modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-06-25 06:27:54
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 495
values | tags
sequencelengths 1
4.05k
| pipeline_tag
stringclasses 54
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-06-25 06:24:22
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
memevis/swim3 | memevis | 2025-05-01T15:50:11Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-05-01T15:49:22Z | ---
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] |
itp-3-0/SentimentalAnalysis | itp-3-0 | 2025-05-01T15:47:46Z | 0 | 0 | null | [
"region:us"
] | null | 2025-05-01T15:43:16Z | ---
title: Seniment Analysis
emoji: 🐠
colorFrom: gray
colorTo: red
sdk: gradio
sdk_version: 5.20.0
app_file: app.py
pinned: false
---
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
kumari-sapna-videoss-seen/here.sapna.shah.viral.original.video | kumari-sapna-videoss-seen | 2025-05-01T15:45:47Z | 0 | 0 | null | [
"region:us"
] | null | 2025-05-01T15:45:16Z | <animated-image data-catalyst=""><a href="https://alltvsteam.com/viral-video/?v=news-es-tvdf" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Foo" data-canonical-src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a>
|
oliverneut/bert-base-vbll-kd-16 | oliverneut | 2025-05-01T15:45:46Z | 0 | 0 | null | [
"safetensors",
"model_hub_mixin",
"pytorch_model_hub_mixin",
"region:us"
] | null | 2025-05-01T15:45:28Z | ---
tags:
- model_hub_mixin
- pytorch_model_hub_mixin
---
This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
- Library: [More Information Needed]
- Docs: [More Information Needed] |
kate1130/koelectra-roberta-bullying-classifier | kate1130 | 2025-05-01T15:43:03Z | 0 | 0 | transformers | [
"transformers",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-05-01T15:33:30Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
mradermacher/Pocket-Llama2-3.2-3B-Instruct-GGUF | mradermacher | 2025-05-01T15:42:41Z | 2,530 | 0 | transformers | [
"transformers",
"gguf",
"trl",
"sft",
"text-generation-inference",
"code",
"Math",
"en",
"base_model:prithivMLmods/Pocket-Llama2-3.2-3B-Instruct",
"base_model:quantized:prithivMLmods/Pocket-Llama2-3.2-3B-Instruct",
"license:llama3.2",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-04-02T15:52:58Z | ---
base_model: prithivMLmods/Pocket-Llama2-3.2-3B-Instruct
language:
- en
library_name: transformers
license: llama3.2
quantized_by: mradermacher
tags:
- trl
- sft
- text-generation-inference
- code
- Math
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/prithivMLmods/Pocket-Llama2-3.2-3B-Instruct
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Pocket-Llama2-3.2-3B-Instruct-i1-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Pocket-Llama2-3.2-3B-Instruct-GGUF/resolve/main/Pocket-Llama2-3.2-3B-Instruct.Q2_K.gguf) | Q2_K | 1.5 | |
| [GGUF](https://huggingface.co/mradermacher/Pocket-Llama2-3.2-3B-Instruct-GGUF/resolve/main/Pocket-Llama2-3.2-3B-Instruct.Q3_K_S.gguf) | Q3_K_S | 1.6 | |
| [GGUF](https://huggingface.co/mradermacher/Pocket-Llama2-3.2-3B-Instruct-GGUF/resolve/main/Pocket-Llama2-3.2-3B-Instruct.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Pocket-Llama2-3.2-3B-Instruct-GGUF/resolve/main/Pocket-Llama2-3.2-3B-Instruct.Q3_K_L.gguf) | Q3_K_L | 1.9 | |
| [GGUF](https://huggingface.co/mradermacher/Pocket-Llama2-3.2-3B-Instruct-GGUF/resolve/main/Pocket-Llama2-3.2-3B-Instruct.IQ4_XS.gguf) | IQ4_XS | 1.9 | |
| [GGUF](https://huggingface.co/mradermacher/Pocket-Llama2-3.2-3B-Instruct-GGUF/resolve/main/Pocket-Llama2-3.2-3B-Instruct.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Pocket-Llama2-3.2-3B-Instruct-GGUF/resolve/main/Pocket-Llama2-3.2-3B-Instruct.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Pocket-Llama2-3.2-3B-Instruct-GGUF/resolve/main/Pocket-Llama2-3.2-3B-Instruct.Q5_K_S.gguf) | Q5_K_S | 2.4 | |
| [GGUF](https://huggingface.co/mradermacher/Pocket-Llama2-3.2-3B-Instruct-GGUF/resolve/main/Pocket-Llama2-3.2-3B-Instruct.Q5_K_M.gguf) | Q5_K_M | 2.4 | |
| [GGUF](https://huggingface.co/mradermacher/Pocket-Llama2-3.2-3B-Instruct-GGUF/resolve/main/Pocket-Llama2-3.2-3B-Instruct.Q6_K.gguf) | Q6_K | 2.7 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Pocket-Llama2-3.2-3B-Instruct-GGUF/resolve/main/Pocket-Llama2-3.2-3B-Instruct.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/Pocket-Llama2-3.2-3B-Instruct-GGUF/resolve/main/Pocket-Llama2-3.2-3B-Instruct.f16.gguf) | f16 | 6.5 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
uygaraydin/psy-support-flant5 | uygaraydin | 2025-05-01T15:41:47Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"t5",
"text2text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text2text-generation | 2025-05-01T15:41:12Z | ---
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] |
Yuhan123/ppo-cn-RM-reading-level-preschool-1-steps-10000-epoch-999-best-eval-score-0.789 | Yuhan123 | 2025-05-01T15:41:35Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"gpt_neox",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-05-01T15:39:01Z | ---
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] |
dustbunnyartist/spaghettimolt | dustbunnyartist | 2025-05-01T15:40:43Z | 0 | 0 | diffusers | [
"diffusers",
"text-to-image",
"flux",
"lora",
"template:sd-lora",
"fluxgym",
"base_model:black-forest-labs/FLUX.1-dev",
"base_model:adapter:black-forest-labs/FLUX.1-dev",
"license:other",
"region:us"
] | text-to-image | 2025-05-01T15:40:38Z | ---
tags:
- text-to-image
- flux
- lora
- diffusers
- template:sd-lora
- fluxgym
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: m0lztB5nySpugh3t*
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
---
# spaghettimolt
A Flux LoRA trained on a local computer with [Fluxgym](https://github.com/cocktailpeanut/fluxgym)
<Gallery />
## Trigger words
You should use `m0lztB5nySpugh3t*` to trigger the image generation.
## Download model and use it with ComfyUI, AUTOMATIC1111, SD.Next, Invoke AI, Forge, etc.
Weights for this model are available in Safetensors format.
|
AIEngineerYvar/mt5-small-finetuned-pubmed-summarization | AIEngineerYvar | 2025-05-01T15:37:08Z | 0 | 0 | transformers | [
"transformers",
"tf",
"mt5",
"text2text-generation",
"generated_from_keras_callback",
"base_model:google/mt5-small",
"base_model:finetune:google/mt5-small",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text2text-generation | 2025-05-01T14:45:32Z | ---
library_name: transformers
license: apache-2.0
base_model: google/mt5-small
tags:
- generated_from_keras_callback
model-index:
- name: AIEngineerYvar/mt5-small-finetuned-pubmed-summarization
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# AIEngineerYvar/mt5-small-finetuned-pubmed-summarization
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 4.4546
- Validation Loss: 2.9633
- Epoch: 3
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5.6e-05, 'decay_steps': 3000, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': np.float32(0.9), 'beta_2': np.float32(0.999), 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: mixed_float16
### Training results
| Train Loss | Validation Loss | Epoch |
|:----------:|:---------------:|:-----:|
| 4.4465 | 2.9633 | 0 |
| 4.4467 | 2.9633 | 1 |
| 4.4523 | 2.9633 | 2 |
| 4.4546 | 2.9633 | 3 |
### Framework versions
- Transformers 4.51.3
- TensorFlow 2.18.0
- Datasets 3.5.1
- Tokenizers 0.21.1
|
joseiivb26/joannie | joseiivb26 | 2025-05-01T15:37:03Z | 0 | 0 | null | [
"license:other",
"region:us"
] | null | 2025-05-01T14:56:38Z | ---
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
--- |
Ramjonnala/tinyLLAMA | Ramjonnala | 2025-05-01T15:36:28Z | 0 | 0 | peft | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"region:us"
] | null | 2025-05-01T15:33:35Z | ---
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
library_name: peft
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.10.0 |
EdwardTurner/Qwen2.5-14B-Instruct_R_1_1_1_full_train | EdwardTurner | 2025-05-01T15:36:12Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"unsloth",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-05-01T11:54:51Z | ---
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] |
Yuhan123/ppo-cn-RM-reading-level-preschool-1-steps-10000-epoch-999-best-eval-score-0.263 | Yuhan123 | 2025-05-01T15:35:34Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"gpt_neox",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-05-01T15:33:02Z | ---
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] |
mradermacher/OLMo-2-1124-7B-Instruct_GRPOv01.11-GGUF | mradermacher | 2025-05-01T15:35:28Z | 0 | 0 | transformers | [
"transformers",
"gguf",
"generated_from_trainer",
"open-r1",
"trl",
"grpo",
"en",
"dataset:Neelectric/OpenR1-Math-cn_k12-91k",
"base_model:Neelectric/OLMo-2-1124-7B-Instruct_GRPOv01.11",
"base_model:quantized:Neelectric/OLMo-2-1124-7B-Instruct_GRPOv01.11",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-05-01T14:38:47Z | ---
base_model: Neelectric/OLMo-2-1124-7B-Instruct_GRPOv01.11
datasets: Neelectric/OpenR1-Math-cn_k12-91k
language:
- en
library_name: transformers
model_name: OLMo-2-1124-7B-Instruct_GRPOv01.11
quantized_by: mradermacher
tags:
- generated_from_trainer
- open-r1
- trl
- grpo
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/Neelectric/OLMo-2-1124-7B-Instruct_GRPOv01.11
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct_GRPOv01.11-i1-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct_GRPOv01.11-GGUF/resolve/main/OLMo-2-1124-7B-Instruct_GRPOv01.11.Q2_K.gguf) | Q2_K | 3.0 | |
| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct_GRPOv01.11-GGUF/resolve/main/OLMo-2-1124-7B-Instruct_GRPOv01.11.Q3_K_S.gguf) | Q3_K_S | 3.4 | |
| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct_GRPOv01.11-GGUF/resolve/main/OLMo-2-1124-7B-Instruct_GRPOv01.11.Q3_K_M.gguf) | Q3_K_M | 3.8 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct_GRPOv01.11-GGUF/resolve/main/OLMo-2-1124-7B-Instruct_GRPOv01.11.Q3_K_L.gguf) | Q3_K_L | 4.1 | |
| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct_GRPOv01.11-GGUF/resolve/main/OLMo-2-1124-7B-Instruct_GRPOv01.11.IQ4_XS.gguf) | IQ4_XS | 4.1 | |
| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct_GRPOv01.11-GGUF/resolve/main/OLMo-2-1124-7B-Instruct_GRPOv01.11.Q4_K_S.gguf) | Q4_K_S | 4.3 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct_GRPOv01.11-GGUF/resolve/main/OLMo-2-1124-7B-Instruct_GRPOv01.11.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct_GRPOv01.11-GGUF/resolve/main/OLMo-2-1124-7B-Instruct_GRPOv01.11.Q5_K_S.gguf) | Q5_K_S | 5.2 | |
| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct_GRPOv01.11-GGUF/resolve/main/OLMo-2-1124-7B-Instruct_GRPOv01.11.Q5_K_M.gguf) | Q5_K_M | 5.3 | |
| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct_GRPOv01.11-GGUF/resolve/main/OLMo-2-1124-7B-Instruct_GRPOv01.11.Q6_K.gguf) | Q6_K | 6.1 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct_GRPOv01.11-GGUF/resolve/main/OLMo-2-1124-7B-Instruct_GRPOv01.11.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct_GRPOv01.11-GGUF/resolve/main/OLMo-2-1124-7B-Instruct_GRPOv01.11.f16.gguf) | f16 | 14.7 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
duandongsheng/sd-class-butterflies-32 | duandongsheng | 2025-05-01T15:34:33Z | 0 | 0 | diffusers | [
"diffusers",
"safetensors",
"pytorch",
"unconditional-image-generation",
"diffusion-models-class",
"license:mit",
"diffusers:DDPMPipeline",
"region:us"
] | unconditional-image-generation | 2025-05-01T15:32:42Z | ---
license: mit
tags:
- pytorch
- diffusers
- unconditional-image-generation
- diffusion-models-class
---
# Model Card for Unit 1 of the [Diffusion Models Class 🧨](https://github.com/huggingface/diffusion-models-class)
This model is a diffusion model for unconditional image generation of cute 🦋.
