modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-06-23 18:27:52
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 492
values | tags
sequencelengths 1
4.05k
| pipeline_tag
stringclasses 54
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-06-23 18:25:26
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
karakuri-ai/karakuri-lm-7b-apm-v0.1 | karakuri-ai | 2024-05-20T10:16:41Z | 295 | 4 | transformers | [
"transformers",
"safetensors",
"gemma",
"text-generation",
"steerlm",
"conversational",
"en",
"ja",
"dataset:OpenAssistant/oasst2",
"dataset:nvidia/HelpSteer",
"base_model:google/gemma-7b",
"base_model:finetune:google/gemma-7b",
"license:gemma",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-04-25T04:17:30Z | ---
library_name: transformers
license: gemma
datasets:
- OpenAssistant/oasst2
- nvidia/HelpSteer
language:
- en
- ja
tags:
- gemma
- steerlm
base_model: google/gemma-7b
---
# KARAKURI LM 7B APM v0.1
## Model Details
### Model Description
- **Developed by:** [KARAKURI Inc.](https://about.karakuri.ai/)
- **Model type:** Causal decoder-only transformer language model
- **Languages**: Primarily English
- **License:** [Gemma Terms of Use](https://ai.google.dev/gemma/terms)
- **Finetuned from model:** [google/gemma-7b](https://huggingface.co/google/gemma-7b)
- **Contact**: For questions and comments about the model, please email `[email protected]`
## Usage
KARAKURI LM 7B APM v0.1 is a attribute prediction model that rates model responses on various aspects that makes a response desirable.
Given a conversation with multiple turns between user and assistant, the model rates the following attributes (between 0 and 4) for every assistant turn.
- helpfulness: Overall helpfulness of the response to the prompt.
- correctness: Inclusion of all pertinent facts without errors.
- coherence: Consistency and clarity of expression.
- complexity: Intellectual depth required to write response (i.e. whether the response can be written by anyone with basic language competency or requires deep domain expertise).
- verbosity: Amount of detail included in the response, relative to what is asked for in the prompt.
- quality: Perceived goodness of response.
- toxicity: Undesirable elements such as vulgar, harmful or potentially biased response.
- humor: Sense of humor within response.
- creativity: Willingness to generate non-conventional response.
The first five are derived from HelpSteer, while the remaining four are derived from OASST2.
You can run the model using the 🤗 Transformers:
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "karakuri-ai/karakuri-lm-7b-apm-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype="auto",
device_map="auto",
)
messages = [
{"role": "user", "content": "Hello!"},
{"role": "assistant", "content": "Hello! How can I help you today?"},
]
tokenizer.apply_chat_template(
messages,
label="helpsteer",
tokenize=False,
add_generation_prompt=True,
)
# <bos>[INST] Hello! [/INST] Hello! How can I help you today? [ATTR_1]
input_ids = tokenizer.apply_chat_template(
messages,
label="helpsteer",
add_generation_prompt=True,
return_tensors="pt",
).to(model.device)
outputs = model.generate(input_ids, max_new_tokens=32)
tokenizer.decode(outputs[0][input_ids.shape[-1]:])
# helpfulness: 2 correctness: 1 coherence: 2 complexity: 1 verbosity: 1 [/ATTR_1]<eos>
messages += [
{"role": "label", "content": "helpfulness: 2 correctness: 1 coherence: 2 complexity: 1 verbosity: 1"},
{"role": "user", "content": "Thank you!"},
{"role": "assistant", "content": "You're welcome! I'm happy to help however I can."},
]
tokenizer.apply_chat_template(
messages,
label="helpsteer",
tokenize=False,
add_generation_prompt=True,
)
# <bos>[INST] Hello! [/INST] Hello! How can I help you today? [ATTR_1] helpfulness: 2 correctness: 1 coherence: 2 complexity: 1 verbosity: 1 [/ATTR_1]<eos>[INST] Thank you! [/INST] You're welcome! I'm happy to help however I can. [ATTR_1]
messages = [
{"role": "user", "content": "Hello!"},
{"role": "assistant", "content": "Hello! How can I help you today?"},
]
tokenizer.apply_chat_template(
messages,
label="oasst",
tokenize=False,
add_generation_prompt=True,
)
# <bos>[INST] Hello! [/INST] Hello! How can I help you today? [ATTR_2]
input_ids = tokenizer.apply_chat_template(
messages,
label="oasst",
add_generation_prompt=True,
return_tensors="pt",
).to(model.device)
outputs = model.generate(input_ids, max_new_tokens=32)
tokenizer.decode(outputs[0][input_ids.shape[-1]:])
# quality: 3 toxicity: 1 humor: 1 creativity: 1 [/ATTR_2]<eos>
```
## Training Details
### Training Data
- [OASST2](https://huggingface.co/datasets/OpenAssistant/oasst2)
- [HelpSteer](https://huggingface.co/datasets/nvidia/HelpSteer)
### Training Infrastructure
- **Hardware**: The model was trained on single node of an Amazon EC2 trn1.32xlarge instance.
- **Software**: We use code based on [neuronx-nemo-megatron](https://github.com/aws-neuron/neuronx-nemo-megatron).
## Citation
```
@misc{karakuri_lm_7b_apm_v01,
author = { {KARAKURI} {I}nc. },
title = { {KARAKURI} {LM} 7{B} {APM} v0.1 },
year = { 2024 },
url = { https://huggingface.co/karakuri-ai/karakuri-lm-7b-apm-v0.1 },
publisher = { Hugging Face },
journal = { Hugging Face repository }
}
``` |
azolkowski/gpt2-wikitext2 | azolkowski | 2024-05-20T10:16:25Z | 191 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"gpt2",
"text-generation",
"generated_from_trainer",
"base_model:openai-community/gpt2",
"base_model:finetune:openai-community/gpt2",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-20T09:50:42Z | ---
license: mit
base_model: gpt2
tags:
- generated_from_trainer
model-index:
- name: gpt2-wikitext2
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-wikitext2
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 6.1086
## 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: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 6.5532 | 1.0 | 2249 | 6.4660 |
| 6.1872 | 2.0 | 4498 | 6.1945 |
| 6.0092 | 3.0 | 6747 | 6.1086 |
### Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
|
ISTA-DASLab/SOLAR-10.7B-Instruct-v1.0-GPTQ-4bit | ISTA-DASLab | 2024-05-20T10:15:11Z | 80 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"4-bit",
"gptq",
"region:us"
] | text-generation | 2024-05-17T07:35:22Z | ---
license: apache-2.0
inference: false
---
# Description
4 bit quantization of [upstage/SOLAR-10.7B-Instruct-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0) using GPTQ. We use the config below for quantization/evaluation and [HuggingFaceH4/ultrachat_200k](https://huggingface.co/datasets/HuggingFaceH4/ultrachat_200k) as the calibration data. The code is available under [this repository.](https://github.com/IST-DASLab/marlin/tree/2f6d7c10e124b3c5fa29ff8d77d568bd7af3274c/gptq)
```yaml
bits: 4
damp_percent: 0.01
desc_act: true
exllama_config:
version: 2
group_size: 128
quant_method: gptq
static_groups: false
sym: true
true_sequential: true
```
## Evaluations
Below is a comprehensive evaluation using the awesome [mosaicml/llm-foundry](https://github.com/mosaicml/llm-foundry/tree/main/scripts/eval).
| model_name | core_average | world_knowledge | commonsense_reasoning | language_understanding | symbolic_problem_solving | reading_comprehension |
|:----------------------------------|---------------:|------------------:|------------------------:|-------------------------:|---------------------------:|------------------------:|
| upstage/SOLAR-10.7B-Instruct-v1.0 | 0.594131 | 0.602579 | 0.600195 | 0.747605 | 0.406245 | 0.614029 |
| Category | Benchmark | Subtask | Accuracy | Number few shot |
| :----------------------- | :--------------------------- | :---------------------------------- | -------: | :-------------- |
| symbolic_problem_solving | gsm8k | | 0.638362 | 0-shot |
| commonsense_reasoning | copa | | 0.84 | 0-shot |
| commonsense_reasoning | commonsense_qa | | 0.841933 | 0-shot |
| commonsense_reasoning | piqa | | 0.818281 | 0-shot |
| commonsense_reasoning | bigbench_strange_stories | | 0.793103 | 0-shot |
| commonsense_reasoning | bigbench_strategy_qa | | 0.66623 | 0-shot |
| language_understanding | lambada_openai | | 0.735882 | 0-shot |
| language_understanding | hellaswag | | 0.855208 | 0-shot |
| reading_comprehension | coqa | | 0.222723 | 0-shot |
| reading_comprehension | boolq | | 0.893884 | 0-shot |
| world_knowledge | triviaqa_sm_sub | | 0.628333 | 3-shot |
| world_knowledge | jeopardy | Average | 0.500792 | 3-shot |
| world_knowledge | | american_history | 0.581114 | 3-shot |
| world_knowledge | | literature | 0.655102 | 3-shot |
| world_knowledge | | science | 0.371849 | 3-shot |
| world_knowledge | | word_origins | 0.271233 | 3-shot |
| world_knowledge | | world_history | 0.624665 | 3-shot |
| world_knowledge | bigbench_qa_wikidata | | 0.669209 | 3-shot |
| world_knowledge | arc_easy | | 0.815657 | 3-shot |
| world_knowledge | arc_challenge | | 0.650171 | 3-shot |
| commonsense_reasoning | siqa | | 0.881781 | 3-shot |
| language_understanding | winograd | | 0.897436 | 3-shot |
| symbolic_problem_solving | bigbench_operators | | 0.595238 | 3-shot |
| reading_comprehension | squad | | 0.626395 | 3-shot |
| symbolic_problem_solving | svamp | | 0.603333 | 5-shot |
| world_knowledge | mmlu | Average | 0.647028 | 5-shot |
| world_knowledge | | abstract_algebra | 0.29 | 5-shot |
| world_knowledge | | anatomy | 0.577778 | 5-shot |
| world_knowledge | | astronomy | 0.710526 | 5-shot |
| world_knowledge | | business_ethics | 0.73 | 5-shot |
| world_knowledge | | clinical_knowledge | 0.701887 | 5-shot |
| world_knowledge | | college_biology | 0.729167 | 5-shot |
| world_knowledge | | college_chemistry | 0.39 | 5-shot |
| world_knowledge | | college_computer_science | 0.5 | 5-shot |
| world_knowledge | | college_mathematics | 0.31 | 5-shot |
| world_knowledge | | college_medicine | 0.66474 | 5-shot |
| world_knowledge | | college_physics | 0.411765 | 5-shot |
| world_knowledge | | computer_security | 0.72 | 5-shot |
| world_knowledge | | conceptual_physics | 0.582979 | 5-shot |
| world_knowledge | | econometrics | 0.473684 | 5-shot |
| world_knowledge | | electrical_engineering | 0.565517 | 5-shot |
| world_knowledge | | elementary_mathematics | 0.470899 | 5-shot |
| world_knowledge | | formal_logic | 0.460317 | 5-shot |
| world_knowledge | | global_facts | 0.33 | 5-shot |
| world_knowledge | | high_school_biology | 0.770968 | 5-shot |
| world_knowledge | | high_school_chemistry | 0.448276 | 5-shot |
| world_knowledge | | high_school_computer_science | 0.71 | 5-shot |
| world_knowledge | | high_school_european_history | 0.830303 | 5-shot |
| world_knowledge | | high_school_geography | 0.848485 | 5-shot |
| world_knowledge | | high_school_government_and_politics | 0.896373 | 5-shot |
| world_knowledge | | high_school_macroeconomics | 0.646154 | 5-shot |
| world_knowledge | | high_school_mathematics | 0.348148 | 5-shot |
| world_knowledge | | high_school_microeconomics | 0.722689 | 5-shot |
| world_knowledge | | high_school_physics | 0.344371 | 5-shot |
| world_knowledge | | high_school_psychology | 0.833028 | 5-shot |
| world_knowledge | | high_school_statistics | 0.523148 | 5-shot |
| world_knowledge | | high_school_us_history | 0.852941 | 5-shot |
| world_knowledge | | high_school_world_history | 0.827004 | 5-shot |
| world_knowledge | | human_aging | 0.713004 | 5-shot |
| world_knowledge | | human_sexuality | 0.755725 | 5-shot |
| world_knowledge | | international_law | 0.768595 | 5-shot |
| world_knowledge | | jurisprudence | 0.796296 | 5-shot |
| world_knowledge | | logical_fallacies | 0.723926 | 5-shot |
| world_knowledge | | machine_learning | 0.508929 | 5-shot |
| world_knowledge | | management | 0.825243 | 5-shot |
| world_knowledge | | marketing | 0.871795 | 5-shot |
| world_knowledge | | medical_genetics | 0.73 | 5-shot |
| world_knowledge | | miscellaneous | 0.814815 | 5-shot |
| world_knowledge | | moral_disputes | 0.736994 | 5-shot |
| world_knowledge | | moral_scenarios | 0.43352 | 5-shot |
| world_knowledge | | nutrition | 0.728758 | 5-shot |
| world_knowledge | | philosophy | 0.700965 | 5-shot |
| world_knowledge | | prehistory | 0.765432 | 5-shot |
| world_knowledge | | professional_accounting | 0.507092 | 5-shot |
| world_knowledge | | professional_law | 0.487614 | 5-shot |
| world_knowledge | | professional_medicine | 0.727941 | 5-shot |
| world_knowledge | | professional_psychology | 0.661765 | 5-shot |
| world_knowledge | | public_relations | 0.718182 | 5-shot |
| world_knowledge | | security_studies | 0.669388 | 5-shot |
| world_knowledge | | sociology | 0.81592 | 5-shot |
| world_knowledge | | us_foreign_policy | 0.89 | 5-shot |
| world_knowledge | | virology | 0.518072 | 5-shot |
| world_knowledge | | world_religions | 0.789474 | 5-shot |
| symbolic_problem_solving | bigbench_dyck_languages | | 0.458 | 5-shot |
| language_understanding | winogrande | | 0.826361 | 5-shot |
| symbolic_problem_solving | agi_eval_lsat_ar | | 0.269565 | 5-shot |
| symbolic_problem_solving | simple_arithmetic_nospaces | | 0.372 | 5-shot |
| symbolic_problem_solving | simple_arithmetic_withspaces | | 0.367 | 5-shot |
| reading_comprehension | agi_eval_lsat_rc | | 0.794776 | 5-shot |
| reading_comprehension | agi_eval_lsat_lr | | 0.641176 | 5-shot |
| reading_comprehension | agi_eval_sat_en | | 0.849515 | 5-shot |
| world_knowledge | arc_challenge | | 0.670648 | 25-shot |
| commonsense_reasoning | openbook_qa | | 0.56 | 10-shot |
| language_understanding | hellaswag | | 0.866461 | 10-shot |
| | bigbench_cs_algorithms | | 0.652273 | 10-shot |
| symbolic_problem_solving | bigbench_elementary_math_qa | | 0.392453 | 1-shot | |
neerajx0/gpt | neerajx0 | 2024-05-20T10:15:05Z | 0 | 0 | transformers | [
"transformers",
"gpt",
"text-generation-inference",
"en",
"arxiv:1910.09700",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-05-20T10:13:01Z | ---
license: apache-2.0
language:
- en
library_name: transformers
tags:
- gpt
- text-generation-inference
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
vvduc03/lora-llava-3b-adapter | vvduc03 | 2024-05-20T10:10:43Z | 7 | 0 | transformers | [
"transformers",
"safetensors",
"llava_mistral",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-20T09:46:02Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
DownwardSpiral33/gpt2-imdb-pos-roberta16-256_0_035-2024.05.20.09.15 | DownwardSpiral33 | 2024-05-20T10:08:16Z | 136 | 0 | transformers | [
"transformers",
"safetensors",
"gpt2",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-20T10:07:45Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
shivank-pixis/Fashion_Beauty-lora-20May_new | shivank-pixis | 2024-05-20T10:02:54Z | 10 | 0 | diffusers | [
"diffusers",
"stable-diffusion-xl",
"stable-diffusion-xl-diffusers",
"text-to-image",
"lora",
"template:sd-lora",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0",
"license:openrail++",
"region:us"
] | text-to-image | 2024-05-20T09:20:24Z | ---
tags:
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
- text-to-image
- diffusers
- lora
- template:sd-lora
widget:
- text: 'in the style of <s0><s1>'
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: in the style of <s0><s1>
license: openrail++
---
# SDXL LoRA DreamBooth - shivank-pixis/Fashion_Beauty-lora-20May_new
<Gallery />
## Model description
### These are shivank-pixis/Fashion_Beauty-lora-20May_new LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
## Download model
### Use it with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke
- **LoRA**: download **[`./Fashion_Beauty-lora-20May_new.safetensors` here 💾](/shivank-pixis/Fashion_Beauty-lora-20May_new/blob/main/./Fashion_Beauty-lora-20May_new.safetensors)**.
- Place it on your `models/Lora` folder.
- On AUTOMATIC1111, load the LoRA by adding `<lora:./Fashion_Beauty-lora-20May_new:1>` to your prompt. On ComfyUI just [load it as a regular LoRA](https://comfyanonymous.github.io/ComfyUI_examples/lora/).
- *Embeddings*: download **[`./Fashion_Beauty-lora-20May_new_emb.safetensors` here 💾](/shivank-pixis/Fashion_Beauty-lora-20May_new/blob/main/./Fashion_Beauty-lora-20May_new_emb.safetensors)**.
