the General Georgian Language Model, you can utilize the model through various natural language processing (NLP) tasks, such as:
- Text classification
- Named entity recognition
- Sentiment analysis
- Language generation
You can fine-tune this model on specific downstream tasks using task-specific datasets or use it as a feature extractor for transfer learning.
## Example Code
Here is an example of how to use the General Georgian Language Model using the Hugging Face `transformers` library in Python:
```python
from transformers import AutoTokenizer, TFAutoModel
from transformers import pipeline
# Load the tokenizer and model
tokenizer = AutoTokenizer.from_pretrained("Davit6174/georgian-distilbert-mlm")
model = TFAutoModel.from_pretrained("Davit6174/georgian-distilbert-mlm")
# Build pipeline
mask_filler = pipeline(
"fill-mask", model=model, tokenizer=tokenizer
)
text = 'ქართული [MASK] სწავლა საკმაოდ რთულია'
# Generate model output
preds = mask_filler(text)
# Print top 5 predictions
for pred in preds:
print(f">>> {pred['sequence']}")
```
## Limitations and Considerations
- The model's performance may vary across different downstream tasks and domains.
- The model's understanding of context and nuanced meanings may not always be accurate.
- The model may generate plausible-sounding but incorrect or nonsensical Georgian text.
- Therefore, it is recommended to evaluate the model's performance and fine-tune it on task-specific datasets when necessary.
## Acknowledgments
The Georgian Language Model was pretrained using the Hugging Face transformers library and trained on the MC4 dataset, which is maintained by the community. I would like to express my gratitude to the contributors and maintainers of these valuable resources.
|
Subsets and Splits