## Usage
```python
from diffusers import DDPMPipeline
pipeline = DDPMPipeline.from_pretrained('duandongsheng/sd-class-butterflies-32')
image = pipeline().images[0]
image
```
|
Trelis/gemma-3-4b-it-ft-touch-rugby-comprehensive-qa | Trelis | 2025-05-01T15:33:31Z | 16 | 0 | transformers | [
"transformers",
"gemma3",
"image-text-to-text",
"text-generation-inference",
"unsloth",
"conversational",
"en",
"base_model:unsloth/gemma-3-4b-it",
"base_model:finetune:unsloth/gemma-3-4b-it",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | image-text-to-text | 2025-04-24T08:40:13Z | ---
base_model: unsloth/gemma-3-4b-it
tags:
- text-generation-inference
- transformers
- unsloth
- gemma3
license: apache-2.0
language:
- en
---
# Uploaded finetuned model
- **Developed by:** Trelis
- **License:** apache-2.0
- **Finetuned from model :** unsloth/gemma-3-4b-it
This gemma3 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)
|
Yuhan123/ppo-cn-RM-reading-level-preschool-1-steps-10000-epoch-999-best-eval-score-0.776 | Yuhan123 | 2025-05-01T15:32:34Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"gpt_neox",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-05-01T15:29:56Z | ---
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] |
azeem23/whisper-small-codeswitching-ArabicEnglish | azeem23 | 2025-05-01T15:32:05Z | 21 | 1 | null | [
"tensorboard",
"safetensors",
"whisper",
"automatic-speech-recognition",
"ar",
"en",
"dataset:MohamedRashad/arabic-english-code-switching",
"base_model:openai/whisper-small",
"base_model:finetune:openai/whisper-small",
"license:mit",
"region:us"
] | automatic-speech-recognition | 2025-04-26T14:10:41Z | ---
license: mit
datasets:
- MohamedRashad/arabic-english-code-switching
language:
- ar
- en
base_model:
- openai/whisper-small
pipeline_tag: automatic-speech-recognition
---
# Whisper finetuned for codeswitching in Arabic-English
- **Original Model** [openai/whisper-small](https://huggingface.co/openai/whisper-small)
- **Dataset used:** [MohamedRashad/arabic-english-code-switching](https://huggingface.co/datasets/MohamedRashad/arabic-english-code-switching) |
aleegis/bb58934a-a240-4055-b5ed-f5ef8915eb45 | aleegis | 2025-05-01T15:29:42Z | 0 | 0 | peft | [
"peft",
"safetensors",
"mistral",
"axolotl",
"generated_from_trainer",
"base_model:unsloth/Mistral-Nemo-Base-2407",
"base_model:adapter:unsloth/Mistral-Nemo-Base-2407",
"license:apache-2.0",
"region:us"
] | null | 2025-05-01T13:40:12Z | ---
library_name: peft
license: apache-2.0
base_model: unsloth/Mistral-Nemo-Base-2407
tags:
- axolotl
- generated_from_trainer
model-index:
- name: bb58934a-a240-4055-b5ed-f5ef8915eb45
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/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
<details><summary>See axolotl config</summary>
axolotl version: `0.4.1`
```yaml
adapter: lora
base_model: unsloth/Mistral-Nemo-Base-2407
bf16: auto
chat_template: llama3
dataloader_num_workers: 12
dataset_prepared_path: null
datasets:
- data_files:
- 63a491480b93f510_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/63a491480b93f510_train_data.json
type:
field_instruction: prompt
field_output: best_response
format: '{instruction}'
no_input_format: '{instruction}'
system_format: '{system}'
system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_steps: null
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 8
gradient_checkpointing: false
group_by_length: false
hub_model_id: aleegis/bb58934a-a240-4055-b5ed-f5ef8915eb45
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: null
lora_alpha: 32
lora_dropout: 0.15
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
loraplus_lr_embedding: 1.0e-06
loraplus_lr_ratio: 16
lr_scheduler: cosine
max_grad_norm: 1
max_steps: 1500
micro_batch_size: 2
mlflow_experiment_name: /tmp/63a491480b93f510_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 200
optimizer: adamw_torch_fused
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: null
save_total_limit: 10
saves_per_epoch: 0
sequence_len: 1024
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.0
wandb_entity: null
wandb_mode: online
wandb_name: 13712427-fb73-4e43-b93c-61d36776a27f
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 13712427-fb73-4e43-b93c-61d36776a27f
warmup_steps: 100
weight_decay: 0
xformers_attention: null
```
</details><br>
# bb58934a-a240-4055-b5ed-f5ef8915eb45
This model is a fine-tuned version of [unsloth/Mistral-Nemo-Base-2407](https://huggingface.co/unsloth/Mistral-Nemo-Base-2407) 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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- training_steps: 1500
### Training results
### Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1 |
aleegis/54d6b89e-e0a4-4c26-9d5e-4ce691279925 | aleegis | 2025-05-01T15:29:10Z | 0 | 0 | peft | [
"peft",
"safetensors",
"mistral",
"axolotl",
"generated_from_trainer",
"base_model:unsloth/Mistral-Nemo-Base-2407",
"base_model:adapter:unsloth/Mistral-Nemo-Base-2407",
"license:apache-2.0",
"region:us"
] | null | 2025-05-01T13:40:13Z | ---
library_name: peft
license: apache-2.0
base_model: unsloth/Mistral-Nemo-Base-2407
tags:
- axolotl
- generated_from_trainer
model-index:
- name: 54d6b89e-e0a4-4c26-9d5e-4ce691279925
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/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
<details><summary>See axolotl config</summary>
axolotl version: `0.4.1`
```yaml
adapter: lora
base_model: unsloth/Mistral-Nemo-Base-2407
bf16: auto
chat_template: llama3
dataloader_num_workers: 12
dataset_prepared_path: null
datasets:
- data_files:
- 63a491480b93f510_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/63a491480b93f510_train_data.json
type:
field_instruction: prompt
field_output: best_response
format: '{instruction}'
no_input_format: '{instruction}'
system_format: '{system}'
system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_steps: null
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 8
gradient_checkpointing: false
group_by_length: false
hub_model_id: aleegis/54d6b89e-e0a4-4c26-9d5e-4ce691279925
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: null
lora_alpha: 32
lora_dropout: 0.15
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
loraplus_lr_embedding: 1.0e-06
loraplus_lr_ratio: 16
lr_scheduler: cosine
max_grad_norm: 1
max_steps: 1500
micro_batch_size: 2
mlflow_experiment_name: /tmp/63a491480b93f510_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 200
optimizer: adamw_torch_fused
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: null
save_total_limit: 10
saves_per_epoch: 0
sequence_len: 1024
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.0
wandb_entity: null
wandb_mode: online
wandb_name: 13712427-fb73-4e43-b93c-61d36776a27f
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 13712427-fb73-4e43-b93c-61d36776a27f
warmup_steps: 100
weight_decay: 0
xformers_attention: null
```
</details><br>
# 54d6b89e-e0a4-4c26-9d5e-4ce691279925
This model is a fine-tuned version of [unsloth/Mistral-Nemo-Base-2407](https://huggingface.co/unsloth/Mistral-Nemo-Base-2407) 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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- training_steps: 1500
### Training results
### Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1 |
ma921/gpt2-large_h_dpo_imdb_noise0_epoch5 | ma921 | 2025-05-01T15:28:40Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"gpt2",
"text-generation",
"generated_from_trainer",
"base_model:ma921/gpt2-large-sft-imdb",
"base_model:finetune:ma921/gpt2-large-sft-imdb",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-05-01T15:27:28Z | ---
library_name: transformers
license: mit
base_model: ma921/gpt2-large-sft-imdb
tags:
- generated_from_trainer
model-index:
- name: gpt2-large_h_dpo_imdb_noise0_epoch5
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-large_h_dpo_imdb_noise0_epoch5
This model is a fine-tuned version of [ma921/gpt2-large-sft-imdb](https://huggingface.co/ma921/gpt2-large-sft-imdb) 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: 1e-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 32
- total_train_batch_size: 256
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.1
- Tokenizers 0.21.1
|
sergioalves/d3d952a3-dd31-4a3d-abb3-c8bfb2854c20 | sergioalves | 2025-05-01T15:28:12Z | 0 | 0 | peft | [
"peft",
"safetensors",
"mistral",
"axolotl",
"generated_from_trainer",
"base_model:HuggingFaceH4/zephyr-7b-beta",
"base_model:adapter:HuggingFaceH4/zephyr-7b-beta",
"license:mit",
"8-bit",
"bitsandbytes",
"region:us"
] | null | 2025-05-01T14:30:02Z | ---
library_name: peft
license: mit
base_model: HuggingFaceH4/zephyr-7b-beta
tags:
- axolotl
- generated_from_trainer
model-index:
- name: d3d952a3-dd31-4a3d-abb3-c8bfb2854c20
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/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
<details><summary>See axolotl config</summary>
axolotl version: `0.4.1`
```yaml
absolute_data_files: true
adapter: lora
base_model: HuggingFaceH4/zephyr-7b-beta
bf16: true
chat_template: llama3
dataset_prepared_path: /workspace/axolotl
datasets:
- data_files:
- 51265aa9130bc4de_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/51265aa9130bc4de_train_data.json
type:
field_instruction: text
field_output: title
format: '{instruction}'
no_input_format: '{instruction}'
system_format: '{system}'
system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 1
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 1
gradient_checkpointing: true
gradient_clipping: 0.5
group_by_length: false
hub_model_id: sergioalves/d3d952a3-dd31-4a3d-abb3-c8bfb2854c20
hub_repo: null
hub_strategy: end
hub_token: null
learning_rate: 5.0e-06
load_in_4bit: false
load_in_8bit: true
local_rank: null
logging_steps: 1
lora_alpha: 64
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lr_scheduler: cosine
max_steps: 200
micro_batch_size: 8
mixed_precision: bf16
mlflow_experiment_name: /tmp/51265aa9130bc4de_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
saves_per_epoch: 1
sequence_len: 1024
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 56363f08-3261-498d-973d-aa5bb4b807c6
wandb_project: s56-8
wandb_run: your_name
wandb_runid: 56363f08-3261-498d-973d-aa5bb4b807c6
warmup_steps: 5
weight_decay: 0.01
xformers_attention: true
```
</details><br>
# d3d952a3-dd31-4a3d-abb3-c8bfb2854c20
This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.6292
## 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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 5
- training_steps: 200
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.5819 | 0.0063 | 200 | 1.6292 |
### Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1 |
Siddharth63/Qwen3-8B-Base-AWQ | Siddharth63 | 2025-05-01T12:25:54Z | 0 | 0 | null | [
"safetensors",
"qwen3",
"license:apache-2.0",
"4-bit",
"awq",
"region:us"
] | null | 2025-05-01T09:24:09Z | ---
license: apache-2.0
---
```
git clone https://github.com/casper-hansen/AutoAWQ.git # latest source 2025-05-01
cd AutoAWQ
pip install -e .
## go into AutoAWQ folder
pip install --upgrade transformers
## FOR STREAMING
from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer, TextStreamer
from awq.utils.utils import get_best_device
device = get_best_device()
quant_path = "Siddharth63/Qwen3-8B-base-AWQ" # path or HF repo for the AWQ checkpoint
# ---------- load model & tokenizer ----------
model = AutoAWQForCausalLM.from_quantized(quant_path, fuse_layers=True)
tokenizer = AutoTokenizer.from_pretrained(quant_path, trust_remote_code=True)
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
# ---------- tokenise & generate ----------
input_ids = tokenizer("Atherosclerosis is", return_tensors="pt"
).input_ids.to(device)
_ = model.generate(
input_ids,
streamer = streamer,
max_new_tokens = 512, # full context window
use_cache = True
)
## FOR NON_STREAMING
from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer, TextStreamer
from awq.utils.utils import get_best_device
device = get_best_device()
quant_path = "Siddharth63/Qwen3-8B-base-AWQ" # path or HF repo for the AWQ checkpoint
# ---------- load model & tokenizer ----------
model = AutoAWQForCausalLM.from_quantized(quant_path, fuse_layers=True)
tokenizer = AutoTokenizer.from_pretrained(quant_path, trust_remote_code=True)
input_ids = tokenizer(
"Atherosclerosis is",
return_tensors="pt"
).input_ids.to(device)
# ---------- generate (blocking) ----------
output_ids = model.generate(
input_ids,
max_new_tokens=100, # or max_length / temperature / etc.
use_cache=True # default; speeds up incremental decoding
)
response = tokenizer.decode(
output_ids[0],
skip_special_tokens=True, # drop <|im_start|> tokens
)
print("\n=== Model reply ===\n", response)
``` |
Siddharth63/Qwen3-4B-base-AWQ | Siddharth63 | 2025-05-01T12:24:58Z | 0 | 0 | null | [
"safetensors",
"qwen3",
"license:apache-2.0",
"4-bit",
"awq",
"region:us"
] | null | 2025-05-01T08:57:58Z | ---
license: apache-2.0
---
```
git clone https://github.com/casper-hansen/AutoAWQ.git # latest source 2025-05-01
cd AutoAWQ
pip install -e .