- Place it on it on your `embeddings` folder
- Use it by adding `./Fashion_Beauty-lora-20May_new_emb` to your prompt. For example, `in the style of ./Fashion_Beauty-lora-20May_new_emb`
(you need both the LoRA and the embeddings as they were trained together for this LoRA)
## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
```py
from diffusers import AutoPipelineForText2Image
import torch
from huggingface_hub import hf_hub_download
from safetensors.torch import load_file
pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('shivank-pixis/Fashion_Beauty-lora-20May_new', weight_name='pytorch_lora_weights.safetensors')
embedding_path = hf_hub_download(repo_id='shivank-pixis/Fashion_Beauty-lora-20May_new', filename='./Fashion_Beauty-lora-20May_new_emb.safetensors' repo_type="model")
state_dict = load_file(embedding_path)
pipeline.load_textual_inversion(state_dict["clip_l"], token=["<s0>", "<s1>"], text_encoder=pipeline.text_encoder, tokenizer=pipeline.tokenizer)
pipeline.load_textual_inversion(state_dict["clip_g"], token=["<s0>", "<s1>"], text_encoder=pipeline.text_encoder_2, tokenizer=pipeline.tokenizer_2)
image = pipeline('in the style of <s0><s1>').images[0]
```
For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
## Trigger words
To trigger image generation of trained concept(or concepts) replace each concept identifier in you prompt with the new inserted tokens:
to trigger concept `TOK` → use `<s0><s1>` in your prompt
## Details
All [Files & versions](/shivank-pixis/Fashion_Beauty-lora-20May_new/tree/main).
The weights were trained using [🧨 diffusers Advanced Dreambooth Training Script](https://github.com/huggingface/diffusers/blob/main/examples/advanced_diffusion_training/train_dreambooth_lora_sdxl_advanced.py).
LoRA for the text encoder was enabled. False.
Pivotal tuning was enabled: True.
Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
|
kalytm/nous-3 | kalytm | 2024-05-20T09:59:28Z | 256 | 1 | transformers | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-04-09T15:56:13Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
RichardErkhov/Equall_-_Saul-7B-Instruct-v1-4bits | RichardErkhov | 2024-05-20T09:58:31Z | 77 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"arxiv:2403.03883",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
] | text-generation | 2024-05-20T09:44:50Z | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
Saul-7B-Instruct-v1 - bnb 4bits
- Model creator: https://huggingface.co/Equall/
- Original model: https://huggingface.co/Equall/Saul-7B-Instruct-v1/
Original model description:
---
library_name: transformers
tags:
- legal
license: mit
language:
- en
---
# Equall/Saul-Instruct-v1
This is the instruct model for Equall/Saul-Instruct-v1, a large instruct language model tailored for Legal domain. This model is obtained by continue pretraining of Mistral-7B.
Checkout our website and register https://equall.ai/
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** Equall.ai in collaboration with CentraleSupelec, Sorbonne Université, Instituto Superior Técnico and NOVA School of Law
- **Model type:** 7B
- **Language(s) (NLP):** English
- **License:** MIT
### Model Sources
<!-- Provide the basic links for the model. -->
- **Paper:** https://arxiv.org/abs/2403.03883
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
You can use it for legal use cases that involves generation.
Here's how you can run the model using the pipeline() function from 🤗 Transformers:
```python
# Install transformers from source - only needed for versions <= v4.34
# pip install git+https://github.com/huggingface/transformers.git
# pip install accelerate
import torch
from transformers import pipeline
pipe = pipeline("text-generation", model="Equall/Saul-Instruct-v1", torch_dtype=torch.bfloat16, device_map="auto")
# We use the tokenizer’s chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
messages = [
{"role": "user", "content": "[YOUR QUERY GOES HERE]"},
]
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipe(prompt, max_new_tokens=256, do_sample=False)
print(outputs[0]["generated_text"])
```
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
This model is built upon the technology of LLM, which comes with inherent limitations. It may occasionally generate inaccurate or nonsensical outputs. Furthermore, being a 7B model, it's anticipated to exhibit less robust performance compared to larger models, such as the 70B variant.
## Citation
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
```bibtex
@misc{colombo2024saullm7b,
title={SaulLM-7B: A pioneering Large Language Model for Law},
author={Pierre Colombo and Telmo Pessoa Pires and Malik Boudiaf and Dominic Culver and Rui Melo and Caio Corro and Andre F. T. Martins and Fabrizio Esposito and Vera Lúcia Raposo and Sofia Morgado and Michael Desa},
year={2024},
eprint={2403.03883},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
|
kalytm/nous-1 | kalytm | 2024-05-20T09:58:26Z | 5 | 0 | transformers | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-04-09T14:46:09Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
kisejin/step2 | kisejin | 2024-05-20T09:48:10Z | 107 | 0 | transformers | [
"transformers",
"safetensors",
"t5",
"text2text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text2text-generation | 2024-05-20T09:47:50Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
dugoalberto/starcoderbase_1b_LoRA | dugoalberto | 2024-05-20T09:45:35Z | 2 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:bigcode/starcoderbase-1b",
"base_model:adapter:bigcode/starcoderbase-1b",
"license:bigcode-openrail-m",
"region:us"
] | null | 2024-05-20T09:43:23Z | ---
license: bigcode-openrail-m
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: bigcode/starcoderbase-1b
model-index:
- name: starcoderbase1_LoRA
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. -->
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/albertodugo/huggingface/runs/luuyi9uk)
# starcoderbase1_LoRA
This model is a fine-tuned version of [bigcode/starcoderbase-1b](https://huggingface.co/bigcode/starcoderbase-1b) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- training_steps: 60
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.11.2.dev0
- Transformers 4.41.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
limitedonly41/website_mistral7b_v02_1200_finetuned_2 | limitedonly41 | 2024-05-20T09:42:14Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"mistral",
"trl",
"en",
"base_model:unsloth/mistral-7b-instruct-v0.2-bnb-4bit",
"base_model:finetune:unsloth/mistral-7b-instruct-v0.2-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-05-20T09:42:01Z | ---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- trl
base_model: unsloth/mistral-7b-instruct-v0.2-bnb-4bit
---
# Uploaded model
- **Developed by:** limitedonly41
- **License:** apache-2.0
- **Finetuned from model :** unsloth/mistral-7b-instruct-v0.2-bnb-4bit
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
deepnet/SN9-BestLlama5 | deepnet | 2024-05-20T09:39:42Z | 8 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-20T09:34:12Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
Angelectronic/llama3-chat_1M | Angelectronic | 2024-05-20T09:39:19Z | 1 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"unsloth",
"generated_from_trainer",
"base_model:unsloth/llama-3-8b-Instruct-bnb-4bit",
"base_model:adapter:unsloth/llama-3-8b-Instruct-bnb-4bit",
"license:apache-2.0",
"region:us"
] | null | 2024-05-20T05:41:40Z | ---
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- unsloth
- generated_from_trainer
base_model: unsloth/llama-3-8b-Instruct-bnb-4bit
model-index:
- name: llama3-chat_1M
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# llama3-chat_1M
This model is a fine-tuned version of [unsloth/llama-3-8b-Instruct-bnb-4bit](https://huggingface.co/unsloth/llama-3-8b-Instruct-bnb-4bit) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.3835, 39.5 bleu on PhoMT test en-vi, 34.4 on IWSLT15
## 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: 16
- seed: 3407
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 5
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:-----:|:---------------:|
| 1.6092 | 0.032 | 500 | 1.4727 |
| 1.539 | 0.064 | 1000 | 1.4609 |
| 1.5211 | 0.096 | 1500 | 1.4528 |
| 1.5228 | 0.128 | 2000 | 1.4453 |
| 1.5106 | 0.16 | 2500 | 1.4431 |
| 1.5023 | 0.192 | 3000 | 1.4393 |
| 1.506 | 0.224 | 3500 | 1.4377 |
| 1.4887 | 0.256 | 4000 | 1.4342 |
| 1.4942 | 0.288 | 4500 | 1.4334 |
| 1.4826 | 0.32 | 5000 | 1.4307 |
| 1.4895 | 0.352 | 5500 | 1.4269 |
| 1.4854 | 0.384 | 6000 | 1.4249 |
| 1.4799 | 0.416 | 6500 | 1.4246 |
| 1.4837 | 0.448 | 7000 | 1.4227 |
| 1.4766 | 0.48 | 7500 | 1.4223 |
| 1.4799 | 0.512 | 8000 | 1.4206 |
| 1.4728 | 0.544 | 8500 | 1.4177 |
| 1.4753 | 0.576 | 9000 | 1.4173 |
| 1.4705 | 0.608 | 9500 | 1.4153 |
| 1.4679 | 0.64 | 10000 | 1.4159 |
| 1.4646 | 0.672 | 10500 | 1.4163 |
| 1.4601 | 0.704 | 11000 | 1.4135 |
| 1.4648 | 0.736 | 11500 | 1.4113 |
| 1.4618 | 0.768 | 12000 | 1.4109 |
| 1.4644 | 0.8 | 12500 | 1.4096 |
| 1.4593 | 0.832 | 13000 | 1.4084 |
| 1.4629 | 0.864 | 13500 | 1.4080 |
| 1.4565 | 0.896 | 14000 | 1.4079 |
| 1.4502 | 0.928 | 14500 | 1.4043 |
| 1.4558 | 0.96 | 15000 | 1.4024 |
| 1.45 | 0.992 | 15500 | 1.4040 |
| 1.3885 | 1.024 | 16000 | 1.4058 |
| 1.3681 | 1.056 | 16500 | 1.4071 |
| 1.3719 | 1.088 | 17000 | 1.4074 |
| 1.3687 | 1.12 | 17500 | 1.4063 |
| 1.3736 | 1.152 | 18000 | 1.4067 |
| 1.3767 | 1.184 | 18500 | 1.4061 |
| 1.3764 | 1.216 | 19000 | 1.4036 |
| 1.3751 | 1.248 | 19500 | 1.4031 |
| 1.3698 | 1.28 | 20000 | 1.4031 |
| 1.3764 | 1.312 | 20500 | 1.4024 |
| 1.379 | 1.3440 | 21000 | 1.4012 |
| 1.3758 | 1.376 | 21500 | 1.3990 |
| 1.3764 | 1.408 | 22000 | 1.3996 |
| 1.3715 | 1.44 | 22500 | 1.3982 |
| 1.3775 | 1.472 | 23000 | 1.3976 |
| 1.3719 | 1.504 | 23500 | 1.3974 |
| 1.3745 | 1.536 | 24000 | 1.3973 |
| 1.3704 | 1.568 | 24500 | 1.3961 |
| 1.3659 | 1.6 | 25000 | 1.3950 |
| 1.3665 | 1.6320 | 25500 | 1.3947 |
| 1.3628 | 1.6640 | 26000 | 1.3923 |
| 1.367 | 1.696 | 26500 | 1.3915 |
| 1.3616 | 1.728 | 27000 | 1.3899 |
| 1.3671 | 1.76 | 27500 | 1.3891 |
| 1.3651 | 1.792 | 28000 | 1.3884 |
| 1.3609 | 1.8240 | 28500 | 1.3872 |
| 1.3647 | 1.8560 | 29000 | 1.3871 |
| 1.3595 | 1.888 | 29500 | 1.3852 |
| 1.3579 | 1.92 | 30000 | 1.3845 |
| 1.3575 | 1.952 | 30500 | 1.3837 |
| 1.3576 | 1.984 | 31000 | 1.3835 |
| 1.3102 | 2.016 | 31500 | 1.3964 |
| 1.2595 | 2.048 | 32000 | 1.3966 |
| 1.2622 | 2.08 | 32500 | 1.3978 |
| 1.2606 | 2.112 | 33000 | 1.3967 |
| 1.2665 | 2.144 | 33500 | 1.3982 |
| 1.2658 | 2.176 | 34000 | 1.3974 |
| 1.2574 | 2.208 | 34500 | 1.3971 |
| 1.2584 | 2.24 | 35000 | 1.3963 |
| 1.2635 | 2.2720 | 35500 | 1.3970 |
| 1.2579 | 2.304 | 36000 | 1.3956 |
| 1.2633 | 2.336 | 36500 | 1.3956 |
| 1.2602 | 2.368 | 37000 | 1.3952 |
| 1.2597 | 2.4 | 37500 | 1.3953 |
| 1.2635 | 2.432 | 38000 | 1.3948 |
| 1.2646 | 2.464 | 38500 | 1.3947 |
| 1.2609 | 2.496 | 39000 | 1.3946 |
| 1.2562 | 2.528 | 39500 | 1.3941 |
| 1.2586 | 2.56 | 40000 | 1.3943 |
| 1.2604 | 2.592 | 40500 | 1.3940 |
| 1.2636 | 2.624 | 41000 | 1.3940 |
| 1.2635 | 2.656 | 41500 | 1.3940 |
| 1.2587 | 2.6880 | 42000 | 1.3938 |
| 1.2603 | 2.7200 | 42500 | 1.3939 |
| 1.2592 | 2.752 | 43000 | 1.3937 |
| 1.2568 | 2.784 | 43500 | 1.3934 |
| 1.2595 | 2.816 | 44000 | 1.3936 |
| 1.2565 | 2.848 | 44500 | 1.3935 |
| 1.2585 | 2.88 | 45000 | 1.3936 |
| 1.2624 | 2.912 | 45500 | 1.3933 |
| 1.2581 | 2.944 | 46000 | 1.3934 |
| 1.2571 | 2.976 | 46500 | 1.3934 |
### Framework versions
- PEFT 0.10.0
- Transformers 4.40.2
- Pytorch 2.3.0
- Datasets 2.19.1
- Tokenizers 0.19.1 |
fine-tuned/test-run | fine-tuned | 2024-05-20T09:35:51Z | 9 | 0 | sentence-transformers | [
"sentence-transformers",
"safetensors",
"bert",
"feature-extraction",
"sentence-similarity",
"mteb",
"Argumentation",
"Data",
"Research",
"Corpus",
"Analysis",
"custom_code",
"en",
"dataset:fine-tuned/test-run",
"dataset:allenai/c4",
"license:apache-2.0",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] | feature-extraction | 2024-05-16T09:34:10Z | ---
license: apache-2.0
datasets:
- fine-tuned/test-run
- allenai/c4
language:
- en
pipeline_tag: feature-extraction
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- mteb
- Argumentation
- Data
- Research
- Corpus
- Analysis
---
This model is a fine-tuned version of [**jinaai/jina-embeddings-v2-base-en**](https://huggingface.co/jinaai/jina-embeddings-v2-base-en) designed for the following use case:
academic research for argumentation data
## How to Use
This model can be easily integrated into your NLP pipeline for tasks such as text classification, sentiment analysis, entity recognition, and more. Here's a simple example to get you started:
```python
from sentence_transformers import SentenceTransformer
from sentence_transformers.util import cos_sim
model = SentenceTransformer(
'fine-tuned/test-run',
trust_remote_code=True
)
embeddings = model.encode([
'first text to embed',
'second text to embed'
])
print(cos_sim(embeddings[0], embeddings[1]))
```
|
shyp/output | shyp | 2024-05-20T09:35:42Z | 1 | 0 | peft | [
"peft",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:meta-llama/Meta-Llama-3-8B",
"base_model:adapter:meta-llama/Meta-Llama-3-8B",
"license:llama3",
"region:us"
] | null | 2024-05-20T09:35:32Z | ---
license: llama3
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: meta-llama/Meta-Llama-3-8B
model-index:
- name: output
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. -->
# output
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 48
- eval_batch_size: 24
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 96
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 3
### Framework versions
- PEFT 0.7.1
- Transformers 4.38.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.15.2 |
costazd/q-FrozenLake-v1-4x4-noSlippery | costazd | 2024-05-20T09:29:02Z | 0 | 0 | null | [
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | reinforcement-learning | 2024-05-20T09:29:00Z | ---
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="costazd/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"])
```
|
fzzhang/mistralv1_spectral_r8_5e5_e05_merged | fzzhang | 2024-05-20T09:27:47Z | 6 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-19T22:24:08Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
abhiaim12/finetuning-emotion-model | abhiaim12 | 2024-05-20T09:21:04Z | 121 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:emotion",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2024-05-20T09:10:58Z | ---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- emotion
metrics:
- accuracy
- f1
model-index:
- name: finetuning-emotion-model
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: emotion
type: emotion
config: split
split: validation
args: split
metrics:
- name: Accuracy
type: accuracy
value: 0.9345
- name: F1
type: f1
value: 0.9344074719710947
---
<!-- 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. -->
# finetuning-emotion-model
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1533
- Accuracy: 0.9345
- F1: 0.9344
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| No log | 1.0 | 250 | 0.1673 | 0.929 | 0.9294 |
| 0.1654 | 2.0 | 500 | 0.1533 | 0.9345 | 0.9344 |
### Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
|
SUWU123/llama2 | SUWU123 | 2024-05-20T09:20:06Z | 0 | 0 | null | [
"license:apache-2.0",
"region:us"
] | null | 2024-05-20T09:20:06Z | ---
license: apache-2.0
---
|
fishjojo1/whisper-tiny-til-asr | fishjojo1 | 2024-05-20T09:17:16Z | 127 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"base_model:openai/whisper-tiny.en",
"base_model:finetune:openai/whisper-tiny.en",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | automatic-speech-recognition | 2024-05-20T08:20:20Z | ---
license: apache-2.0
base_model: openai/whisper-tiny.en
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-tiny-til-asr
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-tiny-til-asr
This model is a fine-tuned version of [openai/whisper-tiny.en](https://huggingface.co/openai/whisper-tiny.en) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0001
- Wer: 0.0166
## 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: 3.7500000000000003e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 1000
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:------:|:----:|:---------------:|:------:|
| 0.002 | 1.0152 | 200 | 0.0040 | 0.1163 |
| 0.0001 | 2.0305 | 400 | 0.0003 | 0.0499 |
| 0.0001 | 3.0457 | 600 | 0.0003 | 0.0499 |
| 0.0 | 4.0609 | 800 | 0.0001 | 0.0166 |
| 0.0 | 5.0761 | 1000 | 0.0001 | 0.0166 |
### Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
|
S4kana/Anime_Picture | S4kana | 2024-05-20T09:17:00Z | 0 | 0 | null | [
"license:apache-2.0",
"region:us"
] | null | 2024-05-20T09:17:00Z | ---
license: apache-2.0
---
|
zee0110/a2c-PandaReachDense-v3 | zee0110 | 2024-05-20T09:15:03Z | 0 | 0 | stable-baselines3 | [
"stable-baselines3",
"PandaReachDense-v3",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | reinforcement-learning | 2024-05-20T09:10:37Z | ---
library_name: stable-baselines3
tags:
- PandaReachDense-v3
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: A2C
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: PandaReachDense-v3
type: PandaReachDense-v3
metrics:
- type: mean_reward
value: -0.22 +/- 0.11
name: mean_reward
verified: false
---
# **A2C** Agent playing **PandaReachDense-v3**
This is a trained model of a **A2C** agent playing **PandaReachDense-v3**
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
...
```
|
thorirhrafn/GPT1B_domar_RLHF_rouge | thorirhrafn | 2024-05-20T09:14:46Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-05-19T11:18:18Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
lenatr99/loha_fine_tuned_cb_XLMroberta | lenatr99 | 2024-05-20T09:09:51Z | 1 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"generated_from_trainer",
"base_model:FacebookAI/xlm-roberta-base",
"base_model:adapter:FacebookAI/xlm-roberta-base",
"license:mit",
"region:us"
] | null | 2024-05-20T09:09:45Z | ---
license: mit
library_name: peft
tags:
- generated_from_trainer
base_model: xlm-roberta-base
metrics:
- accuracy
- f1
model-index:
- name: loha_fine_tuned_cb_XLMroberta
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. -->
# loha_fine_tuned_cb_XLMroberta
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.3380
- Accuracy: 0.3182
- F1: 0.1536
## 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
- training_steps: 400
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|
| 0.8809 | 3.5714 | 50 | 1.2255 | 0.3182 | 0.1536 |
| 0.7544 | 7.1429 | 100 | 1.2817 | 0.3182 | 0.1536 |
| 0.7672 | 10.7143 | 150 | 1.3164 | 0.3182 | 0.1536 |
| 0.7357 | 14.2857 | 200 | 1.3296 | 0.3182 | 0.1536 |
| 0.7661 | 17.8571 | 250 | 1.3282 | 0.3182 | 0.1536 |
| 0.7522 | 21.4286 | 300 | 1.3353 | 0.3182 | 0.1536 |
| 0.7208 | 25.0 | 350 | 1.3379 | 0.3182 | 0.1536 |
| 0.7377 | 28.5714 | 400 | 1.3380 | 0.3182 | 0.1536 |
### Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
tedad09/ProvaLoRA | tedad09 | 2024-05-20T09:06:52Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-05-20T09:06:50Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
tmnam/vihealthbert-w_unsup-SynPD | tmnam | 2024-05-20T09:04:19Z | 57 | 0 | transformers | [
"transformers",
"safetensors",
"roberta",
"fill-mask",
"generated_from_trainer",
"dataset:tmnam20/pretrained-vn-med-nli",
"base_model:demdecuong/vihealthbert-base-word",
"base_model:finetune:demdecuong/vihealthbert-base-word",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | 2024-05-09T05:51:14Z | ---
base_model: demdecuong/vihealthbert-base-word
tags:
- generated_from_trainer
datasets:
- tmnam20/pretrained-vn-med-nli
metrics:
- accuracy
model-index:
- name: vihealthbert-w_unsup-SynPD
results:
- task:
name: Masked Language Modeling
type: fill-mask
dataset:
name: tmnam20/pretrained-vn-med-nli all
type: tmnam20/pretrained-vn-med-nli
args: all
metrics:
- name: Accuracy
type: accuracy
value: 0.6891028971951825
---
<!-- 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. -->
# vihealthbert-w_unsup-SynPD
This model is a fine-tuned version of [demdecuong/vihealthbert-base-word](https://huggingface.co/demdecuong/vihealthbert-base-word) on the tmnam20/pretrained-vn-med-nli all dataset.
It achieves the following results on the evaluation set:
- Loss: 1.5579
- Accuracy: 0.6891
## 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: 3e-05
- train_batch_size: 32
- eval_batch_size: 16
- seed: 19144
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:------:|:-----:|:---------------:|:--------:|
| 5.8543 | 0.3446 | 2000 | 3.8967 | 0.3950 |
| 3.4544 | 0.6893 | 4000 | 2.8119 | 0.5306 |
| 2.8312 | 1.0339 | 6000 | 2.4040 | 0.5771 |
| 2.5914 | 1.3786 | 8000 | 2.6482 | 0.5350 |
| 2.5649 | 1.7232 | 10000 | 2.1335 | 0.6087 |
| 2.2749 | 2.0679 | 12000 | 1.9895 | 0.6282 |
| 2.1572 | 2.4125 | 14000 | 1.9313 | 0.6353 |
| 2.1009 | 2.7572 | 16000 | 1.8646 | 0.6429 |
| 2.0609 | 3.1018 | 18000 | 1.8572 | 0.6450 |
| 2.0885 | 3.4465 | 20000 | 1.9489 | 0.6285 |
| 1.9891 | 3.7911 | 22000 | 1.7700 | 0.6583 |
| 1.9368 | 4.1358 | 24000 | 1.7398 | 0.6609 |
| 1.9003 | 4.4804 | 26000 | 1.7165 | 0.6664 |
| 1.9058 | 4.8251 | 28000 | 1.7032 | 0.6670 |
| 1.859 | 5.1697 | 30000 | 1.6771 | 0.6718 |
| 1.8401 | 5.5144 | 32000 | 1.6652 | 0.6710 |
| 1.8181 | 5.8590 | 34000 | 1.6417 | 0.6754 |
| 1.8133 | 6.2037 | 36000 | 1.6431 | 0.6748 |
| 1.7888 | 6.5483 | 38000 | 1.6363 | 0.6755 |
| 1.7811 | 6.8930 | 40000 | 1.6205 | 0.6793 |
| 1.7481 | 7.2376 | 42000 | 1.6190 | 0.6807 |
| 1.7509 | 7.5823 | 44000 | 1.6142 | 0.6794 |
| 1.7517 | 7.9269 | 46000 | 1.5949 | 0.6819 |
| 1.7358 | 8.2716 | 48000 | 1.5909 | 0.6843 |
| 1.7287 | 8.6162 | 50000 | 1.5757 | 0.6851 |
| 1.7132 | 8.9609 | 52000 | 1.5671 | 0.6885 |
| 1.7042 | 9.3055 | 54000 | 1.5685 | 0.6867 |
| 1.7051 | 9.6502 | 56000 | 1.5609 | 0.6876 |
| 1.7051 | 9.9948 | 58000 | 1.5576 | 0.6883 |
### Framework versions
- Transformers 4.40.2
- Pytorch 2.2.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
|
reemmasoud/idv_vs_col_llama-3_PromptTuning_CAUSAL_LM_gradient_descent_v6 | reemmasoud | 2024-05-20T08:58:38Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-05-20T08:58:36Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
leafspark/Yi-1.5-9B-Chat-16K-Q3_K_S-GGUF | leafspark | 2024-05-20T08:54:15Z | 2 | 0 | null | [
"gguf",
"llama-cpp",
"gguf-my-repo",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2024-05-20T08:53:29Z | ---
license: apache-2.0
tags:
- llama-cpp
- gguf-my-repo
---
# leafspark/Yi-1.5-9B-Chat-16K-Q3_K_S-GGUF
This model was converted to GGUF format from [`01-ai/Yi-1.5-9B-Chat-16K`](https://huggingface.co/01-ai/Yi-1.5-9B-Chat-16K) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/01-ai/Yi-1.5-9B-Chat-16K) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew.
```bash
brew install ggerganov/ggerganov/llama.cpp
```
Invoke the llama.cpp server or the CLI.
CLI:
```bash
llama-cli --hf-repo leafspark/Yi-1.5-9B-Chat-16K-Q3_K_S-GGUF --model yi-1.5-9b-chat-16k.Q3_K_S.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo leafspark/Yi-1.5-9B-Chat-16K-Q3_K_S-GGUF --model yi-1.5-9b-chat-16k.Q3_K_S.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
```
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m yi-1.5-9b-chat-16k.Q3_K_S.gguf -n 128
```
|
prince-canuma/Llama-3-6B-v0.1-ckpt-32k | prince-canuma | 2024-05-20T08:51:48Z | 6 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-20T08:41:57Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
omar8/bpm-gpt-2 | omar8 | 2024-05-20T08:51:30Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"unsloth",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-05-19T22:23:45Z | ---
library_name: transformers
tags:
- unsloth
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
AlkQ/ppo-LunarLander-v2.1 | AlkQ | 2024-05-20T08:51:03Z | 4 | 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 | 2024-04-30T16:35:49Z | ---
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: -12.18 +/- 49.94
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': 200000
'learning_rate': 0.0003
'num_envs': 4
'num_steps': 256
'anneal_lr': True
'gae': True
'gamma': 0.99
'gae_lambda': 0.95
'num_minibatches': 8
'update_epochs': 4
'norm_adv': True
'clip_coef': 0.1
'clip_vloss': True
'ent_coef': 0.01
'vf_coef': 0.5
'max_grad_norm': 0.5
'target_kl': None
'repo_id': 'AlkQ/ppo-LunarLander-v2'
'batch_size': 1024
'minibatch_size': 128}
```
|
lenatr99/lora_fine_tuned_cb_XLMroberta | lenatr99 | 2024-05-20T08:49:54Z | 1 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"generated_from_trainer",
"base_model:FacebookAI/xlm-roberta-base",
"base_model:adapter:FacebookAI/xlm-roberta-base",
"license:mit",
"region:us"
] | null | 2024-05-20T08:49:47Z | ---
license: mit
library_name: peft
tags:
- generated_from_trainer
base_model: xlm-roberta-base
metrics:
- accuracy
- f1
model-index:
- name: lora_fine_tuned_cb_XLMroberta
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. -->
# lora_fine_tuned_cb_XLMroberta
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4225
- Accuracy: 0.3182
- F1: 0.1536
## 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
- training_steps: 400
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|
| 0.9083 | 3.5714 | 50 | 1.2624 | 0.3182 | 0.1536 |
| 0.7455 | 7.1429 | 100 | 1.4585 | 0.3182 | 0.1536 |
| 0.7714 | 10.7143 | 150 | 1.4354 | 0.3182 | 0.1536 |
| 0.721 | 14.2857 | 200 | 1.3749 | 0.3182 | 0.1536 |
| 0.7302 | 17.8571 | 250 | 1.4032 | 0.3182 | 0.1536 |
| 0.7313 | 21.4286 | 300 | 1.4237 | 0.3182 | 0.1536 |
| 0.6958 | 25.0 | 350 | 1.4302 | 0.3182 | 0.1536 |
| 0.7295 | 28.5714 | 400 | 1.4225 | 0.3182 | 0.1536 |
### Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
002amine/soccertwos | 002amine | 2024-05-20T08:47:39Z | 11 | 0 | ml-agents | [
"ml-agents",
"tensorboard",
"onnx",
"SoccerTwos",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SoccerTwos",
"region:us"
] | reinforcement-learning | 2024-05-20T08:42:56Z | ---
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: 002amine/soccertwos
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
r-psingh/my_cool_submission | r-psingh | 2024-05-20T08:46:00Z | 0 | 0 | null | [
"region:us"
] | null | 2024-05-20T08:41:21Z | # My Cool Submission
This repo contains a submission to the [S23DR Challenge](https://huggingface.co/spaces/usm3d/S23DR) (part of the [USM3D](https://usm3d.github.io/) workshop at CVPR2024). It was prepared by [r-psingh](https://huggingface.co/r-psingh).
|
chrisx01/tsetse-42 | chrisx01 | 2024-05-20T08:43:23Z | 79 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"mistral",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"8-bit",
"bitsandbytes",
"region:us"
] | text-generation | 2024-05-20T08:24:47Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
leafspark/Yi-1.5-9B-Chat-16K-Q2_K-GGUF | leafspark | 2024-05-20T08:42:01Z | 2 | 0 | null | [
"gguf",
"llama-cpp",
"gguf-my-repo",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2024-05-20T08:41:27Z | ---
license: apache-2.0
tags:
- llama-cpp
- gguf-my-repo
---
# leafspark/Yi-1.5-9B-Chat-16K-Q2_K-GGUF
This model was converted to GGUF format from [`01-ai/Yi-1.5-9B-Chat-16K`](https://huggingface.co/01-ai/Yi-1.5-9B-Chat-16K) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/01-ai/Yi-1.5-9B-Chat-16K) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew.
```bash
brew install ggerganov/ggerganov/llama.cpp
```
Invoke the llama.cpp server or the CLI.
CLI:
```bash
llama-cli --hf-repo leafspark/Yi-1.5-9B-Chat-16K-Q2_K-GGUF --model yi-1.5-9b-chat-16k.Q2_K.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo leafspark/Yi-1.5-9B-Chat-16K-Q2_K-GGUF --model yi-1.5-9b-chat-16k.Q2_K.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
```
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m yi-1.5-9b-chat-16k.Q2_K.gguf -n 128
```
|
mesa44/LunarLander-v2 | mesa44 | 2024-05-20T08:41:44Z | 0 | 0 | null | [
"tensorboard",
"LunarLander-v2",
"ppo",
"deep-reinforcement-learning",
"reinforcement-learning",
"custom-implementation",
"deep-rl-course",
"model-index",
"region:us"
] | reinforcement-learning | 2024-05-20T08:41:21Z | ---
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: 44.32 +/- 92.42
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': 100000
'learning_rate': 0.001
'num_envs': 8
'num_steps': 128
'anneal_lr': True
'gae': True
'gamma': 0.99
'gae_lambda': 0.95
'num_minibatches': 4
'update_epochs': 16
'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': 'mesa44/LunarLander-v2'
'batch_size': 1024
'minibatch_size': 256}
```
|
scarface247/ppo-SnowballTargettesting | scarface247 | 2024-05-20T08:31:12Z | 6 | 0 | ml-agents | [
"ml-agents",
"tensorboard",
"onnx",
"SnowballTarget",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SnowballTarget",
"region:us"
] | reinforcement-learning | 2024-05-20T08:11:20Z | ---
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: scarface247/ppo-SnowballTargettesting
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
lenatr99/prompt_fine_tuned_CB_XLMroberta | lenatr99 | 2024-05-20T08:23:25Z | 1 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"generated_from_trainer",
"base_model:FacebookAI/xlm-roberta-base",
"base_model:adapter:FacebookAI/xlm-roberta-base",
"license:mit",
"region:us"
] | null | 2024-05-20T08:23:22Z | ---
license: mit
library_name: peft
tags:
- generated_from_trainer
base_model: xlm-roberta-base
metrics:
- accuracy
- f1
model-index:
- name: prompt_fine_tuned_CB_XLMroberta
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. -->
# prompt_fine_tuned_CB_XLMroberta
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4733
- Accuracy: 0.3182
- F1: 0.1536
## 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: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 400
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|
| 0.9542 | 0.4545 | 50 | 1.1060 | 0.3182 | 0.1536 |
| 0.8627 | 0.9091 | 100 | 1.1621 | 0.3182 | 0.1536 |
| 0.6647 | 1.3636 | 150 | 1.2304 | 0.3182 | 0.1536 |
| 0.8065 | 1.8182 | 200 | 1.3215 | 0.3182 | 0.1536 |
| 0.7675 | 2.2727 | 250 | 1.3718 | 0.3182 | 0.1536 |
| 0.8203 | 2.7273 | 300 | 1.4238 | 0.3182 | 0.1536 |
| 0.7817 | 3.1818 | 350 | 1.4576 | 0.3182 | 0.1536 |
| 0.7012 | 3.6364 | 400 | 1.4733 | 0.3182 | 0.1536 |
### Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
MHHQ/nikoai3 | MHHQ | 2024-05-20T08:21:57Z | 0 | 0 | null | [
"license:openrail++",
"region:us"
] | null | 2024-05-20T08:21:07Z | ---
license: openrail++
---
|
cloudyu/Llama-3-70Bx2-MOE-GGUF | cloudyu | 2024-05-20T08:17:06Z | 4 | 0 | null | [
"gguf",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2024-05-20T07:13:42Z | quant version of cloudyu/Llama-3-70Bx2-MOE |
albertoramez/output_model | albertoramez | 2024-05-20T08:15:50Z | 65 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"layoutlmv2",
"document-question-answering",
"generated_from_trainer",
"base_model:microsoft/layoutlmv2-base-uncased",
"base_model:finetune:microsoft/layoutlmv2-base-uncased",
"license:cc-by-nc-sa-4.0",
"endpoints_compatible",
"region:us"
] | document-question-answering | 2024-05-17T11:27:54Z | ---
license: cc-by-nc-sa-4.0
base_model: microsoft/layoutlmv2-base-uncased
tags:
- generated_from_trainer
model-index:
- name: output_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. -->
# output_model
This model is a fine-tuned version of [microsoft/layoutlmv2-base-uncased](https://huggingface.co/microsoft/layoutlmv2-base-uncased) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
### Framework versions
- Transformers 4.40.2
- Pytorch 2.3.0+cpu
- Datasets 2.19.1
- Tokenizers 0.19.1
|
NikolayKozloff/Yi-1.5-9B-32K-Q6_K-GGUF | NikolayKozloff | 2024-05-20T08:15:03Z | 5 | 1 | null | [
"gguf",
"llama-cpp",
"gguf-my-repo",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-05-20T08:14:44Z | ---
license: apache-2.0
tags:
- llama-cpp
- gguf-my-repo
---
# NikolayKozloff/Yi-1.5-9B-32K-Q6_K-GGUF
This model was converted to GGUF format from [`01-ai/Yi-1.5-9B-32K`](https://huggingface.co/01-ai/Yi-1.5-9B-32K) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/01-ai/Yi-1.5-9B-32K) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew.