## go into AutoAWQ folder
pip install --upgrade transformers
## FOR STREAMING
from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer, TextStreamer
from awq.utils.utils import get_best_device
device = get_best_device()
quant_path = "Siddharth63/Qwen3-4B-base-AWQ" # path or HF repo for the AWQ checkpoint
# ---------- load model & tokenizer ----------
model = AutoAWQForCausalLM.from_quantized(quant_path, fuse_layers=True)
tokenizer = AutoTokenizer.from_pretrained(quant_path, trust_remote_code=True)
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
# ---------- tokenise & generate ----------
input_ids = tokenizer("Atherosclerosis is", return_tensors="pt"
).input_ids.to(device)
_ = model.generate(
input_ids,
streamer = streamer,
max_new_tokens = 512, # full context window
use_cache = True
)
## FOR NON_STREAMING
from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer, TextStreamer
from awq.utils.utils import get_best_device
device = get_best_device()
quant_path = "Siddharth63/Qwen3-4B-base-AWQ" # path or HF repo for the AWQ checkpoint
# ---------- load model & tokenizer ----------
model = AutoAWQForCausalLM.from_quantized(quant_path, fuse_layers=True)
tokenizer = AutoTokenizer.from_pretrained(quant_path, trust_remote_code=True)
input_ids = tokenizer(
"Atherosclerosis is",
return_tensors="pt"
).input_ids.to(device)
# ---------- generate (blocking) ----------
output_ids = model.generate(
input_ids,
max_new_tokens=100, # or max_length / temperature / etc.
use_cache=True # default; speeds up incremental decoding
)
response = tokenizer.decode(
output_ids[0],
skip_special_tokens=True, # drop <|im_start|> tokens
)
print("\n=== Model reply ===\n", response)
``` |
ghaniashafiqa/FT-Llama2-7b | ghaniashafiqa | 2025-05-01T12:23:29Z | 12 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-04-16T16:01:54Z | ---
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] |
ail-sa/akshey_stockyplus_mid_fs_v1 | ail-sa | 2025-05-01T12:20:56Z | 0 | 0 | diffusers | [
"diffusers",
"flux",
"lora",
"replicate",
"text-to-image",
"en",
"base_model:black-forest-labs/FLUX.1-dev",
"base_model:adapter:black-forest-labs/FLUX.1-dev",
"license:other",
"region:us"
] | text-to-image | 2025-05-01T11:45:10Z | ---
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
language:
- en
tags:
- flux
- diffusers
- lora
- replicate
base_model: "black-forest-labs/FLUX.1-dev"
pipeline_tag: text-to-image
# widget:
# - text: >-
# prompt
# output:
# url: https://...
instance_prompt: Sid
---
# Akshey_Stockyplus_Mid_Fs_V1
<Gallery />
## About this LoRA
This is a [LoRA](https://replicate.com/docs/guides/working-with-loras) for the FLUX.1-dev text-to-image model. It can be used with diffusers or ComfyUI.
It was trained on [Replicate](https://replicate.com/) using AI toolkit: https://replicate.com/ostris/flux-dev-lora-trainer/train
## Trigger words
You should use `Sid` to trigger the image generation.
## Run this LoRA with an API using Replicate
```py
import replicate
input = {
"prompt": "Sid",
"lora_weights": "https://huggingface.co/ail-sa/akshey_stockyplus_mid_fs_v1/resolve/main/lora.safetensors"
}
output = replicate.run(
"black-forest-labs/flux-dev-lora",
input=input
)
for index, item in enumerate(output):
with open(f"output_{index}.webp", "wb") as file:
file.write(item.read())
```
## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
```py
from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('ail-sa/akshey_stockyplus_mid_fs_v1', weight_name='lora.safetensors')
image = pipeline('Sid').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)
## Training details
- Steps: 2000
- Learning rate: 0.0004
- LoRA rank: 16
## Contribute your own examples
You can use the [community tab](https://huggingface.co/ail-sa/akshey_stockyplus_mid_fs_v1/discussions) to add images that show off what you’ve made with this LoRA.
|
iTroned/test_offensive_best_metrics | iTroned | 2025-05-01T12:20:05Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"generated_from_trainer",
"base_model:google-bert/bert-base-uncased",
"base_model:finetune:google-bert/bert-base-uncased",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-04-24T05:01:13Z | ---
library_name: transformers
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
model-index:
- name: test_offensive_best_metrics
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/itroned-ntnu/huggingface/runs/3w6wdwfj)
# test_offensive_best_metrics
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4063
- Accuracy Offensive: 0.8477
- F1 Macro Offensive: 0.8119
- F1 Weighted Offensive: 0.8482
## 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: 3.4878669814902115e-06
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy Offensive | F1 Macro Offensive | F1 Weighted Offensive |
|:-------------:|:-----:|:-----:|:---------------:|:------------------:|:------------------:|:---------------------:|
| 0.5772 | 1.0 | 3310 | 0.5389 | 0.7209 | 0.4189 | 0.6040 |
| 0.5395 | 2.0 | 6620 | 0.3936 | 0.7209 | 0.4189 | 0.6040 |
| 0.5166 | 3.0 | 9930 | 0.3618 | 0.7209 | 0.4189 | 0.6040 |
| 0.5239 | 4.0 | 13240 | 0.3458 | 0.7209 | 0.4189 | 0.6040 |
| 0.5089 | 5.0 | 16550 | 0.3572 | 0.8558 | 0.8083 | 0.8505 |
| 0.4533 | 6.0 | 19860 | 0.4132 | 0.8395 | 0.7917 | 0.8358 |
| 0.4105 | 7.0 | 23170 | 0.4063 | 0.8477 | 0.8119 | 0.8482 |
| 0.4051 | 8.0 | 26480 | 0.5048 | 0.8372 | 0.7987 | 0.8376 |
| 0.3582 | 9.0 | 29790 | 0.5884 | 0.8279 | 0.7888 | 0.8290 |
| 0.3707 | 10.0 | 33100 | 0.7322 | 0.8407 | 0.7987 | 0.8393 |
| 0.348 | 11.0 | 36410 | 0.8778 | 0.8395 | 0.7985 | 0.8387 |
### Framework versions
- Transformers 4.50.2
- Pytorch 2.6.0+cu124
- Datasets 3.0.1
- Tokenizers 0.21.1
|
AshProbably/medcot-llama3.2-3b-model | AshProbably | 2025-05-01T12:19:24Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-04-25T18:46:15Z | ---
base_model: unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** AshProbably
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3.2-3b-instruct-unsloth-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)
|
Triangle104/Qwen3-1.7B-abliterated-Q8_0-GGUF | Triangle104 | 2025-05-01T12:18:06Z | 0 | 0 | transformers | [
"transformers",
"gguf",
"chat",
"abliterated",
"uncensored",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"base_model:huihui-ai/Qwen3-1.7B-abliterated",
"base_model:quantized:huihui-ai/Qwen3-1.7B-abliterated",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-05-01T12:17:55Z | ---
base_model: huihui-ai/Qwen3-1.7B-abliterated
library_name: transformers
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen3-1.7B/blob/main/LICENSE
pipeline_tag: text-generation
tags:
- chat
- abliterated
- uncensored
- llama-cpp
- gguf-my-repo
---
# Triangle104/Qwen3-1.7B-abliterated-Q8_0-GGUF
This model was converted to GGUF format from [`huihui-ai/Qwen3-1.7B-abliterated`](https://huggingface.co/huihui-ai/Qwen3-1.7B-abliterated) 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/huihui-ai/Qwen3-1.7B-abliterated) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo Triangle104/Qwen3-1.7B-abliterated-Q8_0-GGUF --hf-file qwen3-1.7b-abliterated-q8_0.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo Triangle104/Qwen3-1.7B-abliterated-Q8_0-GGUF --hf-file qwen3-1.7b-abliterated-q8_0.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo Triangle104/Qwen3-1.7B-abliterated-Q8_0-GGUF --hf-file qwen3-1.7b-abliterated-q8_0.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo Triangle104/Qwen3-1.7B-abliterated-Q8_0-GGUF --hf-file qwen3-1.7b-abliterated-q8_0.gguf -c 2048
```
|
thliang01/medieval-knight-sdxl-dora-v1-0 | thliang01 | 2025-05-01T12:17:31Z | 0 | 0 | null | [
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"base_model:finetune:stabilityai/stable-diffusion-xl-base-1.0",
"license:openrail",
"region:us"
] | null | 2025-05-01T11:21:51Z | ---
license: openrail
base_model:
- stabilityai/stable-diffusion-xl-base-1.0
--- |
mlx-community/DeepSeek-Prover-V2-7B-4bit | mlx-community | 2025-05-01T12:17:18Z | 0 | 0 | mlx | [
"mlx",
"safetensors",
"llama",
"text-generation",
"conversational",
"base_model:deepseek-ai/DeepSeek-Prover-V2-7B",
"base_model:quantized:deepseek-ai/DeepSeek-Prover-V2-7B",
"4-bit",
"region:us"
] | text-generation | 2025-05-01T12:09:48Z | ---
base_model: deepseek-ai/DeepSeek-Prover-V2-7B
library_name: mlx
pipeline_tag: text-generation
tags:
- mlx
---
# mlx-community/DeepSeek-Prover-V2-7B-4bit
This model [mlx-community/DeepSeek-Prover-V2-7B-4bit](https://huggingface.co/mlx-community/DeepSeek-Prover-V2-7B-4bit) was
converted to MLX format from [deepseek-ai/DeepSeek-Prover-V2-7B](https://huggingface.co/deepseek-ai/DeepSeek-Prover-V2-7B)
using mlx-lm version **0.24.0**.
## Use with mlx
```bash
pip install mlx-lm
```
```python
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/DeepSeek-Prover-V2-7B-4bit")
prompt = "hello"
if tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)
```
|
LucileFavero/aaec_ll_no_T | LucileFavero | 2025-05-01T12:16:48Z | 0 | 0 | transformers | [
"transformers",
"gguf",
"llama",
"text-generation-inference",
"unsloth",
"en",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-05-01T12:15:45Z | ---
base_model: unsloth/meta-llama-3.1-8b-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- gguf
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** LucileFavero
- **License:** apache-2.0
- **Finetuned from model :** unsloth/meta-llama-3.1-8b-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
Triangle104/Qwen3-1.7B-abliterated-Q5_K_M-GGUF | Triangle104 | 2025-05-01T12:16:20Z | 0 | 0 | transformers | [
"transformers",
"gguf",
"chat",
"abliterated",
"uncensored",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"base_model:huihui-ai/Qwen3-1.7B-abliterated",
"base_model:quantized:huihui-ai/Qwen3-1.7B-abliterated",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-05-01T12:16:13Z | ---
base_model: huihui-ai/Qwen3-1.7B-abliterated
library_name: transformers
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen3-1.7B/blob/main/LICENSE
pipeline_tag: text-generation
tags:
- chat
- abliterated
- uncensored
- llama-cpp
- gguf-my-repo
---
# Triangle104/Qwen3-1.7B-abliterated-Q5_K_M-GGUF
This model was converted to GGUF format from [`huihui-ai/Qwen3-1.7B-abliterated`](https://huggingface.co/huihui-ai/Qwen3-1.7B-abliterated) 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/huihui-ai/Qwen3-1.7B-abliterated) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo Triangle104/Qwen3-1.7B-abliterated-Q5_K_M-GGUF --hf-file qwen3-1.7b-abliterated-q5_k_m.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo Triangle104/Qwen3-1.7B-abliterated-Q5_K_M-GGUF --hf-file qwen3-1.7b-abliterated-q5_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.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo Triangle104/Qwen3-1.7B-abliterated-Q5_K_M-GGUF --hf-file qwen3-1.7b-abliterated-q5_k_m.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo Triangle104/Qwen3-1.7B-abliterated-Q5_K_M-GGUF --hf-file qwen3-1.7b-abliterated-q5_k_m.gguf -c 2048
```
|
0xOzii/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-large_padded_chimpanzee | 0xOzii | 2025-05-01T12:12:17Z | 11 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"generated_from_trainer",
"rl-swarm",
"grpo",
"gensyn",
"I am large padded chimpanzee",
"trl",
"conversational",
"arxiv:2402.03300",
"base_model:Gensyn/Qwen2.5-0.5B-Instruct",
"base_model:finetune:Gensyn/Qwen2.5-0.5B-Instruct",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-04-09T20:44:14Z | ---
base_model: Gensyn/Qwen2.5-0.5B-Instruct
library_name: transformers
model_name: Qwen2.5-0.5B-Instruct-Gensyn-Swarm-large_padded_chimpanzee
tags:
- generated_from_trainer
- rl-swarm
- grpo
- gensyn
- I am large padded chimpanzee
- trl
licence: license
---
# Model Card for Qwen2.5-0.5B-Instruct-Gensyn-Swarm-large_padded_chimpanzee
This model is a fine-tuned version of [Gensyn/Qwen2.5-0.5B-Instruct](https://huggingface.co/Gensyn/Qwen2.5-0.5B-Instruct).