```bash
brew install ggerganov/ggerganov/llama.cpp
```
Invoke the llama.cpp server or the CLI.
CLI:
```bash
llama-cli --hf-repo NikolayKozloff/Yi-1.5-9B-32K-Q6_K-GGUF --model yi-1.5-9b-32k.Q6_K.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo NikolayKozloff/Yi-1.5-9B-32K-Q6_K-GGUF --model yi-1.5-9b-32k.Q6_K.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
```
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m yi-1.5-9b-32k.Q6_K.gguf -n 128
```
|
Zoyd/01-ai_Yi-1.5-9B-Chat-16K-5_0bpw_exl2 | Zoyd | 2024-05-20T08:11:59Z | 6 | 1 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:2403.04652",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"5-bit",
"exl2",
"region:us"
] | text-generation | 2024-05-20T07:24:57Z | ---
license: apache-2.0
---
**Exllamav2** quant (**exl2** / **5.0 bpw**) made with ExLlamaV2 v0.0.21
Other EXL2 quants:
| **Quant** | **Model Size** | **lm_head** |
| ----- | ---------- | ------- |
|<center>**[2.2](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-2_2bpw_exl2)**</center> | <center>2900 MB</center> | <center>6</center> |
|<center>**[2.5](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-2_5bpw_exl2)**</center> | <center>3171 MB</center> | <center>6</center> |
|<center>**[3.0](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-3_0bpw_exl2)**</center> | <center>3669 MB</center> | <center>6</center> |
|<center>**[3.5](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-3_5bpw_exl2)**</center> | <center>4162 MB</center> | <center>6</center> |
|<center>**[3.75](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-3_75bpw_exl2)**</center> | <center>4411 MB</center> | <center>6</center> |
|<center>**[4.0](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-4_0bpw_exl2)**</center> | <center>4657 MB</center> | <center>6</center> |
|<center>**[4.25](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-4_25bpw_exl2)**</center> | <center>4906 MB</center> | <center>6</center> |
|<center>**[5.0](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-5_0bpw_exl2)**</center> | <center>5648 MB</center> | <center>6</center> |
|<center>**[6.0](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-6_0bpw_exl2)**</center> | <center>6687 MB</center> | <center>8</center> |
|<center>**[6.5](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-6_5bpw_exl2)**</center> | <center>7178 MB</center> | <center>8</center> |
|<center>**[8.0](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-8_0bpw_exl2)**</center> | <center>8328 MB</center> | <center>8</center> |
<div align="center">
<picture>
<img src="https://raw.githubusercontent.com/01-ai/Yi/main/assets/img/Yi_logo_icon_light.svg" width="150px">
</picture>
</div>
<p align="center">
<a href="https://github.com/01-ai">🐙 GitHub</a> •
<a href="https://discord.gg/hYUwWddeAu">👾 Discord</a> •
<a href="https://twitter.com/01ai_yi">🐤 Twitter</a> •
<a href="https://github.com/01-ai/Yi-1.5/issues/2">💬 WeChat</a>
<br/>
<a href="https://arxiv.org/abs/2403.04652">📝 Paper</a> •
<a href="https://github.com/01-ai/Yi/tree/main?tab=readme-ov-file#faq">🙌 FAQ</a> •
<a href="https://github.com/01-ai/Yi/tree/main?tab=readme-ov-file#learning-hub">📗 Learning Hub</a>
</p>
# Intro
Yi-1.5 is an upgraded version of Yi. It is continuously pre-trained on Yi with a high-quality corpus of 500B tokens and fine-tuned on 3M diverse fine-tuning samples.
Compared with Yi, Yi-1.5 delivers stronger performance in coding, math, reasoning, and instruction-following capability, while still maintaining excellent capabilities in language understanding, commonsense reasoning, and reading comprehension.
<div align="center">
Model | Context Length | Pre-trained Tokens
| :------------: | :------------: | :------------: |
| Yi-1.5 | 4K, 16K, 32K | 3.6T
</div>
# Models
- Chat models
<div align="center">
| Name | Download |
| --------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Yi-1.5-34B-Chat | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-34B-Chat-16K | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-9B-Chat | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-9B-Chat-16K | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-6B-Chat | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
</div>
- Base models
<div align="center">
| Name | Download |
| ---------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Yi-1.5-34B | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-34B-32K | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-9B | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-9B-32K | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-6B | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
</div>
# Benchmarks
- Chat models
Yi-1.5-34B-Chat is on par with or excels beyond larger models in most benchmarks.
Yi-1.5-9B-Chat is the top performer among similarly sized open-source models.
- Base models
Yi-1.5-34B is on par with or excels beyond larger models in some benchmarks.
Yi-1.5-9B is the top performer among similarly sized open-source models.
# Quick Start
For getting up and running with Yi-1.5 models quickly, see [README](https://github.com/01-ai/Yi-1.5).
|
Zoyd/01-ai_Yi-1.5-9B-Chat-16K-4_25bpw_exl2 | Zoyd | 2024-05-20T08:11:45Z | 7 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:2403.04652",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"exl2",
"region:us"
] | text-generation | 2024-05-20T07:19:49Z | ---
license: apache-2.0
---
**Exllamav2** quant (**exl2** / **4.25 bpw**) made with ExLlamaV2 v0.0.21
Other EXL2 quants:
| **Quant** | **Model Size** | **lm_head** |
| ----- | ---------- | ------- |
|<center>**[2.2](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-2_2bpw_exl2)**</center> | <center>2900 MB</center> | <center>6</center> |
|<center>**[2.5](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-2_5bpw_exl2)**</center> | <center>3171 MB</center> | <center>6</center> |
|<center>**[3.0](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-3_0bpw_exl2)**</center> | <center>3669 MB</center> | <center>6</center> |
|<center>**[3.5](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-3_5bpw_exl2)**</center> | <center>4162 MB</center> | <center>6</center> |
|<center>**[3.75](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-3_75bpw_exl2)**</center> | <center>4411 MB</center> | <center>6</center> |
|<center>**[4.0](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-4_0bpw_exl2)**</center> | <center>4657 MB</center> | <center>6</center> |
|<center>**[4.25](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-4_25bpw_exl2)**</center> | <center>4906 MB</center> | <center>6</center> |
|<center>**[5.0](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-5_0bpw_exl2)**</center> | <center>5648 MB</center> | <center>6</center> |
|<center>**[6.0](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-6_0bpw_exl2)**</center> | <center>6687 MB</center> | <center>8</center> |
|<center>**[6.5](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-6_5bpw_exl2)**</center> | <center>7178 MB</center> | <center>8</center> |
|<center>**[8.0](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-8_0bpw_exl2)**</center> | <center>8328 MB</center> | <center>8</center> |
<div align="center">
<picture>
<img src="https://raw.githubusercontent.com/01-ai/Yi/main/assets/img/Yi_logo_icon_light.svg" width="150px">
</picture>
</div>
<p align="center">
<a href="https://github.com/01-ai">🐙 GitHub</a> •
<a href="https://discord.gg/hYUwWddeAu">👾 Discord</a> •
<a href="https://twitter.com/01ai_yi">🐤 Twitter</a> •
<a href="https://github.com/01-ai/Yi-1.5/issues/2">💬 WeChat</a>
<br/>
<a href="https://arxiv.org/abs/2403.04652">📝 Paper</a> •
<a href="https://github.com/01-ai/Yi/tree/main?tab=readme-ov-file#faq">🙌 FAQ</a> •
<a href="https://github.com/01-ai/Yi/tree/main?tab=readme-ov-file#learning-hub">📗 Learning Hub</a>
</p>
# Intro
Yi-1.5 is an upgraded version of Yi. It is continuously pre-trained on Yi with a high-quality corpus of 500B tokens and fine-tuned on 3M diverse fine-tuning samples.
Compared with Yi, Yi-1.5 delivers stronger performance in coding, math, reasoning, and instruction-following capability, while still maintaining excellent capabilities in language understanding, commonsense reasoning, and reading comprehension.
<div align="center">
Model | Context Length | Pre-trained Tokens
| :------------: | :------------: | :------------: |
| Yi-1.5 | 4K, 16K, 32K | 3.6T
</div>
# Models
- Chat models
<div align="center">
| Name | Download |
| --------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Yi-1.5-34B-Chat | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-34B-Chat-16K | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-9B-Chat | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-9B-Chat-16K | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-6B-Chat | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
</div>
- Base models
<div align="center">
| Name | Download |
| ---------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Yi-1.5-34B | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-34B-32K | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-9B | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-9B-32K | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-6B | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
</div>
# Benchmarks
- Chat models
Yi-1.5-34B-Chat is on par with or excels beyond larger models in most benchmarks.
Yi-1.5-9B-Chat is the top performer among similarly sized open-source models.
- Base models
Yi-1.5-34B is on par with or excels beyond larger models in some benchmarks.
Yi-1.5-9B is the top performer among similarly sized open-source models.
# Quick Start
For getting up and running with Yi-1.5 models quickly, see [README](https://github.com/01-ai/Yi-1.5).
|
Zoyd/01-ai_Yi-1.5-9B-Chat-16K-4_0bpw_exl2 | Zoyd | 2024-05-20T08:11:33Z | 6 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:2403.04652",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"exl2",
"region:us"
] | text-generation | 2024-05-20T07:18:02Z | ---
license: apache-2.0
---
**Exllamav2** quant (**exl2** / **4.0 bpw**) made with ExLlamaV2 v0.0.21
Other EXL2 quants:
| **Quant** | **Model Size** | **lm_head** |
| ----- | ---------- | ------- |
|<center>**[2.2](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-2_2bpw_exl2)**</center> | <center>2900 MB</center> | <center>6</center> |
|<center>**[2.5](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-2_5bpw_exl2)**</center> | <center>3171 MB</center> | <center>6</center> |
|<center>**[3.0](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-3_0bpw_exl2)**</center> | <center>3669 MB</center> | <center>6</center> |
|<center>**[3.5](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-3_5bpw_exl2)**</center> | <center>4162 MB</center> | <center>6</center> |
|<center>**[3.75](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-3_75bpw_exl2)**</center> | <center>4411 MB</center> | <center>6</center> |
|<center>**[4.0](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-4_0bpw_exl2)**</center> | <center>4657 MB</center> | <center>6</center> |
|<center>**[4.25](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-4_25bpw_exl2)**</center> | <center>4906 MB</center> | <center>6</center> |
|<center>**[5.0](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-5_0bpw_exl2)**</center> | <center>5648 MB</center> | <center>6</center> |
|<center>**[6.0](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-6_0bpw_exl2)**</center> | <center>6687 MB</center> | <center>8</center> |
|<center>**[6.5](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-6_5bpw_exl2)**</center> | <center>7178 MB</center> | <center>8</center> |
|<center>**[8.0](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-8_0bpw_exl2)**</center> | <center>8328 MB</center> | <center>8</center> |
<div align="center">
<picture>
<img src="https://raw.githubusercontent.com/01-ai/Yi/main/assets/img/Yi_logo_icon_light.svg" width="150px">
</picture>
</div>
<p align="center">
<a href="https://github.com/01-ai">🐙 GitHub</a> •
<a href="https://discord.gg/hYUwWddeAu">👾 Discord</a> •
<a href="https://twitter.com/01ai_yi">🐤 Twitter</a> •
<a href="https://github.com/01-ai/Yi-1.5/issues/2">💬 WeChat</a>
<br/>
<a href="https://arxiv.org/abs/2403.04652">📝 Paper</a> •
<a href="https://github.com/01-ai/Yi/tree/main?tab=readme-ov-file#faq">🙌 FAQ</a> •
<a href="https://github.com/01-ai/Yi/tree/main?tab=readme-ov-file#learning-hub">📗 Learning Hub</a>
</p>
# Intro
Yi-1.5 is an upgraded version of Yi. It is continuously pre-trained on Yi with a high-quality corpus of 500B tokens and fine-tuned on 3M diverse fine-tuning samples.
Compared with Yi, Yi-1.5 delivers stronger performance in coding, math, reasoning, and instruction-following capability, while still maintaining excellent capabilities in language understanding, commonsense reasoning, and reading comprehension.
<div align="center">
Model | Context Length | Pre-trained Tokens
| :------------: | :------------: | :------------: |
| Yi-1.5 | 4K, 16K, 32K | 3.6T
</div>
# Models
- Chat models
<div align="center">
| Name | Download |
| --------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Yi-1.5-34B-Chat | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-34B-Chat-16K | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-9B-Chat | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-9B-Chat-16K | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-6B-Chat | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
</div>
- Base models
<div align="center">
| Name | Download |
| ---------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Yi-1.5-34B | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-34B-32K | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-9B | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-9B-32K | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-6B | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
</div>
# Benchmarks
- Chat models
Yi-1.5-34B-Chat is on par with or excels beyond larger models in most benchmarks.
Yi-1.5-9B-Chat is the top performer among similarly sized open-source models.
- Base models
Yi-1.5-34B is on par with or excels beyond larger models in some benchmarks.
Yi-1.5-9B is the top performer among similarly sized open-source models.
# Quick Start
For getting up and running with Yi-1.5 models quickly, see [README](https://github.com/01-ai/Yi-1.5).
|
Zoyd/01-ai_Yi-1.5-9B-Chat-16K-3_5bpw_exl2 | Zoyd | 2024-05-20T08:11:11Z | 6 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:2403.04652",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"exl2",
"region:us"
] | text-generation | 2024-05-20T06:51:19Z | ---
license: apache-2.0
---
**Exllamav2** quant (**exl2** / **3.5 bpw**) made with ExLlamaV2 v0.0.21
Other EXL2 quants:
| **Quant** | **Model Size** | **lm_head** |
| ----- | ---------- | ------- |
|<center>**[2.2](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-2_2bpw_exl2)**</center> | <center>2900 MB</center> | <center>6</center> |
|<center>**[2.5](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-2_5bpw_exl2)**</center> | <center>3171 MB</center> | <center>6</center> |
|<center>**[3.0](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-3_0bpw_exl2)**</center> | <center>3669 MB</center> | <center>6</center> |
|<center>**[3.5](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-3_5bpw_exl2)**</center> | <center>4162 MB</center> | <center>6</center> |
|<center>**[3.75](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-3_75bpw_exl2)**</center> | <center>4411 MB</center> | <center>6</center> |
|<center>**[4.0](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-4_0bpw_exl2)**</center> | <center>4657 MB</center> | <center>6</center> |
|<center>**[4.25](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-4_25bpw_exl2)**</center> | <center>4906 MB</center> | <center>6</center> |
|<center>**[5.0](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-5_0bpw_exl2)**</center> | <center>5648 MB</center> | <center>6</center> |
|<center>**[6.0](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-6_0bpw_exl2)**</center> | <center>6687 MB</center> | <center>8</center> |
|<center>**[6.5](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-6_5bpw_exl2)**</center> | <center>7178 MB</center> | <center>8</center> |
|<center>**[8.0](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-8_0bpw_exl2)**</center> | <center>8328 MB</center> | <center>8</center> |
<div align="center">
<picture>
<img src="https://raw.githubusercontent.com/01-ai/Yi/main/assets/img/Yi_logo_icon_light.svg" width="150px">
</picture>
</div>
<p align="center">
<a href="https://github.com/01-ai">🐙 GitHub</a> •
<a href="https://discord.gg/hYUwWddeAu">👾 Discord</a> •
<a href="https://twitter.com/01ai_yi">🐤 Twitter</a> •
<a href="https://github.com/01-ai/Yi-1.5/issues/2">💬 WeChat</a>
<br/>
<a href="https://arxiv.org/abs/2403.04652">📝 Paper</a> •
<a href="https://github.com/01-ai/Yi/tree/main?tab=readme-ov-file#faq">🙌 FAQ</a> •
<a href="https://github.com/01-ai/Yi/tree/main?tab=readme-ov-file#learning-hub">📗 Learning Hub</a>
</p>
# Intro
Yi-1.5 is an upgraded version of Yi. It is continuously pre-trained on Yi with a high-quality corpus of 500B tokens and fine-tuned on 3M diverse fine-tuning samples.
Compared with Yi, Yi-1.5 delivers stronger performance in coding, math, reasoning, and instruction-following capability, while still maintaining excellent capabilities in language understanding, commonsense reasoning, and reading comprehension.