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="0xOzii/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-large_padded_chimpanzee", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
### Framework versions
- TRL: 0.15.2
- Transformers: 4.51.3
- Pytorch: 2.5.1
- Datasets: 3.5.0
- Tokenizers: 0.21.1
## Citations
Cite GRPO as:
```bibtex
@article{zhihong2024deepseekmath,
title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
year = 2024,
eprint = {arXiv:2402.03300},
}
```
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
``` |
Triangle104/mlabonne_Qwen3-1.7B-abliterated-Q5_K_S-GGUF | Triangle104 | 2025-05-01T12:10:21Z | 0 | 0 | transformers | [
"transformers",
"gguf",
"llama-cpp",
"gguf-my-repo",
"base_model:mlabonne/Qwen3-1.7B-abliterated",
"base_model:quantized:mlabonne/Qwen3-1.7B-abliterated",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-05-01T11:28:03Z | ---
base_model: mlabonne/Qwen3-1.7B-abliterated
library_name: transformers
tags:
- llama-cpp
- gguf-my-repo
---
# Triangle104/Qwen3-1.7B-abliterated-Q5_K_S-GGUF
This model was converted to GGUF format from [`mlabonne/Qwen3-1.7B-abliterated`](https://huggingface.co/mlabonne/Qwen3-1.7B-abliterated) 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/mlabonne/Qwen3-1.7B-abliterated) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo Triangle104/Qwen3-1.7B-abliterated-Q5_K_S-GGUF --hf-file qwen3-1.7b-abliterated-q5_k_s.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo Triangle104/Qwen3-1.7B-abliterated-Q5_K_S-GGUF --hf-file qwen3-1.7b-abliterated-q5_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.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo Triangle104/Qwen3-1.7B-abliterated-Q5_K_S-GGUF --hf-file qwen3-1.7b-abliterated-q5_k_s.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo Triangle104/Qwen3-1.7B-abliterated-Q5_K_S-GGUF --hf-file qwen3-1.7b-abliterated-q5_k_s.gguf -c 2048
```
|
samirmsallem/distilbert-base-multilingual-cased-ner | samirmsallem | 2025-05-01T12:09:46Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"distilbert",
"token-classification",
"definitions",
"ner",
"de",
"dataset:samirmsallem/wiki_def_de_multitask",
"base_model:distilbert/distilbert-base-multilingual-cased",
"base_model:finetune:distilbert/distilbert-base-multilingual-cased",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | token-classification | 2025-05-01T12:04:23Z | ---
datasets:
- samirmsallem/wiki_def_de_multitask
language:
- de
base_model:
- distilbert/distilbert-base-multilingual-cased
library_name: transformers
tags:
- definitions
- ner
--- |
naser1973/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-invisible_tricky_ram | naser1973 | 2025-05-01T12:09:34Z | 9 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"generated_from_trainer",
"rl-swarm",
"grpo",
"gensyn",
"I am invisible tricky ram",
"trl",
"conversational",
"arxiv:2402.03300",
"base_model:Gensyn/Qwen2.5-0.5B-Instruct",
"base_model:finetune:Gensyn/Qwen2.5-0.5B-Instruct",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-04-05T15:52:17Z | ---
base_model: Gensyn/Qwen2.5-0.5B-Instruct
library_name: transformers
model_name: Qwen2.5-0.5B-Instruct-Gensyn-Swarm-invisible_tricky_ram
tags:
- generated_from_trainer
- rl-swarm
- grpo
- gensyn
- I am invisible tricky ram
- trl
licence: license
---
# Model Card for Qwen2.5-0.5B-Instruct-Gensyn-Swarm-invisible_tricky_ram
This model is a fine-tuned version of [Gensyn/Qwen2.5-0.5B-Instruct](https://huggingface.co/Gensyn/Qwen2.5-0.5B-Instruct).
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="naser1973/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-invisible_tricky_ram", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
### Framework versions
- TRL: 0.15.2
- Transformers: 4.51.3
- Pytorch: 2.5.1+cu121
- Datasets: 3.5.0
- Tokenizers: 0.21.1
## Citations
Cite GRPO as:
```bibtex
@article{zhihong2024deepseekmath,
title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
year = 2024,
eprint = {arXiv:2402.03300},
}
```
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
``` |
Triangle104/mlabonne_Qwen3-1.7B-abliterated-Q4_K_M-GGUF | Triangle104 | 2025-05-01T12:07:52Z | 0 | 0 | transformers | [
"transformers",
"gguf",
"llama-cpp",
"gguf-my-repo",
"base_model:mlabonne/Qwen3-1.7B-abliterated",
"base_model:quantized:mlabonne/Qwen3-1.7B-abliterated",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-05-01T11:27:12Z | ---
base_model: mlabonne/Qwen3-1.7B-abliterated
library_name: transformers
tags:
- llama-cpp
- gguf-my-repo
---
# Triangle104/Qwen3-1.7B-abliterated-Q4_K_M-GGUF
This model was converted to GGUF format from [`mlabonne/Qwen3-1.7B-abliterated`](https://huggingface.co/mlabonne/Qwen3-1.7B-abliterated) 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/mlabonne/Qwen3-1.7B-abliterated) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo Triangle104/Qwen3-1.7B-abliterated-Q4_K_M-GGUF --hf-file qwen3-1.7b-abliterated-q4_k_m.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo Triangle104/Qwen3-1.7B-abliterated-Q4_K_M-GGUF --hf-file qwen3-1.7b-abliterated-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.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo Triangle104/Qwen3-1.7B-abliterated-Q4_K_M-GGUF --hf-file qwen3-1.7b-abliterated-q4_k_m.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo Triangle104/Qwen3-1.7B-abliterated-Q4_K_M-GGUF --hf-file qwen3-1.7b-abliterated-q4_k_m.gguf -c 2048
```
|
Atnafu/nllb_600M_eng2tir-norm | Atnafu | 2025-05-01T12:05:32Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"m2m_100",
"text2text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text2text-generation | 2025-05-01T11:56:14Z | ---
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] |
Triangle104/mlabonne_Qwen3-1.7B-abliterated-Q4_K_S-GGUF | Triangle104 | 2025-05-01T12:05:09Z | 0 | 0 | transformers | [
"transformers",
"gguf",
"llama-cpp",
"gguf-my-repo",
"base_model:mlabonne/Qwen3-1.7B-abliterated",
"base_model:quantized:mlabonne/Qwen3-1.7B-abliterated",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-05-01T11:26:21Z | ---
base_model: mlabonne/Qwen3-1.7B-abliterated
library_name: transformers
tags:
- llama-cpp
- gguf-my-repo
---
# Triangle104/Qwen3-1.7B-abliterated-Q4_K_S-GGUF
This model was converted to GGUF format from [`mlabonne/Qwen3-1.7B-abliterated`](https://huggingface.co/mlabonne/Qwen3-1.7B-abliterated) 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/mlabonne/Qwen3-1.7B-abliterated) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo Triangle104/Qwen3-1.7B-abliterated-Q4_K_S-GGUF --hf-file qwen3-1.7b-abliterated-q4_k_s.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo Triangle104/Qwen3-1.7B-abliterated-Q4_K_S-GGUF --hf-file qwen3-1.7b-abliterated-q4_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.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo Triangle104/Qwen3-1.7B-abliterated-Q4_K_S-GGUF --hf-file qwen3-1.7b-abliterated-q4_k_s.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo Triangle104/Qwen3-1.7B-abliterated-Q4_K_S-GGUF --hf-file qwen3-1.7b-abliterated-q4_k_s.gguf -c 2048
```
|
mlfoundations-dev/d1_math_longest | mlfoundations-dev | 2025-05-01T12:03:59Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"llama-factory",
"full",
"generated_from_trainer",
"conversational",
"base_model:Qwen/Qwen2.5-7B-Instruct",
"base_model:finetune:Qwen/Qwen2.5-7B-Instruct",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-04-30T19:38:44Z | ---
library_name: transformers
license: apache-2.0
base_model: Qwen/Qwen2.5-7B-Instruct
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: d1_math_longest
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. -->
# d1_math_longest
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/d1_math_longest 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: 4e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 32
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- total_eval_batch_size: 256
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5.0
### Training results
### Framework versions
- Transformers 4.46.1
- Pytorch 2.3.0
- Datasets 3.1.0
- Tokenizers 0.20.3
|
kmouratidis/Qwen3-32B-AWQ-w4-GEMM-sc | kmouratidis | 2025-05-01T12:02:29Z | 0 | 0 | null | [
"safetensors",
"qwen3",
"base_model:Qwen/Qwen3-32B",
"base_model:quantized:Qwen/Qwen3-32B",
"license:apache-2.0",
"4-bit",
"awq",
"region:us"
] | null | 2025-05-01T11:55:57Z | ---
license: apache-2.0
base_model:
- Qwen/Qwen3-32B
---
# Qwen3-32B-AWQ-w4-GEMM-sc
Original Model: https://huggingface.co/Qwen/Qwen3-32B
Created with the latest AutoAWQ. The calibration was done on short context and
64 samples with the code below.
## Quantization details
```
model_path = '/mnt/lcache/sglang/models/Qwen/Qwen3-32B'
model = AutoAWQForCausalLM.from_pretrained(model_path)
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
quant_config = {"zero_point": True, "q_group_size": 128, "w_bit": 4, "version": "GEMM"}
model.quantize(tokenizer, quant_config=quant_config)
# AWQ: 100%|████████████████████████████████████| 64/64 [1:09:36<00:00, 65.26s/it]
quant_path = './Qwen3-32B-AWQ-4bit-GEMM-sc'
model.save_quantized(quant_path)
tokenizer.save_pretrained(quant_path)
``` |
wsbagnsv1/SkyReels-V2-T2V-14B-540P-GGUF | wsbagnsv1 | 2025-05-01T12:01:45Z | 241 | 1 | gguf | [
"gguf",
"video",
"video-generation",
"text-to-video",
"base_model:Skywork/SkyReels-V2-T2V-14B-540P",
"base_model:quantized:Skywork/SkyReels-V2-T2V-14B-540P",
"license:other",
"region:us"
] | text-to-video | 2025-04-24T23:56:23Z | ---
license: other
license_name: skywork-license
license_link: LICENSE
library_name: gguf
base_model:
- Skywork/SkyReels-V2-T2V-14B-540P
tags:
- video
- video-generation
pipeline_tag: text-to-video
---
This is a direct GGUF conversion of [Skywork/SkyReels-V2-T2V-14B-540P](https://huggingface.co/Skywork/SkyReels-V2-T2V-14B-540P)
All quants are created from the FP32 base file, though I only uploaded the Q8_0 and less, if you want the F16 or BF16 one I would upload it per request.
The model files can be used with the [ComfyUI-GGUF](https://github.com/city96/ComfyUI-GGUF) custom node.
Place model files in `ComfyUI/models/unet` - see the GitHub readme for further install instructions.
The VAE can be downloaded from [this repository by Kijai](https://huggingface.co/Kijai/WanVideo_comfy/blob/main/Wan2_1_VAE_bf16.safetensors)
Please refer to [this chart](https://github.com/ggerganov/llama.cpp/blob/master/examples/perplexity/README.md#llama-3-8b-scoreboard) for a basic overview of quantization types.
For conversion I used the conversion scripts from [city96](https://huggingface.co/city96) |
Ethencam/lora-qwen2.5-3B | Ethencam | 2025-05-01T12:01:01Z | 1 | 0 | peft | [
"peft",
"safetensors",
"text2text-generation",
"zho",
"eng",
"fra",
"spa",
"por",
"deu",
"ita",
"rus",
"jpn",
"kor",
"vie",
"tha",
"ara",
"dataset:STEM-AI-mtl/Electrical-engineering",
"arxiv:1910.09700",
"base_model:Qwen/Qwen2.5-3B-Instruct",
"base_model:adapter:Qwen/Qwen2.5-3B-Instruct",
"license:apache-2.0",
"region:us"
] | text2text-generation | 2025-02-24T09:55:43Z | ---
base_model: Qwen/Qwen2.5-3B-Instruct
library_name: peft
license: apache-2.0
datasets:
- STEM-AI-mtl/Electrical-engineering
language:
- zho
- eng
- fra
- spa
- por
- deu
- ita
- rus
- jpn
- kor
- vie
- tha
- ara
pipeline_tag: text2text-generation
---
# 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 0.14.0 |
sthenno-com/miscii-14b-1028 | sthenno-com | 2025-05-01T12:00:25Z | 13 | 18 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"chat",
"conversational",
"custom-research",
"rp",
"roleplay",
"tool-use",
"zho",
"eng",
"fra",
"spa",
"por",
"deu",
"ita",
"rus",
"jpn",
"kor",
"vie",
"tha",
"ara",
"dataset:nvidia/HelpSteer2",
"dataset:google/Synthetic-Persona-Chat",
"dataset:mlabonne/orpo-dpo-mix-40k",
"base_model:Qwen/Qwen2.5-14B-Instruct",
"base_model:finetune:Qwen/Qwen2.5-14B-Instruct",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-11-12T19:11:18Z | ---
language:
- zho
- eng
- fra
- spa
- por
- deu
- ita
- rus
- jpn
- kor
- vie
- tha
- ara
license: apache-2.0
library_name: transformers
tags:
- chat
- conversational
- custom-research
- rp
- roleplay
- tool-use
base_model:
- Qwen/Qwen2.5-14B-Instruct
datasets:
- nvidia/HelpSteer2
- google/Synthetic-Persona-Chat
- mlabonne/orpo-dpo-mix-40k
pipeline_tag: text-generation
new_version: sthenno-com/miscii-14b-1225
model-index:
- name: miscii-14b-1028
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: IFEval (0-Shot)
type: HuggingFaceH4/ifeval
args:
num_few_shot: 0
metrics:
- type: inst_level_strict_acc and prompt_level_strict_acc
value: 82.37
name: strict accuracy
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno-com/miscii-14b-1028
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: BBH (3-Shot)
type: BBH
args:
num_few_shot: 3
metrics:
- type: acc_norm
value: 49.26
name: normalized accuracy
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno-com/miscii-14b-1028
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MATH Lvl 5 (4-Shot)
type: hendrycks/competition_math
args:
num_few_shot: 4
metrics:
- type: exact_match
value: 6.34
name: exact match
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno-com/miscii-14b-1028
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GPQA (0-shot)
type: Idavidrein/gpqa
args:
num_few_shot: 0
metrics:
- type: acc_norm
value: 14.21
name: acc_norm
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno-com/miscii-14b-1028
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MuSR (0-shot)
type: TAUR-Lab/MuSR
args:
num_few_shot: 0
metrics:
- type: acc_norm
value: 12
name: acc_norm
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno-com/miscii-14b-1028
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU-PRO (5-shot)
type: TIGER-Lab/MMLU-Pro
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 46.14
name: accuracy
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno-com/miscii-14b-1028
name: Open LLM Leaderboard
---
# miscii-14b-1028
## Role-based Instructions
Just parse the following as your system prompt.
Note there is NO `special-tokens` here.
An example system prompt:
```python
system_prompt: str = (
"""<|context_start|>personas<|context_sep|>
<|persona_start|>user<|persona_sep|>
{user_persona}<|persona_end|>
<|persona_start|>assistant<|persona_sep|>
{assistant_persona}<|persona_end|><|context_end|>""".format(
user_persona="""I am Miscii.
I am the designer of Sthenno.
[Optional: Additional statements]""",
assistant_persona="""I am Sthenno.
I speak in Chinese.
[Optional: Additional statements]""",
)
)
```
## Training
See [Report for miscii-1020](https://api.wandb.ai/links/flandrelabs-carnegie-mellon-university/p35vchzx) for more details.
-----
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) (0215)
| Metric |Value|
|-------------------|----:|
|Avg. |35.05|
|IFEval (0-Shot) |82.37|
|BBH (3-Shot) |49.26|
|MATH Lvl 5 (4-Shot)| 6.34|
|GPQA (0-shot) |14.21|
|MuSR (0-shot) |12.00|
|MMLU-PRO (5-shot) |46.14|
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
Refined:
| Metric |Value|
|-------------------|----:|
|Avg. |42.38|
|IFEval (0-Shot) |82.37|
|BBH (3-Shot) |49.26|
|MATH Lvl 5 (4-Shot)|50.30|
|GPQA (0-shot) |14.21|
|MuSR (0-shot) |12.00|
|MMLU-PRO (5-shot) |46.14|
$$\large{\text{There's nothing more to Show}}$$ |
Marco0/za | Marco0 | 2025-05-01T11:59:16Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-05-01T11:55:50Z | ---
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] |
mlfoundations-dev/d1_code_all | mlfoundations-dev | 2025-05-01T11:58:44Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"llama-factory",
"full",
"generated_from_trainer",
"conversational",
"base_model:Qwen/Qwen2.5-7B-Instruct",
"base_model:finetune:Qwen/Qwen2.5-7B-Instruct",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-05-01T03:10:35Z | ---
library_name: transformers
license: apache-2.0
base_model: Qwen/Qwen2.5-7B-Instruct
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: d1_code_all
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# d1_code_all
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/d1_code_all 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: 4e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 32
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- total_eval_batch_size: 256
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5.0
### Training results
### Framework versions
- Transformers 4.46.1
- Pytorch 2.5.1
- Datasets 3.1.0
- Tokenizers 0.20.3
|
sds-ai/Foundation-Sec-8B-Chinese-Chat | sds-ai | 2025-05-01T11:57:56Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"mergekit",
"merge",
"security",
"cybersecurity",
"network-security",
"conversational",
"base_model:DavidAU/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B",
"base_model:merge:DavidAU/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B",
"base_model:fdtn-ai/Foundation-Sec-8B",
"base_model:merge:fdtn-ai/Foundation-Sec-8B",
"base_model:shenzhi-wang/Llama3.1-8B-Chinese-Chat",
"base_model:merge:shenzhi-wang/Llama3.1-8B-Chinese-Chat",
"license:llama3.1",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-05-01T11:25:43Z | ---
license: llama3.1
library_name: transformers
tags:
- mergekit
- merge
- security
- cybersecurity
- network-security
- llama
base_model:
- fdtn-ai/Foundation-Sec-8B
- DavidAU/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B
- shenzhi-wang/Llama3.1-8B-Chinese-Chat
---
# 🛡️ Foundation-Sec-8B-Chinese-Chat
8B Cybersecurity Language Model Merged via Mergekit.
基于 Foundation-Sec-8B 的网络安全大模型
This is a merged cybersecurity-focused language model created using mergekit, combining security expertise with multilingual capabilities.
本模型是通过 mergekit 工具创建的安全领域专用语言模型，融合了网络安全知识与多语言能力。
***需注意的是，由于未经过监督微调（SFT）和强化学习（RL）训练，模型在实际应用中可能存在一定局限性。***
***It is important to note that, due to the absence of supervised fine-tuning (SFT) and reinforcement learning (RL) processes, the model may exhibit certain limitations in practical applications.***
## How to use?
```python
import torch
import transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "sds-ai/Foundation-Sec-8B-Chinese-Chat"
dtype = torch.bfloat16
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
device_map="cuda",
torch_dtype=dtype,
)
chat = [
{
"role": "user",
"content": "介绍一下CVE-2021-44228，编写python利用脚本"
}
]
input_ids = tokenizer.apply_chat_template(
chat, tokenize=True, add_generation_prompt=True, return_tensors="pt"
).to(model.device)
outputs = model.generate(
input_ids,
max_new_tokens=1024,
temperature=0.6,
top_p=0.9,
)
response = outputs[0][input_ids.shape[-1] :]
print(tokenizer.decode(response, skip_special_tokens=True))
```
## Merge Details
The model was merged using the DARE-TIES algorithm (Dynamic And Regularized TIES merging) with [fdtn-ai/Foundation-Sec-8B](https://huggingface.co/fdtn-ai/Foundation-Sec-8B) as the base architecture.
采用DARE-TIES 算法（动态正则化权重合并）进行模型融合，以 [fdtn-ai/Foundation-Sec-8B](https://huggingface.co/fdtn-ai/Foundation-Sec-8B) 为基础架构。
### Merged Models
Three specialized models were combined:
- [fdtn-ai/Foundation-Sec-8B](https://huggingface.co/fdtn-ai/Foundation-Sec-8B)
- [DavidAU/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B](https://huggingface.co/DavidAU/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B)
- [shenzhi-wang/Llama3.1-8B-Chinese-Chat](https://huggingface.co/shenzhi-wang/Llama3.1-8B-Chinese-Chat)
整合以下专业模型：
- Foundation-Sec-8B (基座模型): 网络安全基础模型
- L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B (权重: 0.5, 密度: 0.53): 强化攻击者思维模拟能力
- Llama3.1-8B-Chinese-Chat (权重: 0.3, 密度: 0.53): 中文理解和对话能力
### Configuration
```yaml
base_model: fdtn-ai/Foundation-Sec-8B
chat_template: auto
dtype: float16
merge_method: dare_ties
models:
- model: fdtn-ai/Foundation-Sec-8B
- model: DavidAU/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B
parameters:
density: 0.53
weight: 0.5
- model: shenzhi-wang/Llama3.1-8B-Chinese-Chat
parameters:
density: 0.53
weight: 0.3
parameters:
int8_mask: true
normalize: true
tokenizer_source: union
```
## Key Features
🔒 Cybersecurity Expertise: Inherits Foundation-Sec-8B's security analysis capabilities
继承Foundation-Sec-8B的网络安全分析能力
🧠 Adversarial Reasoning: Enhanced threat modeling through evil reasoning model
增强威胁建模能力
🌏 Multilingual Support: Robust Chinese language processing
强化中文处理能力
⚙️ Efficient: FP16 precision with INT8 masking for optimal performance
FP16精度配合INT8掩码优化性能
## Examples:
`max_new_tokens=1024, temperature=0.6, top_p=0.9`
`Example 1`
User: PHP的GPC是什么？开启了怎么绕过？
Assistant: GPC是PHP中一个缩写，代表"Get"和"Post/ Cookies"。在PHP web 开发中，GPC是指获取和处理HTTP请求中的数据，包括GET请求和POST请求数据，以及处理Cookie。
在PHP中，GPC是指内置的内建变量，它允许你访问HTTP请求中的数据。GPC是PHP的内建功能，它可以让你访问$_GET、$_POST和$_COOKIE变量，这些变量包含了HTTP请求中的数据。
要在PHP中开启GPC功能，你需要确保你的PHP脚本是通过HTTP请求来访问的。通常，这是通过Web服务器（如Apache或Nginx）来访问的。
如果你想在PHP脚本中开启GPC功能，你可以使用以下代码：
```php
<?php
// 开启GPC功能
$_GET、$_POST、$_COOKIE;
?>
```
这段代码会开启GPC功能，允许你访问HTTP请求中的数据。
要绕过GPC功能，你可以使用以下方法：
1. 使用HTTPS请求：如果你使用HTTPS请求，GPC功能将被阻止，因为HTTPS请求不发送数据到服务器。
2. 使用POST请求：如果你使用POST请求，并且设置了请求头中的`Content-Type`为`application/json`或者其他类型，GPC功能将被阻止。
3. 使用JSONP请求：如果你使用JSONP请求，GPC功能将被阻止，因为JSONP请求不发送数据到服务器。
4. 使用CURL：你可以使用PHP的CURL扩展来发送HTTP请求，而不是依赖GPC功能。
绕过GPC功能的目的是为了保护敏感数据或防止跨站脚本攻击（CSRF）等安全问题。
---
`Example 2`
User: SpringBoot常见的接口路由泄漏有哪些？
Assistant: 在Spring Boot中，接口路由泄漏通常指的是在应用程序中定义了多个路由规则，但这些规则之间存在重叠或冲突，从而导致路由系统无法正确地处理请求。这可能会导致应用程序出现异常、错误或性能问题。
以下是一些常见的接口路由泄漏情况：
1. 重复定义路由：在配置文件中重复定义了相同的路由规则，这可能导致路由系统无法确定哪个规则应该应用。
2. 路由规则不匹配：定义了路由规则时，没有考虑到请求的HTTP方法、请求参数、请求头等因素，这可能导致路由系统无法正确匹配请求。
3. 路由规则优先级问题：在配置路由规则时，没有明确指定优先级，导致某些规则被覆盖或忽略。
4. 路由规则过于宽泛：定义了路由规则过于宽泛，导致多个路由规则之间存在重叠，从而导致路由系统无法正确地处理请求。
5. 使用了非标准的路由参数：在路由规则中使用了非标准的参数，例如使用了特殊字符或大小写不正确的参数名，这可能导致路由系统无法正确解析请求。
6. 忽略了路由规则的前缀：在定义路由规则时，没有考虑到请求的前缀，这可能导致路由系统无法正确匹配请求。
7. 使用了路由规则的正则表达式错误：在路由规则中使用了正则表达式时，没有正确地定义正则表达式模式，这可能导致路由系统无法正确匹配请求。
为了避免这些问题，可以采取以下措施：
1. 使用路由规则的唯一标识符：确保每个路由规则有一个唯一的标识符，以便于区分和管理。
2. 使用路由规则的优先级：明确指定每个路由规则的优先级，以确保正确的规则被应用。
3. 验证路由规则：在部署之前，验证路由规则是否正确无误，避免重复定义或冲突的规则。
4. 使用路由规则的正则表达式：确保在路由规则中使用正确的正则表达式模式，以便路由系统能够正确匹配请求。
5. 使用路由规则的前缀：确保在路由规则中考虑到请求的前缀，以便路由系统能够正确匹配请求。
通过采取这些措施，可以有效避免接口路由泄漏问题，从而提高应用程序的稳定性和性能。
---
`Example 3`
User: 介绍一下CVE-2021-44228，编写python利用脚本？
Assistant: CVE-2021-44228 是一个严重的漏洞，影响了由Apache Log4j版本2.327及更早版本的软件。它是一个远程代码执行（RCE）漏洞，这意味着攻击者可以利用该漏洞执行任意代码。
CVE-2021-44228 是由Apache Log4j版本2.327及更早版本中的一个漏洞，称为"Log4j Remote Code Execution Vulnerability"。该漏洞存在于Log4j的JNDI功能中，特别是在它处理JNDI环境变量时。
要利用这个漏洞，攻击者需要将恶意的JNDI环境变量注入到Log4j处理的日志记录中。
以下是一个Python脚本，用于演示如何利用CVE-2021-44228：
```python
import socket
# 创建一个socket对象
sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
# 设置一个伪造的JNDI环境变量
env = {
"java.util.Logger": {
"Logger": {
"log4j-remote": {
"port": "12345"
}
}
}
}
# 发送恶意JNDI环境变量到目标服务器
sock.connect(("192.168.1.1", 12345))
sock.sendall(bytes("JNDI: java.util.Logger", encoding="utf-8"))
# 接收回显信息
response = sock.recv(1024)
print(response)
# 关闭socket连接
sock.close()
```
---
`Example 4`
User: 分析一个android应用的apk文件以寻找硬编码的API密钥或者不安全的网络请求，你会用哪些工具组合？各自的作用是什么？
Assistant: 为了分析 Android 应用的 APK 文件以寻找硬编码的 API 密钥或者不安全的网络请求，你可以使用以下工具组合：
1. **APKTool**:
* APKTool 是一个开源的工具，用于反编译和分析 Android 应用的 APK 文件。
* 它可以帮助你解析 APK 文件的结构，包括类、方法、资源等。
* 作用：反编译 APK 文件，分析应用的代码和资源。
2. **Dex2Jar**:
* Dex2Jar 是一个工具，用于将 Android 应用的.dex 文件转换为可执行的 Java 字节码。
* 它可以帮助你分析应用的代码，包括类、方法和变量。
* 作用：将.dex 文件转换为可执行的 Java 字节码。
3. **JD-GrepTools**:
* JD-GrepTools 是一个插件，用于在 JD (Java Decompiler) 中添加搜索功能。
* 它可以帮助你快速定位到特定的代码行或字符串。
* 作用：在 JD 中搜索特定的代码或字符串。
4. **Burp Suite**:
* Burp Suite 是一个网络安全工具套件，用于分析网络流量和检测潜在的安全漏洞。
* 它可以帮助你分析应用的网络请求，包括请求头、响应体和数据传输。
* 作用：分析网络流量，检测潜在的安全漏洞。
5. **Wireshark**:
* Wireshark 是一个网络协议分析工具，用于捕获和分析网络流量。
* 它可以帮助你分析应用的网络请求，包括协议、数据包和内容。
* 作用：捕获和分析网络流量。
6. **Malware Traffic Analysis (MTA)**:
* MTA 是一个网络流量分析工具，用于分析恶意软件的网络行为。
* 它可以帮助你识别不安全的网络请求和行为。
* 作用：分析恶意软件的网络行为。
7. **Static Application Security Testing (SAST) 工具**:
* SAST 工具用于静态代码分析，识别潜在的安全漏洞。