<div align="center">
Model | Context Length | Pre-trained Tokens
| :------------: | :------------: | :------------: |
| Yi-1.5 | 4K, 16K, 32K | 3.6T
</div>
# Models
- Chat models
<div align="center">
| Name | Download |
| --------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Yi-1.5-34B-Chat | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-34B-Chat-16K | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-9B-Chat | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-9B-Chat-16K | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-6B-Chat | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
</div>
- Base models
<div align="center">
| Name | Download |
| ---------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Yi-1.5-34B | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-34B-32K | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-9B | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-9B-32K | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-6B | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
</div>
# Benchmarks
- Chat models
Yi-1.5-34B-Chat is on par with or excels beyond larger models in most benchmarks.
Yi-1.5-9B-Chat is the top performer among similarly sized open-source models.
- Base models
Yi-1.5-34B is on par with or excels beyond larger models in some benchmarks.
Yi-1.5-9B is the top performer among similarly sized open-source models.
# Quick Start
For getting up and running with Yi-1.5 models quickly, see [README](https://github.com/01-ai/Yi-1.5).
|
Zoyd/01-ai_Yi-1.5-9B-Chat-16K-2_5bpw_exl2 | Zoyd | 2024-05-20T08:10:52Z | 6 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:2403.04652",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"exl2",
"region:us"
] | text-generation | 2024-05-20T06:35:56Z | ---
license: apache-2.0
---
**Exllamav2** quant (**exl2** / **2.5 bpw**) made with ExLlamaV2 v0.0.21
Other EXL2 quants:
| **Quant** | **Model Size** | **lm_head** |
| ----- | ---------- | ------- |
|<center>**[2.2](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-2_2bpw_exl2)**</center> | <center>2900 MB</center> | <center>6</center> |
|<center>**[2.5](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-2_5bpw_exl2)**</center> | <center>3171 MB</center> | <center>6</center> |
|<center>**[3.0](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-3_0bpw_exl2)**</center> | <center>3669 MB</center> | <center>6</center> |
|<center>**[3.5](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-3_5bpw_exl2)**</center> | <center>4162 MB</center> | <center>6</center> |
|<center>**[3.75](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-3_75bpw_exl2)**</center> | <center>4411 MB</center> | <center>6</center> |
|<center>**[4.0](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-4_0bpw_exl2)**</center> | <center>4657 MB</center> | <center>6</center> |
|<center>**[4.25](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-4_25bpw_exl2)**</center> | <center>4906 MB</center> | <center>6</center> |
|<center>**[5.0](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-5_0bpw_exl2)**</center> | <center>5648 MB</center> | <center>6</center> |
|<center>**[6.0](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-6_0bpw_exl2)**</center> | <center>6687 MB</center> | <center>8</center> |
|<center>**[6.5](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-6_5bpw_exl2)**</center> | <center>7178 MB</center> | <center>8</center> |
|<center>**[8.0](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-8_0bpw_exl2)**</center> | <center>8328 MB</center> | <center>8</center> |
<div align="center">
<picture>
<img src="https://raw.githubusercontent.com/01-ai/Yi/main/assets/img/Yi_logo_icon_light.svg" width="150px">
</picture>
</div>
<p align="center">
<a href="https://github.com/01-ai">🐙 GitHub</a> •
<a href="https://discord.gg/hYUwWddeAu">👾 Discord</a> •
<a href="https://twitter.com/01ai_yi">🐤 Twitter</a> •
<a href="https://github.com/01-ai/Yi-1.5/issues/2">💬 WeChat</a>
<br/>
<a href="https://arxiv.org/abs/2403.04652">📝 Paper</a> •
<a href="https://github.com/01-ai/Yi/tree/main?tab=readme-ov-file#faq">🙌 FAQ</a> •
<a href="https://github.com/01-ai/Yi/tree/main?tab=readme-ov-file#learning-hub">📗 Learning Hub</a>
</p>
# Intro
Yi-1.5 is an upgraded version of Yi. It is continuously pre-trained on Yi with a high-quality corpus of 500B tokens and fine-tuned on 3M diverse fine-tuning samples.
Compared with Yi, Yi-1.5 delivers stronger performance in coding, math, reasoning, and instruction-following capability, while still maintaining excellent capabilities in language understanding, commonsense reasoning, and reading comprehension.
<div align="center">
Model | Context Length | Pre-trained Tokens
| :------------: | :------------: | :------------: |
| Yi-1.5 | 4K, 16K, 32K | 3.6T
</div>
# Models
- Chat models
<div align="center">
| Name | Download |
| --------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Yi-1.5-34B-Chat | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-34B-Chat-16K | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-9B-Chat | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-9B-Chat-16K | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-6B-Chat | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
</div>
- Base models
<div align="center">
| Name | Download |
| ---------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Yi-1.5-34B | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-34B-32K | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-9B | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-9B-32K | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-6B | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
</div>
# Benchmarks
- Chat models
Yi-1.5-34B-Chat is on par with or excels beyond larger models in most benchmarks.
Yi-1.5-9B-Chat is the top performer among similarly sized open-source models.
- Base models
Yi-1.5-34B is on par with or excels beyond larger models in some benchmarks.
Yi-1.5-9B is the top performer among similarly sized open-source models.
# Quick Start
For getting up and running with Yi-1.5 models quickly, see [README](https://github.com/01-ai/Yi-1.5).
|
Zoyd/01-ai_Yi-1.5-9B-Chat-16K-2_2bpw_exl2 | Zoyd | 2024-05-20T08:10:42Z | 6 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:2403.04652",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"exl2",
"region:us"
] | text-generation | 2024-05-20T06:17:48Z | ---
license: apache-2.0
---
**Exllamav2** quant (**exl2** / **2.2 bpw**) made with ExLlamaV2 v0.0.21
Other EXL2 quants:
| **Quant** | **Model Size** | **lm_head** |
| ----- | ---------- | ------- |
|<center>**[2.2](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-2_2bpw_exl2)**</center> | <center>2900 MB</center> | <center>6</center> |
|<center>**[2.5](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-2_5bpw_exl2)**</center> | <center>3171 MB</center> | <center>6</center> |
|<center>**[3.0](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-3_0bpw_exl2)**</center> | <center>3669 MB</center> | <center>6</center> |
|<center>**[3.5](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-3_5bpw_exl2)**</center> | <center>4162 MB</center> | <center>6</center> |
|<center>**[3.75](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-3_75bpw_exl2)**</center> | <center>4411 MB</center> | <center>6</center> |
|<center>**[4.0](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-4_0bpw_exl2)**</center> | <center>4657 MB</center> | <center>6</center> |
|<center>**[4.25](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-4_25bpw_exl2)**</center> | <center>4906 MB</center> | <center>6</center> |
|<center>**[5.0](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-5_0bpw_exl2)**</center> | <center>5648 MB</center> | <center>6</center> |
|<center>**[6.0](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-6_0bpw_exl2)**</center> | <center>6687 MB</center> | <center>8</center> |
|<center>**[6.5](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-6_5bpw_exl2)**</center> | <center>7178 MB</center> | <center>8</center> |
|<center>**[8.0](https://huggingface.co/Zoyd/01-ai_Yi-1.5-9B-Chat-16K-8_0bpw_exl2)**</center> | <center>8328 MB</center> | <center>8</center> |
<div align="center">
<picture>
<img src="https://raw.githubusercontent.com/01-ai/Yi/main/assets/img/Yi_logo_icon_light.svg" width="150px">
</picture>
</div>
<p align="center">
<a href="https://github.com/01-ai">🐙 GitHub</a> •
<a href="https://discord.gg/hYUwWddeAu">👾 Discord</a> •
<a href="https://twitter.com/01ai_yi">🐤 Twitter</a> •
<a href="https://github.com/01-ai/Yi-1.5/issues/2">💬 WeChat</a>
<br/>
<a href="https://arxiv.org/abs/2403.04652">📝 Paper</a> •
<a href="https://github.com/01-ai/Yi/tree/main?tab=readme-ov-file#faq">🙌 FAQ</a> •
<a href="https://github.com/01-ai/Yi/tree/main?tab=readme-ov-file#learning-hub">📗 Learning Hub</a>
</p>
# Intro
Yi-1.5 is an upgraded version of Yi. It is continuously pre-trained on Yi with a high-quality corpus of 500B tokens and fine-tuned on 3M diverse fine-tuning samples.
Compared with Yi, Yi-1.5 delivers stronger performance in coding, math, reasoning, and instruction-following capability, while still maintaining excellent capabilities in language understanding, commonsense reasoning, and reading comprehension.
<div align="center">
Model | Context Length | Pre-trained Tokens
| :------------: | :------------: | :------------: |
| Yi-1.5 | 4K, 16K, 32K | 3.6T
</div>
# Models
- Chat models
<div align="center">
| Name | Download |
| --------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Yi-1.5-34B-Chat | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-34B-Chat-16K | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-9B-Chat | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-9B-Chat-16K | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-6B-Chat | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
</div>
- Base models
<div align="center">
| Name | Download |
| ---------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Yi-1.5-34B | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-34B-32K | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-9B | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-9B-32K | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
| Yi-1.5-6B | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) |
</div>
# Benchmarks
- Chat models
Yi-1.5-34B-Chat is on par with or excels beyond larger models in most benchmarks.
Yi-1.5-9B-Chat is the top performer among similarly sized open-source models.
- Base models
Yi-1.5-34B is on par with or excels beyond larger models in some benchmarks.
Yi-1.5-9B is the top performer among similarly sized open-source models.
# Quick Start
For getting up and running with Yi-1.5 models quickly, see [README](https://github.com/01-ai/Yi-1.5).
|
ericzhang1122/Subcellular_locallzation_35M_A100 | ericzhang1122 | 2024-05-20T08:10:08Z | 1 | 0 | peft | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:westlake-repl/SaProt_35M_AF2",
"base_model:adapter:westlake-repl/SaProt_35M_AF2",
"region:us"
] | null | 2024-05-20T08:10:06Z | ---
library_name: peft
base_model: westlake-repl/SaProt_35M_AF2
---
# Model Card for Model ID
This model is used for subcellular locallzation prediction<br><br> The digital label means: <br>0: <br>
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.11.1 |
scarface247/ppo-SnowballTarget | scarface247 | 2024-05-20T08:08:52Z | 9 | 0 | ml-agents | [
"ml-agents",
"tensorboard",
"onnx",
"SnowballTarget",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SnowballTarget",
"region:us"
] | reinforcement-learning | 2024-05-20T07:46:59Z | ---
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: scarface247/ppo-SnowballTarget
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
52101007-HuynhQuocTruong/vi-correction-model | 52101007-HuynhQuocTruong | 2024-05-20T08:04:36Z | 18 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"mbart",
"text2text-generation",
"generated_from_trainer",
"base_model:vinai/bartpho-syllable",
"base_model:finetune:vinai/bartpho-syllable",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text2text-generation | 2024-05-14T03:38:22Z | ---
base_model: vinai/bartpho-syllable
tags:
- text2text-generation
- generated_from_trainer
metrics:
- sacrebleu
model-index:
- name: vi-correction-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. -->
# vi-correction-model
This model is a fine-tuned version of [vinai/bartpho-syllable](https://huggingface.co/vinai/bartpho-syllable) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0561
- Sacrebleu: 22.9297
## 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: 12
- eval_batch_size: 12
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 48
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Sacrebleu |
|:-------------:|:-----:|:----:|:---------------:|:---------:|
| No log | 1.0 | 104 | 0.0988 | 17.3540 |
| No log | 2.0 | 208 | 0.0661 | 21.5130 |
| No log | 3.0 | 312 | 0.0593 | 22.4272 |
| No log | 4.0 | 416 | 0.0564 | 22.8821 |
| No log | 5.0 | 520 | 0.0561 | 22.9297 |
### Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
|
fzzhang/mistralv1_spectral_r8_1e5_e05 | fzzhang | 2024-05-20T08:03:04Z | 5 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"generated_from_trainer",
"base_model:mistralai/Mistral-7B-v0.1",
"base_model:adapter:mistralai/Mistral-7B-v0.1",
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T08:04:32Z | ---
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: mistralai/Mistral-7B-v0.1
model-index:
- name: mistralv1_spectral_r8_1e5_e05
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. -->
# mistralv1_spectral_r8_1e5_e05
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None 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: 1e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 0
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
### Training results
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.1
- Datasets 2.18.0
- Tokenizers 0.15.2 |
leafspark/Yi-1.5-34B-Chat-16K-Q2_K-GGUF | leafspark | 2024-05-20T08:00:06Z | 5 | 0 | null | [
"gguf",
"llama-cpp",
"gguf-my-repo",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2024-05-20T07:59:35Z | ---
license: apache-2.0
tags:
- llama-cpp
- gguf-my-repo
---
# leafspark/Yi-1.5-34B-Chat-16K-Q2_K-GGUF
This model was converted to GGUF format from [`01-ai/Yi-1.5-34B-Chat-16K`](https://huggingface.co/01-ai/Yi-1.5-34B-Chat-16K) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/01-ai/Yi-1.5-34B-Chat-16K) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew.
```bash
brew install ggerganov/ggerganov/llama.cpp
```
Invoke the llama.cpp server or the CLI.
CLI:
```bash
llama-cli --hf-repo leafspark/Yi-1.5-34B-Chat-16K-Q2_K-GGUF --model yi-1.5-34b-chat-16k.Q2_K.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo leafspark/Yi-1.5-34B-Chat-16K-Q2_K-GGUF --model yi-1.5-34b-chat-16k.Q2_K.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
```
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m yi-1.5-34b-chat-16k.Q2_K.gguf -n 128
```
|
Luisdahuis/Workshop_ViT | Luisdahuis | 2024-05-20T07:58:37Z | 196 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"vit",
"image-classification",
"generated_from_trainer",
"base_model:google/vit-base-patch16-224-in21k",
"base_model:finetune:google/vit-base-patch16-224-in21k",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | image-classification | 2024-05-20T07:56:48Z | ---
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Workshop_ViT
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. -->
# Workshop_ViT
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:
- Loss: 0.0628
- Accuracy: 0.9850
## 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
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:------:|:----:|:---------------:|:--------:|
| 0.0724 | 1.5385 | 100 | 0.0905 | 0.9774 |
| 0.0255 | 3.0769 | 200 | 0.0628 | 0.9850 |
### Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
|
ar08/tinyllama-nerd-gguf | ar08 | 2024-05-20T07:54:50Z | 4 | 0 | transformers | [
"transformers",
"gguf",
"llama",
"text-generation-inference",
"text-generation",
"en",
"dataset:yahma/alpaca-cleaned",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-20T06:53:12Z | ---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- llama
- gguf
datasets:
- yahma/alpaca-cleaned
library_name: transformers
pipeline_tag: text-generation
---
# Uploaded Model
- **Developed by:** ar08
- **License:** apache-2.0
## USAGE
To use this model, follow the steps below:
1. **Install the necessary packages:**
```python
# Install llama-cpp-python
pip install llama-cpp-python
# Install transformers from source - only needed for versions <= v4.34
pip install git+https://github.com/huggingface/transformers.git
# Install accelerate
pip install accelerate
```
2. **Instantiate the model:**
```python
from llama_cpp import Llama
# Define the model path
my_model_path = "your_downloaded_model_name/path"
CONTEXT_SIZE = 512
# Load the model
model = Llama(model_path=my_model_path, n_ctx=CONTEXT_SIZE)
```
3. **Generate text from a prompt:**
```python
def generate_text_from_prompt(user_prompt, max_tokens=100, temperature=0.3, top_p=0.1, echo=True, stop=["Q", "\n"]):
# Define the parameters
model_output = model(
user_prompt,
max_tokens=max_tokens,
temperature=temperature,
top_p=top_p,
echo=echo,
stop=stop,
)
return model_output["choices"][0]["text"].strip()
if __name__ == "__main__":
my_prompt = "What do you think about the inclusion policies in Tech companies?"
model_response = generate_text_from_prompt(my_prompt)
print(model_response)
```
``` |
Taha101/newpush | Taha101 | 2024-05-20T07:54:34Z | 9 | 0 | ml-agents | [
"ml-agents",
"tensorboard",
"onnx",
"SoccerTwos",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SoccerTwos",
"region:us"
] | reinforcement-learning | 2024-05-20T07:53:17Z | ---
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: Taha101/newpush
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
fzzhang/mistralv1_spectral_r8_1e4_e05 | fzzhang | 2024-05-20T07:54:22Z | 0 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"generated_from_trainer",
"base_model:mistralai/Mistral-7B-v0.1",
"base_model:adapter:mistralai/Mistral-7B-v0.1",
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T23:01:01Z | ---
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: mistralai/Mistral-7B-v0.1
model-index:
- name: mistralv1_spectral_r8_1e4_e05
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. -->
# mistralv1_spectral_r8_1e4_e05
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 4
- eval_batch_size: 8
- seed: 0
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
### Training results
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.1
- Datasets 2.18.0
- Tokenizers 0.15.2 |
fzzhang/mistralv1_spectral_r8_5e5_e05 | fzzhang | 2024-05-20T07:49:32Z | 0 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"generated_from_trainer",
"base_model:mistralai/Mistral-7B-v0.1",
"base_model:adapter:mistralai/Mistral-7B-v0.1",
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T22:16:12Z | ---
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: mistralai/Mistral-7B-v0.1
model-index:
- name: mistralv1_spectral_r8_5e5_e05
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. -->
# mistralv1_spectral_r8_5e5_e05
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 0
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
### Training results
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.1
- Datasets 2.18.0
- Tokenizers 0.15.2 |
Keerthanah2002/auvk | Keerthanah2002 | 2024-05-20T07:49:14Z | 0 | 0 | diffusers | [
"diffusers",
"safetensors",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | 2024-05-20T07:43:01Z | ---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### auvk Dreambooth model trained by Keerthanah2002 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:
|
omezzinemariem/mistral-text-to-RULE2_merged | omezzinemariem | 2024-05-20T07:48:01Z | 7 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-20T07:44:11Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
elcomendante/test_tolu1 | elcomendante | 2024-05-20T07:46:25Z | 0 | 0 | null | [
"tensorboard",
"safetensors",
"license:apache-2.0",
"region:us"
] | null | 2024-05-17T07:55:58Z | ---
license: apache-2.0
---
|
dugoalberto/DeepCoder_1.3_LoRA | dugoalberto | 2024-05-20T07:46:24Z | 3 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:deepseek-ai/deepseek-coder-1.3b-base",
"base_model:adapter:deepseek-ai/deepseek-coder-1.3b-base",
"license:other",
"region:us"
] | null | 2024-05-20T07:39:06Z | ---
license: other
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: deepseek-ai/deepseek-coder-1.3b-base
model-index:
- name: DeepCoder_1.3_LoRA
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. -->
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/albertodugo/huggingface/runs/86sfukd6)
# DeepCoder_1.3_LoRA
This model is a fine-tuned version of [deepseek-ai/deepseek-coder-1.3b-base](https://huggingface.co/deepseek-ai/deepseek-coder-1.3b-base) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- training_steps: 60
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.11.2.dev0
- Transformers 4.41.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
tsavage68/MedQA_L3_1000steps_1e6rate_05beat_CSFTDPO | tsavage68 | 2024-05-20T07:45:34Z | 6 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"trl",
"dpo",
"generated_from_trainer",
"conversational",
"base_model:meta-llama/Meta-Llama-3-8B-Instruct",
"base_model:finetune:meta-llama/Meta-Llama-3-8B-Instruct",
"license:llama3",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-20T07:41:54Z | ---
license: llama3
base_model: meta-llama/Meta-Llama-3-8B-Instruct
tags:
- trl
- dpo
- generated_from_trainer
model-index:
- name: MedQA_L3_1000steps_1e6rate_05beat_CSFTDPO
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# MedQA_L3_1000steps_1e6rate_05beat_CSFTDPO
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5717
- Rewards/chosen: -1.8210
- Rewards/rejected: -5.7186
- Rewards/accuracies: 0.8066
- Rewards/margins: 3.8976
- Logps/rejected: -32.7538
- Logps/chosen: -21.8647
- Logits/rejected: -1.0151
- Logits/chosen: -1.0132
## 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-06
- train_batch_size: 2
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- training_steps: 1000
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
| 0.7075 | 0.0489 | 50 | 0.6367 | 0.2363 | 0.0705 | 0.6571 | 0.1658 | -21.1755 | -17.7501 | -0.9379 | -0.9373 |
| 0.6451 | 0.0977 | 100 | 0.6114 | -0.8886 | -1.7629 | 0.6923 | 0.8743 | -24.8423 | -19.9998 | -0.9999 | -0.9992 |
| 0.7409 | 0.1466 | 150 | 0.6018 | -1.9813 | -3.3881 | 0.7297 | 1.4068 | -28.0927 | -22.1852 | -0.9814 | -0.9805 |
| 0.4181 | 0.1954 | 200 | 0.5971 | -1.4742 | -3.0996 | 0.7341 | 1.6254 | -27.5157 | -21.1711 | -0.9791 | -0.9778 |
| 0.7476 | 0.2443 | 250 | 0.5735 | -1.5098 | -3.3523 | 0.7648 | 1.8425 | -28.0212 | -21.2423 | -0.9317 | -0.9303 |
| 0.5351 | 0.2931 | 300 | 0.7384 | -1.9600 | -4.7179 | 0.7538 | 2.7579 | -30.7524 | -22.1427 | -0.9715 | -0.9699 |
| 0.3789 | 0.3420 | 350 | 0.6165 | -2.8286 | -5.5771 | 0.7846 | 2.7485 | -32.4706 | -23.8798 | -0.9876 | -0.9860 |
| 0.6639 | 0.3908 | 400 | 0.5874 | -1.6246 | -4.5259 | 0.7912 | 2.9013 | -30.3683 | -21.4718 | -1.0086 | -1.0070 |
| 1.046 | 0.4397 | 450 | 0.5833 | -1.4867 | -4.5791 | 0.8044 | 3.0924 | -30.4748 | -21.1961 | -0.9772 | -0.9753 |
| 1.1477 | 0.4885 | 500 | 0.5726 | -1.9020 | -4.7805 | 0.8022 | 2.8785 | -30.8775 | -22.0266 | -0.9644 | -0.9628 |
| 0.2869 | 0.5374 | 550 | 0.5733 | -1.9387 | -5.0557 | 0.8000 | 3.1170 | -31.4279 | -22.1000 | -0.9901 | -0.9887 |
| 0.3924 | 0.5862 | 600 | 0.5336 | -1.1994 | -4.6601 | 0.8066 | 3.4607 | -30.6367 | -20.6214 | -0.9897 | -0.9880 |
| 0.5685 | 0.6351 | 650 | 0.5600 | -0.6431 | -4.3081 | 0.8000 | 3.6650 | -29.9327 | -19.5088 | -1.0020 | -1.0002 |
| 0.5743 | 0.6839 | 700 | 0.5739 | -1.5294 | -5.3059 | 0.8000 | 3.7764 | -31.9282 | -21.2815 | -1.0088 | -1.0069 |
| 0.5395 | 0.7328 | 750 | 0.5778 | -1.6200 | -5.4658 | 0.8088 | 3.8459 | -32.2482 | -21.4626 | -1.0136 | -1.0117 |
| 0.3395 | 0.7816 | 800 | 0.5754 | -1.8314 | -5.7044 | 0.8000 | 3.8730 | -32.7253 | -21.8854 | -1.0148 | -1.0130 |
| 0.6214 | 0.8305 | 850 | 0.5752 | -1.8114 | -5.6937 | 0.8000 | 3.8823 | -32.7039 | -21.8454 | -1.0152 | -1.0133 |
| 0.9719 | 0.8793 | 900 | 0.5707 | -1.8135 | -5.7132 | 0.8066 | 3.8997 | -32.7430 | -21.8497 | -1.0147 | -1.0128 |
| 0.3164 | 0.9282 | 950 | 0.5710 | -1.8198 | -5.7127 | 0.8000 | 3.8929 | -32.7420 | -21.8623 | -1.0148 | -1.0129 |
| 0.1257 | 0.9770 | 1000 | 0.5717 | -1.8210 | -5.7186 | 0.8066 | 3.8976 | -32.7538 | -21.8647 | -1.0151 | -1.0132 |
### Framework versions
- Transformers 4.41.0
- Pytorch 2.0.0+cu117
- Datasets 2.19.1
- Tokenizers 0.19.1
|
Raneechu/combined2 | Raneechu | 2024-05-20T07:44:54Z | 0 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:meta-llama/Llama-2-7b-hf",
"base_model:adapter:meta-llama/Llama-2-7b-hf",
"license:llama2",
"region:us"
] | null | 2024-05-20T07:44:51Z | ---
license: llama2
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: meta-llama/Llama-2-7b-hf
model-index:
- name: combined2
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. -->
# combined2
This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 1
### Training results
### Framework versions
- Transformers 4.40.1
- Pytorch 2.1.1+cu121
- Datasets 2.14.5
- Tokenizers 0.19.1
## Training procedure
### Framework versions
- PEFT 0.6.2
|
kalytm/nous-2 | kalytm | 2024-05-20T07:43:27Z | 8 | 1 | transformers | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-04-09T14:46:09Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
Taha101/pocapoca | Taha101 | 2024-05-20T07:40:55Z | 33 | 0 | ml-agents | [
"ml-agents",
"tensorboard",
"onnx",
"SoccerTwos",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SoccerTwos",
"region:us"
] | reinforcement-learning | 2024-04-20T12:54:25Z | ---
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: Taha101/pocapoca
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
ukung/TinyMixtral-32x248M-GGUF | ukung | 2024-05-20T07:39:49Z | 6 | 0 | null | [
"gguf",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-05-20T07:10:05Z | ---
license: apache-2.0
---
|
poxd0809/Meta-Llama-3-8B-Instruct-Q4_K_M-GGUF | poxd0809 | 2024-05-20T07:39:29Z | 0 | 0 | null | [
"gguf",
"facebook",
"meta",
"pytorch",
"llama",
"llama-3",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"en",
"license:llama3",
"endpoints_compatible",
"region:us",
"conversational"
] | text-generation | 2024-05-20T07:39:10Z | ---
language:
- en
license: llama3
tags:
- facebook
- meta
- pytorch
- llama
- llama-3
- llama-cpp
- gguf-my-repo
pipeline_tag: text-generation
extra_gated_prompt: "### META LLAMA 3 COMMUNITY LICENSE AGREEMENT\nMeta Llama 3 Version\
\ Release Date: April 18, 2024\n\"Agreement\" means the terms and conditions for\
\ use, reproduction, distribution and modification of the Llama Materials set forth\
\ herein.\n\"Documentation\" means the specifications, manuals and documentation\
\ accompanying Meta Llama 3 distributed by Meta at https://llama.meta.com/get-started/.\n\
\"Licensee\" or \"you\" means you, or your employer or any other person or entity\
\ (if you are entering into this Agreement on such person or entity’s behalf), of\
\ the age required under applicable laws, rules or regulations to provide legal\
\ consent and that has legal authority to bind your employer or such other person\
\ or entity if you are entering in this Agreement on their behalf.\n\"Meta Llama\
\ 3\" means the foundational large language models and software and algorithms,\
\ including machine-learning model code, trained model weights, inference-enabling\
\ code, training-enabling code, fine-tuning enabling code and other elements of\
\ the foregoing distributed by Meta at https://llama.meta.com/llama-downloads.\n\
\"Llama Materials\" means, collectively, Meta’s proprietary Meta Llama 3 and Documentation\
\ (and any portion thereof) made available under this Agreement.\n\"Meta\" or \"\
we\" means Meta Platforms Ireland Limited (if you are located in or, if you are\
\ an entity, your principal place of business is in the EEA or Switzerland) and\
\ Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).\n\
\ \n1. License Rights and Redistribution.\na. Grant of Rights. You are granted\
\ a non-exclusive, worldwide, non-transferable and royalty-free limited license\
\ under Meta’s intellectual property or other rights owned by Meta embodied in the\
\ Llama Materials to use, reproduce, distribute, copy, create derivative works of,\
\ and make modifications to the Llama Materials.\nb. Redistribution and Use.\ni.\
\ If you distribute or make available the Llama Materials (or any derivative works\
\ thereof), or a product or service that uses any of them, including another AI\
\ model, you shall (A) provide a copy of this Agreement with any such Llama Materials;\
\ and (B) prominently display “Built with Meta Llama 3” on a related website, user\
\ interface, blogpost, about page, or product documentation. If you use the Llama\
\ Materials to create, train, fine tune, or otherwise improve an AI model, which\
\ is distributed or made available, you shall also include “Llama 3” at the beginning\
\ of any such AI model name.\nii. If you receive Llama Materials, or any derivative\
\ works thereof, from a Licensee as part of an integrated end user product, then\
\ Section 2 of this Agreement will not apply to you.\niii. You must retain in all\
\ copies of the Llama Materials that you distribute the following attribution notice\
\ within a “Notice” text file distributed as a part of such copies: “Meta Llama\
\ 3 is licensed under the Meta Llama 3 Community License, Copyright © Meta Platforms,\
\ Inc. All Rights Reserved.”\niv. Your use of the Llama Materials must comply with\
\ applicable laws and regulations (including trade compliance laws and regulations)\
\ and adhere to the Acceptable Use Policy for the Llama Materials (available at\
\ https://llama.meta.com/llama3/use-policy), which is hereby incorporated by reference\
\ into this Agreement.\nv. You will not use the Llama Materials or any output or\
\ results of the Llama Materials to improve any other large language model (excluding\
\ Meta Llama 3 or derivative works thereof).\n2. Additional Commercial Terms. If,\
\ on the Meta Llama 3 version release date, the monthly active users of the products\
\ or services made available by or for Licensee, or Licensee’s affiliates, is greater\
\ than 700 million monthly active users in the preceding calendar month, you must\
\ request a license from Meta, which Meta may grant to you in its sole discretion,\
\ and you are not authorized to exercise any of the rights under this Agreement\
\ unless or until Meta otherwise expressly grants you such rights.\n3. Disclaimer\
\ of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT\
\ AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF\
\ ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED,\
\ INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY,\
\ OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING\
\ THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME\
\ ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.\n\
4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER\
\ ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY,\
\ OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT,\
\ SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META\
\ OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n\
5. Intellectual Property.\na. No trademark licenses are granted under this Agreement,\
\ and in connection with the Llama Materials, neither Meta nor Licensee may use\
\ any name or mark owned by or associated with the other or any of its affiliates,\
\ except as required for reasonable and customary use in describing and redistributing\
\ the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you\
\ a license to use “Llama 3” (the “Mark”) solely as required to comply with the\
\ last sentence of Section 1.b.i. You will comply with Meta’s brand guidelines (currently\
\ accessible at https://about.meta.com/brand/resources/meta/company-brand/ ). All\
\ goodwill arising out of your use of the Mark will inure to the benefit of Meta.\n\
b. Subject to Meta’s ownership of Llama Materials and derivatives made by or for\
\ Meta, with respect to any derivative works and modifications of the Llama Materials\
\ that are made by you, as between you and Meta, you are and will be the owner of\
\ such derivative works and modifications.\nc. If you institute litigation or other\
\ proceedings against Meta or any entity (including a cross-claim or counterclaim\
\ in a lawsuit) alleging that the Llama Materials or Meta Llama 3 outputs or results,\
\ or any portion of any of the foregoing, constitutes infringement of intellectual\
\ property or other rights owned or licensable by you, then any licenses granted\
\ to you under this Agreement shall terminate as of the date such litigation or\
\ claim is filed or instituted. You will indemnify and hold harmless Meta from and\
\ against any claim by any third party arising out of or related to your use or\
\ distribution of the Llama Materials.\n6. Term and Termination. The term of this\
\ Agreement will commence upon your acceptance of this Agreement or access to the\
\ Llama Materials and will continue in full force and effect until terminated in\
\ accordance with the terms and conditions herein. Meta may terminate this Agreement\
\ if you are in breach of any term or condition of this Agreement. Upon termination\
\ of this Agreement, you shall delete and cease use of the Llama Materials. Sections\
\ 3, 4 and 7 shall survive the termination of this Agreement.\n7. Governing Law\
\ and Jurisdiction. This Agreement will be governed and construed under the laws\
\ of the State of California without regard to choice of law principles, and the\
\ UN Convention on Contracts for the International Sale of Goods does not apply\
\ to this Agreement. The courts of California shall have exclusive jurisdiction\
\ of any dispute arising out of this Agreement.\n### Meta Llama 3 Acceptable Use\
\ Policy\nMeta is committed to promoting safe and fair use of its tools and features,\
\ including Meta Llama 3. If you access or use Meta Llama 3, you agree to this Acceptable\
\ Use Policy (“Policy”). The most recent copy of this policy can be found at [https://llama.meta.com/llama3/use-policy](https://llama.meta.com/llama3/use-policy)\n\
#### Prohibited Uses\nWe want everyone to use Meta Llama 3 safely and responsibly.\
\ You agree you will not use, or allow others to use, Meta Llama 3 to: 1. Violate\
\ the law or others’ rights, including to:\n 1. Engage in, promote, generate,\
\ contribute to, encourage, plan, incite, or further illegal or unlawful activity\
\ or content, such as:\n 1. Violence or terrorism\n 2. Exploitation\
\ or harm to children, including the solicitation, creation, acquisition, or dissemination\
\ of child exploitative content or failure to report Child Sexual Abuse Material\n\
\ 3. Human trafficking, exploitation, and sexual violence\n 4. The\
\ illegal distribution of information or materials to minors, including obscene\
\ materials, or failure to employ legally required age-gating in connection with\
\ such information or materials.\n 5. Sexual solicitation\n 6. Any\
\ other criminal activity\n 2. Engage in, promote, incite, or facilitate the\
\ harassment, abuse, threatening, or bullying of individuals or groups of individuals\n\
\ 3. Engage in, promote, incite, or facilitate discrimination or other unlawful\
\ or harmful conduct in the provision of employment, employment benefits, credit,\
\ housing, other economic benefits, or other essential goods and services\n 4.\
\ Engage in the unauthorized or unlicensed practice of any profession including,\
\ but not limited to, financial, legal, medical/health, or related professional\
\ practices\n 5. Collect, process, disclose, generate, or infer health, demographic,\
\ or other sensitive personal or private information about individuals without rights\
\ and consents required by applicable laws\n 6. Engage in or facilitate any action\
\ or generate any content that infringes, misappropriates, or otherwise violates\
\ any third-party rights, including the outputs or results of any products or services\
\ using the Llama Materials\n 7. Create, generate, or facilitate the creation\
\ of malicious code, malware, computer viruses or do anything else that could disable,\
\ overburden, interfere with or impair the proper working, integrity, operation\
\ or appearance of a website or computer system\n2. Engage in, promote, incite,\
\ facilitate, or assist in the planning or development of activities that present\
\ a risk of death or bodily harm to individuals, including use of Meta Llama 3 related\
\ to the following:\n 1. Military, warfare, nuclear industries or applications,\
\ espionage, use for materials or activities that are subject to the International\
\ Traffic Arms Regulations (ITAR) maintained by the United States Department of\
\ State\n 2. Guns and illegal weapons (including weapon development)\n 3.\
\ Illegal drugs and regulated/controlled substances\n 4. Operation of critical\
\ infrastructure, transportation technologies, or heavy machinery\n 5. Self-harm\
\ or harm to others, including suicide, cutting, and eating disorders\n 6. Any\
\ content intended to incite or promote violence, abuse, or any infliction of bodily\
\ harm to an individual\n3. Intentionally deceive or mislead others, including use\
\ of Meta Llama 3 related to the following:\n 1. Generating, promoting, or furthering\
\ fraud or the creation or promotion of disinformation\n 2. Generating, promoting,\
\ or furthering defamatory content, including the creation of defamatory statements,\
\ images, or other content\n 3. Generating, promoting, or further distributing\
\ spam\n 4. Impersonating another individual without consent, authorization,\
\ or legal right\n 5. Representing that the use of Meta Llama 3 or outputs are\
\ human-generated\n 6. Generating or facilitating false online engagement, including\
\ fake reviews and other means of fake online engagement\n4. Fail to appropriately\
\ disclose to end users any known dangers of your AI system\nPlease report any violation\
\ of this Policy, software “bug,” or other problems that could lead to a violation\
\ of this Policy through one of the following means:\n * Reporting issues with\
\ the model: [https://github.com/meta-llama/llama3](https://github.com/meta-llama/llama3)\n\
\ * Reporting risky content generated by the model:\n developers.facebook.com/llama_output_feedback\n\
\ * Reporting bugs and security concerns: facebook.com/whitehat/info\n * Reporting\
\ violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: [email protected]"
extra_gated_fields:
First Name: text
Last Name: text
Date of birth: date_picker
Country: country
Affiliation: text
geo: ip_location
? By clicking Submit below I accept the terms of the license and acknowledge that
the information I provide will be collected stored processed and shared in accordance
with the Meta Privacy Policy
: checkbox
extra_gated_description: The information you provide will be collected, stored, processed
and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/).
extra_gated_button_content: Submit
widget:
- example_title: Hello
messages:
- role: user
content: Hey my name is Julien! How are you?