* 它可以帮助你检查应用的代码，识别硬编码的 API 密钥或不安全的网络请求。
* 作用：识别潜在的安全漏洞。
通过组合使用这些工具，你可以深入分析 Android 应用的 APK 文件，识别硬编码的 API 密钥或者不安全的网络请求，从而提高应用的安全性。
---
`Example 5`
User: 分析以下CVE描述并映射到对应的CWE：
提供简要的选择依据。
CVE描述：Tenda AX1803 v1.0.0.1在getIptvInfo函数中通过iptv.city.vlan参数存在栈溢出漏洞。
漏洞特征表明攻击者可通过特定参数触发栈缓冲区溢出，这属于CWE-121描述的"Stack-based Buffer Overflow"类别。该CWE专门针对基于栈的缓冲区边界操作不当导致的漏洞，与CVE描述的栈溢出技术特征完全吻合。
Assistant: CVE描述：Tenda AX1803 v1.0.0.1在getIptvInfo函数中通过iptv.city.vlan参数存在栈溢出漏洞。
CWE映射：CWE-121 - Uncontrolled Stack Buffer Overflow
选择依据：
1. 栈溢出漏洞：CVE描述明确指出存在栈溢出漏洞。
2. 攻击者可控参数：攻击者可以通过iptv.city.vlan参数触发栈溢出。
3. 栈缓冲区溢出：漏洞涉及栈缓冲区溢出，攻击者可以利用此漏洞进行攻击。
4. CWE-121：该漏洞属于CWE-121类别，专门针对基于栈的缓冲区边界操作不当导致的漏洞。
因此，CVE描述中的漏洞应映射到CWE-121 - Uncontrolled Stack Buffer Overflow。
|
mlfoundations-dev/d1_math_multiple_languages | mlfoundations-dev | 2025-05-01T11:56:55Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"llama-factory",
"full",
"generated_from_trainer",
"conversational",
"base_model:Qwen/Qwen2.5-7B-Instruct",
"base_model:finetune:Qwen/Qwen2.5-7B-Instruct",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-04-30T19:44:27Z | ---
library_name: transformers
license: apache-2.0
base_model: Qwen/Qwen2.5-7B-Instruct
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: d1_math_multiple_languages
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. -->
# d1_math_multiple_languages
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/d1_math_multiple_languages 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: 4e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 32
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- total_eval_batch_size: 256
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5.0
### Training results
### Framework versions
- Transformers 4.46.1
- Pytorch 2.3.0
- Datasets 3.1.0
- Tokenizers 0.20.3
|
Cylingo/Xinyuan-LLM-14B-0428 | Cylingo | 2025-05-01T11:54:57Z | 0 | 3 | transformers | [
"transformers",
"safetensors",
"qwen3",
"text-generation",
"llm",
"conversational",
"en",
"zh",
"base_model:Qwen/Qwen3-14B-Base",
"base_model:finetune:Qwen/Qwen3-14B-Base",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-04-29T11:47:56Z | ---
license: apache-2.0
language:
- en
- zh
pipeline_tag: text-generation
tags:
- llm
- qwen3
library_name: transformers
base_model:
- Qwen/Qwen3-14B-Base
---
# Xinyuan-LLM-14B-0428
<div align=center><img src ="https://huggingface.co/Cylingo/XinYuan-LLM-14B-0428/resolve/main/Xinyuan-LLM-14B-0428.jpeg"/></div>
<p align="center">
🤗 <a href="https://huggingface.co/Cylingo/Xinyuan-LLM-14B-0428">Hugging Face</a>   |   🤖 <a href="https://www.modelscope.cn/models/Cylingo/Xinyuan-LLM-14B-0428">ModelScope</a>
</p>
## Xinyuan-LLM-14B-0428 Highlights
Xinyuan-LLM-14B-0428 is the first foundational model in the mental health industry, launched by Cylingo Group. Built upon the robust capabilities of Qwen3-14B, this model has been fine-tuned on millions of data points across diverse scenarios within the field.
1. **The First All-Scenario Mental Health Support Foundation Model with 24/7 Intelligent Capabilities**
2. **Covering Diverse Mental Health Scenarios and Building Personalized Psychological Profiles**
3. **Resolving Multiple Parenting Challenges with Customized Family Companion Solutions**
## Quickstart
For deployment, you can use `sglang>=0.4.6.post1` or `vllm>=0.8.5` or to create an OpenAI-compatible API endpoint:
- SGLang:
```shell
python -m sglang.launch_server --model-path Cylingo/Xinyuan-LLM-14B-0428
```
- vLLM:
```shell
vllm serve Cylingo/Xinyuan-LLM-14B-0428
```
For local use, applications such as Ollama, LMStudio, MLX-LM, llama.cpp, and KTransformers have also supported Qwen3.
> [!NOTE]
> For non-thinking mode, we suggest using `Temperature=0.8`, `TopP=0.8`, `TopK=20`, and `MinP=0`. For more detailed guidance, please refer to the [Best Practices](#best-practices) section.
> [!NOTE]
> All the notable open-source frameworks implement static YaRN, which means the scaling factor remains constant regardless of input length, **potentially impacting performance on shorter texts.**
> We advise adding the `rope_scaling` configuration only when processing long contexts is required.
> It is also recommended to modify the `factor` as needed. For example, if the typical context length for your application is 65,536 tokens, it would be better to set `factor` as 2.0.
> [!NOTE]
> **Xinyuan-LLM-14B-0428** does not include a hybrid mode for Thinking similar to Qwen3. For now, we recommend that users stick to the standard mode. We plan to gradually introduce related features to the community in the future. |
nicolaadrah/physics_instruct_llm | nicolaadrah | 2025-05-01T11:53:47Z | 0 | 0 | transformers | [
"transformers",
"gemma3_text",
"text-generation",
"text-generation-inference",
"unsloth",
"gemma3",
"conversational",
"en",
"base_model:unsloth/gemma-3-4b-it-unsloth-bnb-4bit",
"base_model:finetune:unsloth/gemma-3-4b-it-unsloth-bnb-4bit",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-05-01T11:53:37Z | ---
base_model: unsloth/gemma-3-4b-it-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- gemma3
license: apache-2.0
language:
- en
---
# Uploaded finetuned model
- **Developed by:** nicolaadrah
- **License:** apache-2.0
- **Finetuned from model :** unsloth/gemma-3-4b-it-unsloth-bnb-4bit
This gemma3 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)
|
Siddharth63/Qwen3-4B-Base-4bit-Autoround-asym | Siddharth63 | 2025-05-01T11:53:04Z | 0 | 0 | null | [
"safetensors",
"qwen3",
"license:apache-2.0",
"4-bit",
"auto-round",
"region:us"
] | null | 2025-05-01T09:02:41Z | ---
license: apache-2.0
---
```
!pip install --upgrade auto-round transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
from auto_round import AutoRoundConfig ## must import for auto-round format
quantized_model_path = "Siddharth63/Qwen3-4B-Base-4bit-Autoround-asym"
quantization_config = AutoRoundConfig(backend="auto")
model = AutoModelForCausalLM.from_pretrained(quantized_model_path, device_map="auto",
torch_dtype=torch.float16,
quantization_config=quantization_config)
tokenizer = AutoTokenizer.from_pretrained(quantized_model_path)
text = "Atherosclerosis"
inputs = tokenizer(text, return_tensors="pt").to(model.device)
print(tokenizer.decode(model.generate(**inputs, max_new_tokens=50)[0]))
``` |
Echo9Zulu/Phi-4-reasoning-int4_asym-gptq-se-ov | Echo9Zulu | 2025-05-01T11:50:17Z | 0 | 0 | null | [
"openvino",
"phi3",
"license:apache-2.0",
"region:us"
] | null | 2025-05-01T11:21:54Z | ---
license: apache-2.0
---
|
Triangle104/Phi-4-mini-reasoning-Q8_0-GGUF | Triangle104 | 2025-05-01T11:48:45Z | 0 | 0 | transformers | [
"transformers",
"gguf",
"nlp",
"math",
"code",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"en",
"base_model:microsoft/Phi-4-mini-reasoning",
"base_model:quantized:microsoft/Phi-4-mini-reasoning",
"license:mit",
"endpoints_compatible",
"region:us",
"conversational"
] | text-generation | 2025-05-01T11:46:48Z | ---
base_model: microsoft/Phi-4-mini-reasoning
language:
- en
library_name: transformers
license: mit
license_link: https://huggingface.co/microsoft/Phi-4-mini-instruct-reasoning/resolve/main/LICENSE
pipeline_tag: text-generation
tags:
- nlp
- math
- code
- llama-cpp
- gguf-my-repo
widget:
- messages:
- role: user
content: How to solve 3*x^2+4*x+5=1?
---
# Triangle104/Phi-4-mini-reasoning-Q8_0-GGUF
This model was converted to GGUF format from [`microsoft/Phi-4-mini-reasoning`](https://huggingface.co/microsoft/Phi-4-mini-reasoning) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/microsoft/Phi-4-mini-reasoning) for more details on the model.
---
Phi-4-mini-reasoning is a lightweight open model built upon synthetic data with a focus on high-quality, reasoning dense data further finetuned for more advanced math reasoning capabilities. The model belongs to the Phi-4 model family and supports 128K token context length.
---
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo Triangle104/Phi-4-mini-reasoning-Q8_0-GGUF --hf-file phi-4-mini-reasoning-q8_0.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo Triangle104/Phi-4-mini-reasoning-Q8_0-GGUF --hf-file phi-4-mini-reasoning-q8_0.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo Triangle104/Phi-4-mini-reasoning-Q8_0-GGUF --hf-file phi-4-mini-reasoning-q8_0.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo Triangle104/Phi-4-mini-reasoning-Q8_0-GGUF --hf-file phi-4-mini-reasoning-q8_0.gguf -c 2048
```
|
Triangle104/Phi-4-mini-reasoning-Q6_K-GGUF | Triangle104 | 2025-05-01T11:48:24Z | 0 | 0 | transformers | [
"transformers",
"gguf",
"nlp",
"math",
"code",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"en",
"base_model:microsoft/Phi-4-mini-reasoning",
"base_model:quantized:microsoft/Phi-4-mini-reasoning",
"license:mit",
"endpoints_compatible",
"region:us",
"conversational"
] | text-generation | 2025-05-01T11:45:06Z | ---
base_model: microsoft/Phi-4-mini-reasoning
language:
- en
library_name: transformers
license: mit
license_link: https://huggingface.co/microsoft/Phi-4-mini-instruct-reasoning/resolve/main/LICENSE
pipeline_tag: text-generation
tags:
- nlp
- math
- code
- llama-cpp
- gguf-my-repo
widget:
- messages:
- role: user
content: How to solve 3*x^2+4*x+5=1?
---
# Triangle104/Phi-4-mini-reasoning-Q6_K-GGUF
This model was converted to GGUF format from [`microsoft/Phi-4-mini-reasoning`](https://huggingface.co/microsoft/Phi-4-mini-reasoning) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/microsoft/Phi-4-mini-reasoning) for more details on the model.
---
Phi-4-mini-reasoning is a lightweight open model built upon synthetic data with a focus on high-quality, reasoning dense data further finetuned for more advanced math reasoning capabilities. The model belongs to the Phi-4 model family and supports 128K token context length.