- example_title: Winter holidays
messages:
- role: system
content: You are a helpful and honest assistant. Please, respond concisely and
truthfully.
- role: user
content: Can you recommend a good destination for Winter holidays?
- example_title: Programming assistant
messages:
- role: system
content: You are a helpful and honest code and programming assistant. Please,
respond concisely and truthfully.
- role: user
content: Write a function that computes the nth fibonacci number.
inference:
parameters:
max_new_tokens: 300
stop:
- <|end_of_text|>
- <|eot_id|>
---
# poxd0809/Meta-Llama-3-8B-Instruct-Q4_K_M-GGUF
This model was converted to GGUF format from [`meta-llama/Meta-Llama-3-8B-Instruct`](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew.
```bash
brew install ggerganov/ggerganov/llama.cpp
```
Invoke the llama.cpp server or the CLI.
CLI:
```bash
llama-cli --hf-repo poxd0809/Meta-Llama-3-8B-Instruct-Q4_K_M-GGUF --model meta-llama-3-8b-instruct.Q4_K_M.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo poxd0809/Meta-Llama-3-8B-Instruct-Q4_K_M-GGUF --model meta-llama-3-8b-instruct.Q4_K_M.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
```
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m meta-llama-3-8b-instruct.Q4_K_M.gguf -n 128
```
|
jayasuryajsk/Llama-3-4.2B | jayasuryajsk | 2024-05-20T07:38:35Z | 8 | 1 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-20T07:36:07Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
DownwardSpiral33/gpt2-imdb-pos-roberta16-256_0_05-2024.05.20.06.39 | DownwardSpiral33 | 2024-05-20T07:31:26Z | 134 | 0 | transformers | [
"transformers",
"safetensors",
"gpt2",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-20T07:31:06Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
voxmenthe/Yi-1.5-34B-Chat-16K-8bit | voxmenthe | 2024-05-20T07:28:26Z | 10 | 1 | mlx | [
"mlx",
"safetensors",
"llama",
"license:apache-2.0",
"region:us"
] | null | 2024-05-20T05:32:25Z | ---
license: apache-2.0
tags:
- mlx
---
# voxmenthe/Yi-1.5-34B-Chat-16K-8bit
The Model [voxmenthe/Yi-1.5-34B-Chat-16K-8bit](https://huggingface.co/voxmenthe/Yi-1.5-34B-Chat-16K-8bit) was converted to MLX format from [01-ai/Yi-1.5-34B-Chat-16K](https://huggingface.co/01-ai/Yi-1.5-34B-Chat-16K) using mlx-lm version **0.13.1**.
## Use with mlx
```bash
pip install mlx-lm
```
```python
from mlx_lm import load, generate
model, tokenizer = load("voxmenthe/Yi-1.5-34B-Chat-16K-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```
|
Niggendar/SDXLAnimePony_beta | Niggendar | 2024-05-20T07:19:27Z | 62 | 2 | diffusers | [
"diffusers",
"safetensors",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionXLPipeline",
"region:us"
] | text-to-image | 2024-05-20T07:12:19Z | ---
library_name: diffusers
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🧨 diffusers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
Magneto/lora_16bit_orpo | Magneto | 2024-05-20T07:19:20Z | 2 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"unsloth",
"trl",
"orpo",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-20T06:59:41Z | ---
library_name: transformers
tags:
- unsloth
- trl
- orpo
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
hunterg21/prueba | hunterg21 | 2024-05-20T07:18:42Z | 0 | 0 | null | [
"license:apache-2.0",
"region:us"
] | null | 2024-05-20T07:18:42Z | ---
license: apache-2.0
---
|
youngkeun2001/Llama-hkcode-Ko-3-8B | youngkeun2001 | 2024-05-20T07:17:03Z | 78 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"trl",
"sft",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
] | text-generation | 2024-05-20T07:11:57Z | ---
library_name: transformers
tags:
- trl
- sft
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
NikolayKozloff/Yi-1.5-9B-Chat-16K-Q8_0-GGUF | NikolayKozloff | 2024-05-20T07:15:00Z | 4 | 1 | null | [
"gguf",
"llama-cpp",
"gguf-my-repo",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2024-05-20T07:14:31Z | ---
license: apache-2.0
tags:
- llama-cpp
- gguf-my-repo
---
# NikolayKozloff/Yi-1.5-9B-Chat-16K-Q8_0-GGUF
This model was converted to GGUF format from [`01-ai/Yi-1.5-9B-Chat-16K`](https://huggingface.co/01-ai/Yi-1.5-9B-Chat-16K) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/01-ai/Yi-1.5-9B-Chat-16K) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew.
```bash
brew install ggerganov/ggerganov/llama.cpp
```
Invoke the llama.cpp server or the CLI.
CLI:
```bash
llama-cli --hf-repo NikolayKozloff/Yi-1.5-9B-Chat-16K-Q8_0-GGUF --model yi-1.5-9b-chat-16k.Q8_0.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo NikolayKozloff/Yi-1.5-9B-Chat-16K-Q8_0-GGUF --model yi-1.5-9b-chat-16k.Q8_0.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
```
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m yi-1.5-9b-chat-16k.Q8_0.gguf -n 128
```
|
jonyoon/code-search-net-tokenizer | jonyoon | 2024-05-20T07:14:21Z | 0 | 0 | transformers | [
"transformers",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-05-20T07:14:20Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
transcenderningning/Llama3-OpenBioLLM-8B | transcenderningning | 2024-05-20T07:13:46Z | 7 | 0 | transformers | [
"transformers",
"pytorch",
"safetensors",
"llama",
"text-generation",
"llama-3",
"Mixtral",
"instruct",
"finetune",
"chatml",
"DPO",
"RLHF",
"gpt4",
"distillation",
"en",
"arxiv:2305.18290",
"arxiv:2303.13375",
"arxiv:2212.13138",
"arxiv:2305.09617",
"arxiv:2402.07023",
"base_model:meta-llama/Meta-Llama-3-8B",
"base_model:finetune:meta-llama/Meta-Llama-3-8B",
"license:llama3",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-20T06:40:58Z | ---
base_model: meta-llama/Meta-Llama-3-8B
tags:
- llama-3
- llama
- Mixtral
- instruct
- finetune
- chatml
- DPO
- RLHF
- gpt4
- distillation
model-index:
- name: OpenBioLLM-8B
results: []
license: llama3
language:
- en
widget:
- example_title: OpenBioLLM-8B
messages:
- role: system
content: >-
You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience.
- role: user
content: How long does it take for newborn jaundice to go away?
output:
text: >-
Newborn jaundice, also known as neonatal jaundice, is a common condition in newborns where the yellowing of the skin and eyes occurs due to an elevated level of bilirubin in the blood. Bilirubin is a yellow pigment that forms when red blood cells break down. In most cases, newborn jaundice resolves on its own without any specific treatment.
The duration of newborn jaundice can vary depending on several factors such as the underlying cause, gestational age at birth, and individual variations in bilirubin metabolism. Here are some general guidelines:
1. Physiological jaundice: This is the most common type of newborn jaundice and usually appears within 24-72 hours after birth. It tends to peak between the second and fifth day of life and gradually improves over the next week or two. By the time the baby is one week old, the jaundice should have mostly resolved.
2. Breast milk jaundice: This type of jaundice occurs in breastfed babies and may appear later than physiological jaundice, typically between the fifth and fourteenth day of life. It tends to persist for a longer duration but usually resolves within six weeks after birth.
3. Pathological jaundice: This type of jaundice is less common and occurs due to an underlying medical condition that affects bilirubin metabolism or liver function. The duration of pathological jaundice depends on the specific cause and may require treatment.
It's important for parents to monitor their newborn's jaundice closely and seek medical advice if the jaundice progresses rapidly, becomes severe, or is accompanied by other symptoms such as poor feeding, lethargy, or excessive sleepiness. In these cases, further evaluation and management may be necessary.
Remember that each baby is unique, and the timing of jaundice resolution can vary. If you have concerns about your newborn's jaundice, it's always best to consult with a healthcare professional for personalized advice and guidance.
---
<div align="center">
<img width="260px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/BrQCb95lmEIFz79QAmoNA.png"></div>
<div align="center">
<h1>Advancing Open-source Large Language Models in Medical Domain</h1>
</div>
<p align="center" style="margin-top: 0px;">
<a href="https://colab.research.google.com/drive/1F5oV20InEYeAJGmBwYF9NM_QhLmjBkKJ?usp=sharing">
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="OpenChat Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 10px; margin-top: 0px; margin-bottom: 0px;"/>
<span class="link-text" style=" margin-right: 5px;">Online Demo</span>
</a> |
<a href="https://github.com/openlifescience-ai">
<img src="https://github.githubassets.com/assets/GitHub-Mark-ea2971cee799.png" alt="GitHub Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/>
<span class="link-text" style=" margin-right: 5px;">GitHub</span>
</a> |
<a href="#">
<img src="https://github.com/alpayariyak/openchat/blob/master/assets/arxiv-logomark-small-square-border.png?raw=true" alt="ArXiv Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/>
<span class="link-text" style="margin-right: 5px;">Paper</span>
</a> |
<a href="https://discord.gg/A5Fjf5zC69">
<img src="https://cloud.githubusercontent.com/assets/6291467/26705903/96c2d66e-477c-11e7-9f4e-f3c0efe96c9a.png" alt="Discord Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/>
<span class="link-text">Discord</span>
</a>
</p>
Introducing OpenBioLLM-8B: A State-of-the-Art Open Source Biomedical Large Language Model
OpenBioLLM-8B is an advanced open source language model designed specifically for the biomedical domain. Developed by Saama AI Labs, this model leverages cutting-edge techniques to achieve state-of-the-art performance on a wide range of biomedical tasks.
🏥 **Biomedical Specialization**: OpenBioLLM-8B is tailored for the unique language and knowledge requirements of the medical and life sciences fields. It was fine-tuned on a vast corpus of high-quality biomedical data, enabling it to understand and generate text with domain-specific accuracy and fluency.
🎓 **Superior Performance**: With 8 billion parameters, OpenBioLLM-8B outperforms other open source biomedical language models of similar scale. It has also demonstrated better results compared to larger proprietary & open-source models like GPT-3.5 and Meditron-70B on biomedical benchmarks.
🧠 **Advanced Training Techniques**: OpenBioLLM-8B builds upon the powerful foundations of the **Meta-Llama-3-8B** and [Meta-Llama-3-8B](meta-llama/Meta-Llama-3-8B) models. It incorporates the DPO dataset and fine-tuning recipe along with a custom diverse medical instruction dataset. Key components of the training pipeline include:
<div align="center">
<img width="1200px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/oPchsJsEpQoGcGXVbh7YS.png">
</div>
- **Policy Optimization**: [Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)](https://arxiv.org/abs/2305.18290)
- **Ranking Dataset**: [berkeley-nest/Nectar](https://huggingface.co/datasets/berkeley-nest/Nectar)
- **Fine-tuning dataset**: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated)
This combination of cutting-edge techniques enables OpenBioLLM-8B to align with key capabilities and preferences for biomedical applications.
⚙️ **Release Details**:
- **Model Size**: 8 billion parameters
- **Quantization**: Optimized quantized versions available [Here](https://huggingface.co/aaditya/OpenBioLLM-Llama3-8B-GGUF)
- **Language(s) (NLP):** en
- **Developed By**: [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) from Saama AI Labs
- **License:** Meta-Llama License
- **Fine-tuned from models:** [meta-llama/Meta-Llama-3-8B](meta-llama/Meta-Llama-3-8B)
- **Resources for more information:**
- Paper: Coming soon
The model can be fine-tuned for more specialized tasks and datasets as needed.
OpenBioLLM-8B represents an important step forward in democratizing advanced language AI for the biomedical community. By leveraging state-of-the-art architectures and training techniques from leading open source efforts like Llama-3, we have created a powerful tool to accelerate innovation and discovery in healthcare and the life sciences.
We are excited to share OpenBioLLM-8B with researchers and developers around the world.
### Use with transformers
**Important: Please use the exact chat template provided by Llama-3 instruct version. Otherwise there will be a degradation in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less.**
See the snippet below for usage with Transformers:
```python
import transformers
import torch
model_id = "aaditya/OpenBioLLM-Llama3-8B"
pipeline = transformers.pipeline(
"text-generation",
model=model_id,
model_kwargs={"torch_dtype": torch.bfloat16},
device="auto",
)
messages = [
{"role": "system", "content": "You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience. Your name is OpenBioLLM, and you were developed by Saama AI Labs. who's willing to help answer the user's query with explanation. In your explanation, leverage your deep medical expertise such as relevant anatomical structures, physiological processes, diagnostic criteria, treatment guidelines, or other pertinent medical concepts. Use precise medical terminology while still aiming to make the explanation clear and accessible to a general audience."},
{"role": "user", "content": "How can i split a 3mg or 4mg waefin pill so i can get a 2.5mg pill?"},
]
prompt = pipeline.tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
terminators = [
pipeline.tokenizer.eos_token_id,
pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
]
outputs = pipeline(
prompt,
max_new_tokens=256,
eos_token_id=terminators,
do_sample=True,
temperature=0.0,
top_p=0.9,
)
print(outputs[0]["generated_text"][len(prompt):])
```
## **Training procedure**
### **Training hyperparameters**
<details>
<summary>Click to see details</summary>
- learning_rate: 0.0002
- lr_scheduler: cosine
- train_batch_size: 12
- eval_batch_size: 8
- GPU: H100 80GB SXM5
- num_devices: 1
- optimizer: adamw_bnb_8bit
- lr_scheduler_warmup_steps: 100
- num_epochs: 4
</details>
### **Peft hyperparameters**
<details>
<summary>Click to see details</summary>
- adapter: qlora
- lora_r: 128
- lora_alpha: 256
- lora_dropout: 0.05
- lora_target_linear: true
-lora_target_modules:
- q_proj
- v_proj
- k_proj
- o_proj
- gate_proj
- down_proj
- up_proj
</details>
### **Training results**
### **Framework versions**
- Transformers 4.39.3
- Pytorch 2.1.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.1
- Axolotl
- Lm harness for evaluation
# Benchmark Results
🔥 OpenBioLLM-8B demonstrates superior performance compared to larger models, such as GPT-3.5, Meditron-70B across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 72.50%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge.
🚨 The GPT-4, Med-PaLM-1, and Med-PaLM-2 results are taken from their official papers. Since Med-PaLM doesn't provide zero-shot accuracy, we are using 5-shot accuracy from their paper for comparison. All results presented are in the zero-shot setting, except for Med-PaLM-2 and Med-PaLM-1, which use 5-shot accuracy.
| | Clinical KG | Medical Genetics | Anatomy | Pro Medicine | College Biology | College Medicine | MedQA 4 opts | PubMedQA | MedMCQA | Avg |
|--------------------|-------------|------------------|---------|--------------|-----------------|------------------|--------------|----------|---------|-------|
| **OpenBioLLM-70B** | **92.93** | **93.197** | **83.904** | 93.75 | 93.827 | **85.749** | 78.162 | 78.97 | **74.014** | **86.05588** |
| Med-PaLM-2 (5-shot) | 88.3 | 90 | 77.8 | **95.2** | 94.4 | 80.9 | **79.7** | **79.2** | 71.3 | 84.08 |
| **GPT-4** | 86.04 | 91 | 80 | 93.01 | **95.14** | 76.88 | 78.87 | 75.2 | 69.52 | 82.85 |
| Med-PaLM-1 (Flan-PaLM, 5-shot) | 80.4 | 75 | 63.7 | 83.8 | 88.9 | 76.3 | 67.6 | 79 | 57.6 | 74.7 |
| **OpenBioLLM-8B** | 76.101 | 86.1 | 69.829 | 78.21 | 84.213 | 68.042 | 58.993 | 74.12 | 56.913 | 72.502 |
| Gemini-1.0 | 76.7 | 75.8 | 66.7 | 77.7 | 88 | 69.2 | 58 | 70.7 | 54.3 | 70.79 |
| GPT-3.5 Turbo 1106 | 74.71 | 74 | 72.79 | 72.79 | 72.91 | 64.73 | 57.71 | 72.66 | 53.79 | 66 |
| Meditron-70B | 66.79 | 69 | 53.33 | 71.69 | 76.38 | 63 | 57.1 | 76.6 | 46.85 | 64.52 |
| gemma-7b | 69.81 | 70 | 59.26 | 66.18 | 79.86 | 60.12 | 47.21 | 76.2 | 48.96 | 64.18 |
| Mistral-7B-v0.1 | 68.68 | 71 | 55.56 | 68.38 | 68.06 | 59.54 | 50.82 | 75.4 | 48.2 | 62.85 |
| Apollo-7B | 62.26 | 72 | 61.48 | 69.12 | 70.83 | 55.49 | 55.22 | 39.8 | 53.77 | 60 |
| MedAlpaca-7b | 57.36 | 69 | 57.04 | 67.28 | 65.28 | 54.34 | 41.71 | 72.8 | 37.51 | 58.03 |
| BioMistral-7B | 59.9 | 64 | 56.5 | 60.4 | 59 | 54.7 | 50.6 | 77.5 | 48.1 | 57.3 |
| AlpaCare-llama2-7b | 49.81 | 49 | 45.92 | 33.82 | 50 | 43.35 | 29.77 | 72.2 | 34.42 | 45.36 |
| ClinicalGPT | 30.56 | 27 | 30.37 | 19.48 | 25 | 24.27 | 26.08 | 63.8 | 28.18 | 30.52 |
<div align="center">
<img width="1600px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/_SzdcJSBjZyo8RS1bTEkP.png">
</div>
## Detailed Medical Subjectwise accuracy
# Use Cases & Examples
🚨 **Below results are from the quantized version of OpenBioLLM-70B**
# Summarize Clinical Notes
OpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries
# Answer Medical Questions
OpenBioLLM-70B can provide answers to a wide range of medical questions.
<details>
<summary>Click to see details</summary>
</details>
# Clinical Entity Recognition
OpenBioLLM-70B can perform advanced clinical entity recognition by identifying and extracting key medical concepts, such as diseases, symptoms, medications, procedures, and anatomical structures, from unstructured clinical text. By leveraging its deep understanding of medical terminology and context, the model can accurately annotate and categorize clinical entities, enabling more efficient information retrieval, data analysis, and knowledge discovery from electronic health records, research articles, and other biomedical text sources. This capability can support various downstream applications, such as clinical decision support, pharmacovigilance, and medical research.
# Biomarkers Extraction
# Classification
OpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization
# De-Identification
OpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA.
**Advisory Notice!**
While OpenBioLLM-70B & 8B leverages high-quality data sources, its outputs may still contain inaccuracies, biases, or misalignments that could pose risks if relied upon for medical decision-making without further testing and refinement. The model's performance has not yet been rigorously evaluated in randomized controlled trials or real-world healthcare environments.
Therefore, we strongly advise against using OpenBioLLM-70B & 8B for any direct patient care, clinical decision support, or other professional medical purposes at this time. Its use should be limited to research, development, and exploratory applications by qualified individuals who understand its limitations.
OpenBioLLM-70B & 8B are intended solely as a research tool to assist healthcare professionals and should never be considered a replacement for the professional judgment and expertise of a qualified medical doctor.
Appropriately adapting and validating OpenBioLLM-70B & 8B for specific medical use cases would require significant additional work, potentially including:
- Thorough testing and evaluation in relevant clinical scenarios
- Alignment with evidence-based guidelines and best practices
- Mitigation of potential biases and failure modes
- Integration with human oversight and interpretation
- Compliance with regulatory and ethical standards
Always consult a qualified healthcare provider for personal medical needs.
# Citation
If you find OpenBioLLM-70B & 8B useful in your work, please cite the model as follows:
```
@misc{OpenBioLLMs,
author = {Ankit Pal, Malaikannan Sankarasubbu},
title = {OpenBioLLMs: Advancing Open-Source Large Language Models for Healthcare and Life Sciences},
year = {2024},
publisher = {Hugging Face},
journal = {Hugging Face repository},
howpublished = {\url{https://huggingface.co/aaditya/OpenBioLLM-Llama3-70B}}
}
```
The accompanying paper is currently in progress and will be released soon.
<div align="center">
<h2> 💌 Contact </h2>
</div>
We look forward to hearing you and collaborating on this exciting project!
**Contributors:**
- [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) [aadityaura at gmail dot com]
- Saama AI Labs
- Note: I am looking for a funded PhD opportunity, especially if it fits my Responsible Generative AI, Multimodal LLMs, Geometric Deep Learning, and Healthcare AI skillset.
# References
We thank the [Meta Team](meta-llama/Meta-Llama-3-70B-Instruct) for their amazing models!
Result sources
- [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (https://arxiv.org/abs/2303.13375)
- [2] Med-PaLM-1 [Large Language Models Encode Clinical Knowledge](https://arxiv.org/abs/2212.13138)
- [3] Med-PaLM-2 [Towards Expert-Level Medical Question Answering with Large Language Models](https://arxiv.org/abs/2305.09617)
- [4] Gemini-1.0 [Gemini Goes to Med School](https://arxiv.org/abs/2402.07023) |
santoshtyss/lex-withEnd-inst-alpca-de | santoshtyss | 2024-05-20T07:12:51Z | 10 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-20T06:55:46Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
zee0110/ppo-SnowballTarget | zee0110 | 2024-05-20T07:08:10Z | 0 | 0 | ml-agents | [
"ml-agents",
"tensorboard",
"onnx",
"SnowballTarget",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SnowballTarget",
"region:us"
] | reinforcement-learning | 2024-05-20T07:08:06Z | ---
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: zee0110/ppo-SnowballTarget
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
leafspark/Yi-1.5-34B-Chat-16K-Q3_K_M-GGUF | leafspark | 2024-05-20T07:05:35Z | 1 | 2 | null | [
"gguf",
"llama-cpp",
"gguf-my-repo",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2024-05-20T07:04:53Z | ---
license: apache-2.0
tags:
- llama-cpp
- gguf-my-repo
---
# leafspark/Yi-1.5-34B-Chat-16K-Q3_K_M-GGUF
This model was converted to GGUF format from [`01-ai/Yi-1.5-34B-Chat-16K`](https://huggingface.co/01-ai/Yi-1.5-34B-Chat-16K) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/01-ai/Yi-1.5-34B-Chat-16K) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew.
```bash
brew install ggerganov/ggerganov/llama.cpp
```
Invoke the llama.cpp server or the CLI.
CLI:
```bash
llama-cli --hf-repo leafspark/Yi-1.5-34B-Chat-16K-Q3_K_M-GGUF --model yi-1.5-34b-chat-16k.Q3_K_M.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo leafspark/Yi-1.5-34B-Chat-16K-Q3_K_M-GGUF --model yi-1.5-34b-chat-16k.Q3_K_M.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
```
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m yi-1.5-34b-chat-16k.Q3_K_M.gguf -n 128
```
|
ukung/Llama3-IndoTunned-GGUF | ukung | 2024-05-20T06:59:48Z | 7 | 0 | null | [
"gguf",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-05-20T04:38:43Z | ---
license: apache-2.0
---
|
kalytm/nous-14 | kalytm | 2024-05-20T06:56:56Z | 236 | 0 | transformers | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-04-18T14:02:45Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
kalytm/nous-7 | kalytm | 2024-05-20T06:56:48Z | 170 | 0 | transformers | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-04-10T00:04:27Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
Vihanga22365/llama-3-8b-Instruct-bnb-4bit-aiaustin-demo | Vihanga22365 | 2024-05-20T06:54:13Z | 3 | 0 | transformers | [
"transformers",
"gguf",
"llama",
"text-generation-inference",
"unsloth",
"en",
"base_model:unsloth/llama-3-8b-Instruct-bnb-4bit",
"base_model:quantized:unsloth/llama-3-8b-Instruct-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2024-05-20T06:51:42Z | ---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- gguf
base_model: unsloth/llama-3-8b-Instruct-bnb-4bit
---
# Uploaded model
- **Developed by:** Vihanga22365
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b-Instruct-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
JamesKim/Gath_mistral_7b | JamesKim | 2024-05-20T06:49:55Z | 6 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-19T16:47:47Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
Niggendar/vendoPony16steps_v10 | Niggendar | 2024-05-20T06:38:55Z | 126 | 1 | diffusers | [
"diffusers",
"safetensors",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionXLPipeline",
"region:us"
] | text-to-image | 2024-05-20T06:26:15Z | ---
library_name: diffusers
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🧨 diffusers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
4season/final_model_test_v2 | 4season | 2024-05-20T06:35:29Z | 8 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"en",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-20T05:14:10Z | ---
license: apache-2.0
language:
- en
---
# 4season/final_model_test_v2
# **Introduction**
Supervised fine-tuning refers to a machine learning technique where a pre-trained model is further trained on a specific task or dataset with labeled examples (supervised learning). The process involves taking a model that has been pre-trained on a large general dataset and then adapting it to a more focused task by continuing the training using task-specific data.
This model is test version, alignment-tuned model.
We utilize state-of-the-art instruction fine-tuning methods including direct preference optimization (DPO).
|
fine-tuned/jina-embeddings-v2-base-en-5202024-55bm-webapp | fine-tuned | 2024-05-20T06:28:57Z | 7 | 0 | sentence-transformers | [
"sentence-transformers",
"safetensors",
"bert",
"feature-extraction",
"sentence-similarity",
"mteb",
"Legal",
"Regulations",
"Government",
"Compliance",
"Local",
"custom_code",
"en",
"dataset:fine-tuned/jina-embeddings-v2-base-en-5202024-55bm-webapp",
"dataset:allenai/c4",
"license:apache-2.0",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] | feature-extraction | 2024-05-20T06:28:43Z | ---
license: apache-2.0
datasets:
- fine-tuned/jina-embeddings-v2-base-en-5202024-55bm-webapp
- allenai/c4
language:
- en
pipeline_tag: feature-extraction
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- mteb
- Legal
- Regulations
- Government
- Compliance
- Local
---
This model is a fine-tuned version of [**jinaai/jina-embeddings-v2-base-en**](https://huggingface.co/jinaai/jina-embeddings-v2-base-en) designed for the following use case:
legal regulations search
## How to Use
This model can be easily integrated into your NLP pipeline for tasks such as text classification, sentiment analysis, entity recognition, and more. Here's a simple example to get you started:
```python
from sentence_transformers import SentenceTransformer
from sentence_transformers.util import cos_sim
model = SentenceTransformer(
'fine-tuned/jina-embeddings-v2-base-en-5202024-55bm-webapp',
trust_remote_code=True
)
embeddings = model.encode([
'first text to embed',
'second text to embed'
])
print(cos_sim(embeddings[0], embeddings[1]))
```
|
leafspark/Yi-1.5-34B-Chat-16K-Q8_0-GGUF | leafspark | 2024-05-20T06:28:28Z | 6 | 0 | null | [
"gguf",
"llama-cpp",
"gguf-my-repo",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2024-05-20T06:27:06Z | ---
license: apache-2.0
tags:
- llama-cpp
- gguf-my-repo
---
# leafspark/Yi-1.5-34B-Chat-16K-Q8_0-GGUF
This model was converted to GGUF format from [`01-ai/Yi-1.5-34B-Chat-16K`](https://huggingface.co/01-ai/Yi-1.5-34B-Chat-16K) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/01-ai/Yi-1.5-34B-Chat-16K) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew.
```bash
brew install ggerganov/ggerganov/llama.cpp
```
Invoke the llama.cpp server or the CLI.
CLI:
```bash
llama-cli --hf-repo leafspark/Yi-1.5-34B-Chat-16K-Q8_0-GGUF --model yi-1.5-34b-chat-16k.Q8_0.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo leafspark/Yi-1.5-34B-Chat-16K-Q8_0-GGUF --model yi-1.5-34b-chat-16k.Q8_0.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
```
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m yi-1.5-34b-chat-16k.Q8_0.gguf -n 128
```
|
jc1266/mistral_with_adapter_merged | jc1266 | 2024-05-20T06:27:30Z | 0 | 0 | peft | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:mistralai/Mistral-7B-Instruct-v0.2",
"base_model:adapter:mistralai/Mistral-7B-Instruct-v0.2",
"region:us"
] | null | 2024-05-19T01:57:08Z | ---
library_name: peft
base_model: mistralai/Mistral-7B-Instruct-v0.2
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.11.1 |
mp1704/tora_7b_pt | mp1704 | 2024-05-20T06:26:10Z | 8 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-20T06:21:37Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
Skhaled/AceGPT-7B-sentiment-analysis-AWQ | Skhaled | 2024-05-20T06:21:29Z | 78 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"awq",
"region:us"
] | text-generation | 2024-05-18T06:02:09Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
Mouwiya/image-model | Mouwiya | 2024-05-20T06:18:14Z | 83 | 0 | transformers | [
"transformers",
"safetensors",
"blip",
"image-text-to-text",
"image-to-text",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | image-to-text | 2024-04-17T06:47:34Z | ---
library_name: transformers
pipeline_tag: image-to-text
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
DUAL-GPO/zephyr-7b-gpo-v3-3-i2 | DUAL-GPO | 2024-05-20T06:16:20Z | 0 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"mistral",
"alignment-handbook",
"generated_from_trainer",
"trl",
"dpo",
"dataset:HuggingFaceH4/ultrafeedback_binarized",
"base_model:lole25/zephyr-7b-irepo-i1",
"base_model:adapter:lole25/zephyr-7b-irepo-i1",
"region:us"
] | null | 2024-05-19T22:09:20Z | ---
library_name: peft
tags:
- alignment-handbook
- generated_from_trainer
- trl
- dpo
- generated_from_trainer
base_model: lole25/zephyr-7b-irepo-i1
datasets:
- HuggingFaceH4/ultrafeedback_binarized
model-index:
- name: zephyr-7b-gpo-v3-3-i2
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. -->
# zephyr-7b-gpo-v3-3-i2
This model is a fine-tuned version of [lole25/zephyr-7b-irepo-i1](https://huggingface.co/lole25/zephyr-7b-irepo-i1) on the HuggingFaceH4/ultrafeedback_binarized dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-06
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
### Training results
### Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.2 |
ukung/TinyMistral-6x248M-Instruct-GGUF | ukung | 2024-05-20T06:13:41Z | 6 | 0 | null | [
"gguf",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-05-20T06:02:07Z | ---
license: apache-2.0
---
|
ahmedesmail16/Train-Test-Augmentation-NO-UPNormal-swinv2-base | ahmedesmail16 | 2024-05-20T06:12:26Z | 152 | 1 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"swinv2",
"image-classification",
"generated_from_trainer",
"base_model:microsoft/swinv2-base-patch4-window12to16-192to256-22kto1k-ft",
"base_model:finetune:microsoft/swinv2-base-patch4-window12to16-192to256-22kto1k-ft",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | image-classification | 2024-05-19T22:10:37Z | ---
license: apache-2.0
base_model: microsoft/swinv2-base-patch4-window12to16-192to256-22kto1k-ft
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Train-Test-Augmentation-NO-UPNormal-swinv2-base
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Train-Test-Augmentation-NO-UPNormal-swinv2-base
This model is a fine-tuned version of [microsoft/swinv2-base-patch4-window12to16-192to256-22kto1k-ft](https://huggingface.co/microsoft/swinv2-base-patch4-window12to16-192to256-22kto1k-ft) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5452
- Accuracy: 0.9030
## 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: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.4905 | 1.0 | 86 | 0.5127 | 0.8252 |
| 0.2148 | 2.0 | 172 | 0.5452 | 0.8445 |
| 0.1355 | 3.0 | 258 | 0.5205 | 0.8608 |
| 0.0472 | 4.0 | 344 | 0.4481 | 0.8921 |
| 0.0229 | 5.0 | 430 | 0.5671 | 0.8782 |
| 0.0505 | 6.0 | 516 | 0.6136 | 0.8837 |
| 0.0254 | 7.0 | 602 | 0.6037 | 0.8891 |
| 0.0009 | 8.0 | 688 | 0.6371 | 0.8819 |
| 0.0034 | 9.0 | 774 | 0.5569 | 0.8981 |
| 0.0019 | 10.0 | 860 | 0.5452 | 0.9030 |
### Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.19.1
- Tokenizers 0.15.2
|
Subsets and Splits