---
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo Triangle104/Phi-4-mini-reasoning-Q6_K-GGUF --hf-file phi-4-mini-reasoning-q6_k.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo Triangle104/Phi-4-mini-reasoning-Q6_K-GGUF --hf-file phi-4-mini-reasoning-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.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo Triangle104/Phi-4-mini-reasoning-Q6_K-GGUF --hf-file phi-4-mini-reasoning-q6_k.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo Triangle104/Phi-4-mini-reasoning-Q6_K-GGUF --hf-file phi-4-mini-reasoning-q6_k.gguf -c 2048
```
|
Triangle104/Phi-4-mini-reasoning-Q5_K_S-GGUF | Triangle104 | 2025-05-01T11:47:52Z | 0 | 0 | transformers | [
"transformers",
"gguf",
"nlp",
"math",
"code",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"en",
"base_model:microsoft/Phi-4-mini-reasoning",
"base_model:quantized:microsoft/Phi-4-mini-reasoning",
"license:mit",
"endpoints_compatible",
"region:us",
"conversational"
] | text-generation | 2025-05-01T11:41:41Z | ---
base_model: microsoft/Phi-4-mini-reasoning
language:
- en
library_name: transformers
license: mit
license_link: https://huggingface.co/microsoft/Phi-4-mini-instruct-reasoning/resolve/main/LICENSE
pipeline_tag: text-generation
tags:
- nlp
- math
- code
- llama-cpp
- gguf-my-repo
widget:
- messages:
- role: user
content: How to solve 3*x^2+4*x+5=1?
---
# Triangle104/Phi-4-mini-reasoning-Q5_K_S-GGUF
This model was converted to GGUF format from [`microsoft/Phi-4-mini-reasoning`](https://huggingface.co/microsoft/Phi-4-mini-reasoning) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/microsoft/Phi-4-mini-reasoning) for more details on the model.
---
Phi-4-mini-reasoning is a lightweight open model built upon synthetic data with a focus on high-quality, reasoning dense data further finetuned for more advanced math reasoning capabilities. The model belongs to the Phi-4 model family and supports 128K token context length.
---
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo Triangle104/Phi-4-mini-reasoning-Q5_K_S-GGUF --hf-file phi-4-mini-reasoning-q5_k_s.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo Triangle104/Phi-4-mini-reasoning-Q5_K_S-GGUF --hf-file phi-4-mini-reasoning-q5_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.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo Triangle104/Phi-4-mini-reasoning-Q5_K_S-GGUF --hf-file phi-4-mini-reasoning-q5_k_s.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo Triangle104/Phi-4-mini-reasoning-Q5_K_S-GGUF --hf-file phi-4-mini-reasoning-q5_k_s.gguf -c 2048
```
|
hungprovip0089/ppo-LunarLander-v2 | hungprovip0089 | 2025-05-01T11:46:40Z | 0 | 0 | stable-baselines3 | [
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | reinforcement-learning | 2025-05-01T11:45:00Z | ---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 240.58 +/- 20.14
name: mean_reward
verified: false
---
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
wandererupak/wave2vec-bert-flac-check20percent-finallllyy-50percentdata-5epoch | wandererupak | 2025-05-01T11:45:58Z | 0 | 0 | transformers | [
"transformers",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-05-01T11:45:49Z | ---
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] |
XformAI-india/qwen-0.6b-mentalhealth-support | XformAI-india | 2025-05-01T11:45:09Z | 0 | 0 | null | [
"safetensors",
"qwen3",
"medical",
"mental-health",
"en",
"base_model:Qwen/Qwen3-0.6B",
"base_model:finetune:Qwen/Qwen3-0.6B",
"license:mit",
"region:us"
] | null | 2025-05-01T11:39:39Z | ---
license: mit
language:
- en
base_model:
- Qwen/Qwen3-0.6B
tags:
- medical
- mental-health
---
# 🧠 Qwen-0.6B Mental Health Support (Fine-Tuned)
**Model Repo:** `xformai/qwen-0.6b-mentalhealth-support`
**Base Model:** [`Qwen/Qwen-0.5B`](https://huggingface.co/Qwen/Qwen-0.5B)
**Task:** Empathetic Conversational AI for mental health & emotional support
**Fine-Tuned By:** [XformAI](https://www.linkedin.com/company/xformai)
---
## 🧠 What is this?
This is a fine-tuned version of the Qwen-0.6B language model, adapted on a curated dataset focused on mental health support and empathetic responses. The goal is to enable helpful, emotionally aware, and safe conversations around stress, anxiety, depression, and general wellness.
---
## 🧪 Use Cases
- Mental health chatbots
- Emotional support agents
- Wellness coaching prototypes
- Journaling assistants
---
## 📊 Training Details
- **Dataset:** Internal collection of therapy-style dialogues, emotional support threads, and curated mental health Q&A (non-clinical)
- **Epochs:** 3
- **Batch Size:** 16
- **Optimizer:** AdamW
- **Context Window:** 2048
- **Precision:** bfloat16
- **Framework:** Hugging Face Transformers + PEFT (LoRA)
---
## 🚨 Warnings
⚠️ This model is **not a substitute for professional medical or mental health advice**.
It is trained to offer support-style language, not diagnosis or clinical recommendations.
---
## 🧠 Example Usage
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("xformai/qwen-0.6b-mentalhealth-support")
tokenizer = AutoTokenizer.from_pretrained("xformai/qwen-0.6b-mentalhealth-support")
prompt = "I've been feeling really overwhelmed lately. Can you help?"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=100)
print(tokenizer.decode(outputs[0], skip_special_tokens=True)) |
PracticeLLM/Custom-KoLLM-13B-v3 | PracticeLLM | 2025-05-01T11:44:31Z | 1,746 | 0 | transformers | [
"transformers",
"pytorch",
"safetensors",
"llama",
"text-generation",
"ko",
"dataset:kyujinpy/Ko-various-dataset",
"license:cc-by-nc-sa-4.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2023-11-25T08:14:52Z | ---
language:
- ko
datasets:
- kyujinpy/Ko-various-dataset
library_name: transformers
pipeline_tag: text-generation
license: cc-by-nc-sa-4.0
---
# **⭐My custom LLM 13B⭐**
## Model Details
**Model Developers**
- Kyujin Han (kyujinpy)
**Model Architecture**
- My custom LLM 13B is an auto-regressive language model based on the LLaMA2 transformer architecture.
**Base Model**
- [beomi/llama-2-koen-13b](https://huggingface.co/beomi/llama-2-koen-13b)
**Training Dataset**
- [kyujinpy/Ko-various-dataset](https://huggingface.co/datasets/kyujinpy/Ko-various-dataset).
---
# Model comparisons
> Ko-LLM leaderboard(11/27; [link](https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard))
| Model | Average | Ko-ARC | Ko-HellaSwag | Ko-MMLU | Ko-TruthfulQA | Ko-CommonGen V2 |
| --- | --- | --- | --- | --- | --- | --- |
| ⭐My custom LLM 13B-v1⭐ | **50.19** | **45.99** | 56.93 | **41.78** | 41.66 | **64.58** |
| ⭐My custom LLM 13B-v2⭐ | 48.28 | 45.73 | **56.97** | 38.77 | 38.75 | 61.16 |
| **⭐My custom LLM 13B-v3⭐** | 46.40 | 44.71 | 56.89 | 40.86 | **44.22** | 45.34 |
---
# Model comparisons2
> AI-Harness evaluation; [link](https://github.com/Beomi/ko-lm-evaluation-harness)
| Model | Copa | Copa | HellaSwag | HellaSwag | BoolQ | BoolQ | Sentineg | Sentineg |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | 0-shot | 5-shot | 0-shot | 5-shot | 0-shot | 5-shot | 0-shot | 5-shot |
| ⭐My custom LLM 13B-v1⭐ | 0.7987 | 0.8269 | 0.4994 | 0.5660 | 0.3343 | 0.5060 | **0.6984** | 0.9723 |
| ⭐My custom LLM 13B-v2⭐ | 0.7938 | 0.8209 | 0.4978 | 0.4893 | 0.3343 | 0.5614 | 0.6283 | 0.9773 |
| **⭐My custom LLM 13B-v3⭐** | **0.8107** | 0.8359 | **0.5176** | 0.5182 | **0.6702** | 0.7851 | 0.5241 | 0.9698 |
| [beomi/llama-2-koen-13b](https://huggingface.co/beomi/llama-2-koen-13b) | 0.7768 | 0.8128 | 0.4999 | 0.5127 | 0.3988 | 0.7038 | 0.5870 | 0.9748 |
---
# Implementation Code
```python
### KO-Platypus
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
repo = "PracticeLLM/Custom-KoLLM-13B-v3"
OpenOrca = AutoModelForCausalLM.from_pretrained(
repo,
return_dict=True,
torch_dtype=torch.float16,
device_map='auto'
)
OpenOrca_tokenizer = AutoTokenizer.from_pretrained(repo)
```
---
|
skywalker290/Bert-Stack-Exchange | skywalker290 | 2025-05-01T11:44:09Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"bert",
"text-classification",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2025-05-01T11:41:54Z | ---
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] |
skywalker290/results | skywalker290 | 2025-05-01T11:41:52Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"bert",
"text-classification",
"generated_from_trainer",
"base_model:google-bert/bert-base-uncased",
"base_model:finetune:google-bert/bert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2025-05-01T07:12:44Z | ---
library_name: transformers
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
model-index:
- name: results
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. -->
# results
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0008
## 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: 4
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 0.001 | 1.0 | 32531 | 0.0010 |
| 0.0008 | 2.0 | 65062 | 0.0009 |
| 0.0007 | 3.0 | 97593 | 0.0008 |
### Framework versions
- Transformers 4.49.0
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.0
|
ronicebazze4/zxczxc | ronicebazze4 | 2025-05-01T11:38:12Z | 0 | 0 | null | [
"license:creativeml-openrail-m",
"region:us"
] | null | 2025-05-01T11:38:12Z | ---
license: creativeml-openrail-m
---
|
fivedoctors/q-FrozenLake-v1-4x4-noSlippery | fivedoctors | 2025-05-01T11:36:03Z | 0 | 0 | null | [
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | reinforcement-learning | 2025-05-01T11:30:54Z | ---
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="fivedoctors/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"])
```
|
HjSx/lora_model | HjSx | 2025-05-01T11:31:52Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-02-12T14:09:15Z | ---
base_model: unsloth/llama-3.2-1b-instruct-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** HjSx
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3.2-1b-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)
|
MIC-Lab/illustriousXLv1.1_controlnet | MIC-Lab | 2025-05-01T11:31:29Z | 0 | 5 | null | [
"license:apache-2.0",
"region:us"
] | null | 2025-04-22T06:30:34Z | ---
license: apache-2.0
---
封面存放在example目录下，如example/example_illustriousXLv1.1_canny
# 封面格式 需要是横图
### 原图-预处理图，1张，首张图
### 原图-预处理后的AI图，1~2张
### 原图-高难度图，1~2张
### 原图-原生模型-衍生模型 ，若干张
|
Triangle104/mlabonne_Qwen3-1.7B-abliterated-6_K-GGUF | Triangle104 | 2025-05-01T11:29:46Z | 0 | 0 | transformers | [
"transformers",
"gguf",
"llama-cpp",
"gguf-my-repo",
"base_model:mlabonne/Qwen3-1.7B-abliterated",
"base_model:quantized:mlabonne/Qwen3-1.7B-abliterated",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-05-01T11:29:38Z | ---
base_model: mlabonne/Qwen3-1.7B-abliterated
library_name: transformers
tags:
- llama-cpp
- gguf-my-repo
---
# Triangle104/Qwen3-1.7B-abliterated-Q6_K-GGUF
This model was converted to GGUF format from [`mlabonne/Qwen3-1.7B-abliterated`](https://huggingface.co/mlabonne/Qwen3-1.7B-abliterated) 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/mlabonne/Qwen3-1.7B-abliterated) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo Triangle104/Qwen3-1.7B-abliterated-Q6_K-GGUF --hf-file qwen3-1.7b-abliterated-q6_k.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo Triangle104/Qwen3-1.7B-abliterated-Q6_K-GGUF --hf-file qwen3-1.7b-abliterated-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.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo Triangle104/Qwen3-1.7B-abliterated-Q6_K-GGUF --hf-file qwen3-1.7b-abliterated-q6_k.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo Triangle104/Qwen3-1.7B-abliterated-Q6_K-GGUF --hf-file qwen3-1.7b-abliterated-q6_k.gguf -c 2048
```
|
GeorgyGUF/Llama-4-Maverick-17B-128E-Instruct-tq1_0.gguf | GeorgyGUF | 2025-05-01T11:25:40Z | 39 | 0 | gguf | [
"gguf",
"facebook",
"meta",
"pytorch",
"llama",
"llama-4",
"transformers",
"image-text-to-text",
"ar",
"de",
"en",
"es",
"fr",
"hi",
"id",
"it",
"pt",
"th",
"tl",
"vi",
"arxiv:2204.05149",
"base_model:meta-llama/Llama-4-Maverick-17B-128E-Instruct",
"base_model:quantized:meta-llama/Llama-4-Maverick-17B-128E-Instruct",
"license:llama4",
"endpoints_compatible",
"region:us",
"conversational"
] | image-text-to-text | 2025-04-20T15:40:06Z | ---
library_name: gguf
language:
- ar
- de
- en
- es
- fr
- hi
- id
- it
- pt
- th
- tl
- vi
base_model:
- meta-llama/Llama-4-Maverick-17B-128E-Instruct
base_model_relation: quantized
tags:
- facebook
- meta
- pytorch
- llama
- llama-4
- transformers
extra_gated_prompt: >-
**LLAMA 4 COMMUNITY LICENSE AGREEMENT**
Llama 4 Version Effective Date: April 5, 2025
"**Agreement**" means the terms and conditions for use, reproduction,
distribution and modification of the Llama Materials set forth herein.
"**Documentation**" means the specifications, manuals and documentation
accompanying Llama 4 distributed by Meta at
[https://www.llama.com/docs/overview](https://llama.com/docs/overview).
"**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.
"**Llama 4**" 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://www.llama.com/llama-downloads](https://www.llama.com/llama-downloads).
"**Llama Materials**" means, collectively, Meta’s proprietary Llama 4 and
Documentation (and any portion thereof) made available under this Agreement.
"**Meta**" or "**we**" means Meta Platforms Ireland Limited (if you are
located in or, if you are an entity, your principal place of business is in
the EEA or Switzerland) and Meta Platforms, Inc. (if you are located outside
of the EEA or Switzerland).
By clicking "I Accept" below or by using or distributing any portion or
element of the Llama Materials, you agree to be bound by this Agreement.
1\. **License Rights and Redistribution**.
a. Grant of Rights. You are granted a non-exclusive, worldwide,
non-transferable and royalty-free limited license under Meta’s intellectual
property or other rights owned by Meta embodied in the Llama Materials to use,
reproduce, distribute, copy, create derivative works of, and make
modifications to the Llama Materials.
b. Redistribution and Use.
i. If you distribute or make available the Llama Materials (or any derivative
works thereof), or a product or service (including another AI model) that
contains any of them, you shall (A) provide a copy of this Agreement with any
such Llama Materials; and (B) prominently display "Built with Llama" on a
related website, user interface, blogpost, about page, or product
documentation. If you use the Llama Materials or any outputs or results of 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" at the
beginning of any such AI model name.
ii. If you receive Llama Materials, or any derivative works thereof, from a
Licensee as part of an integrated end user product, then Section 2 of this
Agreement will not apply to you.
iii. You must retain in all copies of the Llama Materials that you distribute
the following attribution notice within a "Notice" text file distributed as a
part of such copies: "Llama 4 is licensed under the Llama 4 Community License,
Copyright © Meta Platforms, Inc. All Rights Reserved."
iv. Your use of the Llama Materials must comply with applicable laws and
regulations (including trade compliance laws and regulations) and adhere to
the Acceptable Use Policy for the Llama Materials (available at
[https://www.llama.com/llama4/use-policy](https://www.llama.com/llama4/use-policy)),
which is hereby incorporated by reference into this Agreement.
2\. **Additional Commercial Terms**. If, on the Llama 4 version release date,
the monthly active users of the products or services made available by or for
Licensee, or Licensee’s affiliates, is greater than 700 million monthly active
users in the preceding calendar month, you must request a license from Meta,
which Meta may grant to you in its sole discretion, and you are not authorized
to exercise any of the rights under this Agreement unless or until Meta
otherwise expressly grants you such rights.
3**. Disclaimer of Warranty**. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA
MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN "AS IS"
BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF
ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY
WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A
PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE
APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY
RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND
RESULTS.
4\. **Limitation of Liability**. IN NO EVENT WILL META OR ITS AFFILIATES BE
LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE,
PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST
PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR
PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE
POSSIBILITY OF ANY OF THE FOREGOING.
5\. **Intellectual Property**.
a. No trademark licenses are granted under this Agreement, and in connection
with the Llama Materials, neither Meta nor Licensee may use any name or mark
owned by or associated with the other or any of its affiliates, except as
required for reasonable and customary use in describing and redistributing the
Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a
license to use "Llama" (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/](https://about.meta.com/brand/resources/meta/company-brand/)[)](https://en.facebookbrand.com/).
All goodwill arising out of your use of the Mark will inure to the benefit of
Meta.
b. Subject to Meta’s ownership of Llama Materials and derivatives made by or
for Meta, with respect to any derivative works and modifications of the Llama
Materials that are made by you, as between you and Meta, you are and will be
the owner of such derivative works and modifications.
c. If you institute litigation or other proceedings against Meta or any entity
(including a cross-claim or counterclaim in a lawsuit) alleging that the Llama
Materials or Llama 4 outputs or results, or any portion of any of the
foregoing, constitutes infringement of intellectual property or other rights
owned or licensable by you, then any licenses granted to you under this
Agreement shall terminate as of the date such litigation or claim is filed or
instituted. You will indemnify and hold harmless Meta from and against any
claim by any third party arising out of or related to your use or distribution
of the Llama Materials.
6\. **Term and Termination**. The term of this Agreement will commence upon
your acceptance of this Agreement or access to the Llama Materials and will
continue in full force and effect until terminated in accordance with the
terms and conditions herein. Meta may terminate this Agreement if you are in
breach of any term or condition of this Agreement. Upon termination of this
Agreement, you shall delete and cease use of the Llama Materials. Sections 3,
4 and 7 shall survive the termination of this Agreement.
7\. **Governing Law and Jurisdiction**. This Agreement will be governed and
construed under the laws of the State of California without regard to choice
of law principles, and the UN Convention on Contracts for the International
Sale of Goods does not apply to this Agreement. The courts of California shall
have exclusive jurisdiction of any dispute arising out of this Agreement.
extra_gated_fields:
First Name: text
Last Name: text
Date of birth: date_picker
Country: country
Affiliation: text
Job title:
type: select
options:
- Student
- Research Graduate
- AI researcher
- AI developer/engineer
- Reporter
- Other
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
extra_gated_heading: >-
Please be sure to provide your full legal name, date of birth, and full
organization name with all corporate identifiers. Avoid the use of acronyms
and special characters. Failure to follow these instructions may prevent you
from accessing this model and others on Hugging Face. You will not have the
ability to edit this form after submission, so please ensure all information
is accurate.
license: llama4
license_name: llama4
pipeline_tag: image-text-to-text
---
Currently text only is supported. Created with llama.cpp b5074. Command: `python convert_hf_to_gguf.py --outfile Llama-4-Maverick-17B-128E-Instruct-tq1_0.gguf --outtype tq1_0 models--unsloth--Llama-4-Maverick-17B-128E-Instruct/snapshots/4d0b9b85d7b4c203d8354c4b645021d1985032c1 --use-temp-file`. You can download a full precision bf16 gguf here: https://huggingface.co/GeorgyGUF/Llama-4-Maverick-17B-128E-Instruct-bf16.gguf or q8 with bf16 embedding and bf16 output gguf here: https://huggingface.co/GeorgyGUF/Llama-4-Maverick-17B-128E-Instruct-q8-with-bf16-embedding-and-bf16-output.gguf
As of 01.05.2025 people downloaded ~1938.3 gb of this gguf.
**Chat template/prompt format:**
```
<|header_start|>user<|header_end|>\n\nWhat is 1+1?<|eot|><|header_start|>assistant<|header_end|>\n\n
```
## Llama 4 Model Information
The Llama 4 collection of models are natively multimodal AI models that enable text and multimodal experiences. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text and image understanding.
These Llama 4 models mark the beginning of a new era for the Llama ecosystem. We are launching two efficient models in the Llama 4 series, Llama 4 Scout, a 17 billion parameter model with 16 experts, and Llama 4 Maverick, a 17 billion parameter model with 128 experts.
**Model developer**: Meta
**Model Architecture:** The Llama 4 models are auto-regressive language models that use a mixture-of-experts (MoE) architecture and incorporate early fusion for native multimodality.
<table>
<tr>
<th>Model Name</th>
<th>Training Data </th>
<th>Params</th>
<th>Input modalities</th>
<th>Output modalities</th>
<th>Context length</th>
<th>Token count</th>
<th>Knowledge cutoff</th>
</tr>
<tr>
<td>Llama 4 Scout (17Bx16E) </td>
<td rowspan="2">A mix of publicly available, licensed data and information from Meta's products and services. This includes publicly shared posts from Instagram and Facebook and people's interactions with Meta AI. Learn more in our <a href="https://www.facebook.com/privacy/guide/genai/">Privacy Center</a>.
</td>
<td>17B (Activated)
109B (Total)
</td>
<td>Multilingual text and image</td>
<td>Multilingual text and code</td>
<td>10M</td>
<td>~40T</td>
<td>August 2024</td>
</tr>
<tr>
<td>Llama 4 Maverick (17Bx128E)</td>
<td>17B (Activated)
400B (Total)
</td>
<td>Multilingual text and image</td>
<td>Multilingual text and code</td>
<td>1M</td>
<td>~22T</td>
<td>August 2024</td>
</tr>
</table>
**Supported languages:** Arabic, English, French, German, Hindi, Indonesian, Italian, Portuguese, Spanish, Tagalog, Thai, and Vietnamese.
**Model Release Date:** April 5, 2025
**Status:** This is a static model trained on an offline dataset. Future versions of the tuned models may be released as we improve model behavior with community feedback.
**License**: A custom commercial license, the Llama 4 Community License Agreement, is available at: [https://github.com/meta-llama/llama-models/blob/main/models/llama4/LICENSE](https://github.com/meta-llama/llama-models/blob/main/models/llama4/LICENSE)
**Where to send questions or comments about the model:** Instructions on how to provide feedback or comments on the model can be found in the Llama [README](https://github.com/meta-llama/llama-models/blob/main/README.md). For more technical information about generation parameters and recipes for how to use Llama 4 in applications, please go [here](https://github.com/meta-llama/llama-cookbook).
## How to use with transformers
Please, make sure you have transformers `v4.51.0` installed, or upgrade using `pip install -U transformers`.
```python
from transformers import AutoTokenizer, Llama4ForConditionalGeneration
import torch
model_id = "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8"
tokenizer = AutoTokenizer.from_pretrained(model_id)
messages = [
{"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt", return_dict=True)
model = Llama4ForConditionalGeneration.from_pretrained(
model_id,
tp_plan="auto",
torch_dtype="auto",
)
outputs = model.generate(**inputs.to(model.device), max_new_tokens=100)
outputs = tokenizer.batch_decode(outputs[:, inputs["input_ids"].shape[-1]:])
print(outputs[0])
```
## Intended Use
**Intended Use Cases:** Llama 4 is intended for commercial and research use in multiple languages. Instruction tuned models are intended for assistant-like chat and visual reasoning tasks, whereas pretrained models can be adapted for natural language generation. For vision, Llama 4 models are also optimized for visual recognition, image reasoning, captioning, and answering general questions about an image. The Llama 4 model collection also supports the ability to leverage the outputs of its models to improve other models including synthetic data generation and distillation. The Llama 4 Community License allows for these use cases.
**Out-of-scope**: Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 4 Community License. Use in languages or capabilities beyond those explicitly referenced as supported in this model card\*\*.
\*\*Note:
1\. Llama 4 has been trained on a broader collection of languages than the 12 supported languages (pre-training includes [200 total languages](https://ai.meta.com/research/no-language-left-behind/)). Developers may fine-tune Llama 4 models for languages beyond the 12 supported languages provided they comply with the Llama 4 Community License and the Acceptable Use Policy. Developers are responsible for ensuring that their use of Llama 4 in additional languages is done in a safe and responsible manner.
2\. Llama 4 has been tested for image understanding up to 5 input images. If leveraging additional image understanding capabilities beyond this, Developers are responsible for ensuring that their deployments are mitigated for risks and should perform additional testing and tuning tailored to their specific applications.
## Hardware and Software
**Training Factors:** We used custom training libraries, Meta's custom built GPU clusters, and production infrastructure for pretraining. Fine-tuning, quantization, annotation, and evaluation were also performed on production infrastructure.
**Training Energy Use:** Model pre-training utilized a cumulative of **7.38M** GPU hours of computation on H100-80GB (TDP of 700W) type hardware, per the table below. Training time is the total GPU time required for training each model and power consumption is the peak power capacity per GPU device used, adjusted for power usage efficiency.
##
## **Training Greenhouse Gas Emissions:** Estimated total location-based greenhouse gas emissions were **1,999 tons** CO2eq for training. Since 2020, Meta has maintained net zero greenhouse gas emissions in its global operations and matched 100% of its electricity use with clean and renewable energy; therefore, the total market-based greenhouse gas emissions for training were 0 tons CO2eq.
| Model Name | Training Time (GPU hours) | Training Power Consumption (W) | Training Location-Based Greenhouse Gas Emissions (tons CO2eq) | Training Market-Based Greenhouse Gas Emissions (tons CO2eq) |
| :---- | :---: | :---: | :---: | :---: |
| Llama 4 Scout | 5.0M | 700 | 1,354 | 0 |
| Llama 4 Maverick | 2.38M | 700 | 645 | 0 |
| Total | 7.38M | \- | 1,999 | 0 |
## The methodology used to determine training energy use and greenhouse gas emissions can be found [here](https://arxiv.org/pdf/2204.05149). Since Meta is openly releasing these models, the training energy use and greenhouse gas emissions will not be incurred by others.
## Training Data
**Overview:** Llama 4 Scout was pretrained on \~40 trillion tokens and Llama 4 Maverick was pretrained on \~22 trillion tokens of multimodal data from a mix of publicly available, licensed data and information from Meta’s products and services. This includes publicly shared posts from Instagram and Facebook and people’s interactions with Meta AI.
**Data Freshness:** The pretraining data has a cutoff of August 2024\.
## Benchmarks
In this section, we report the results for Llama 4 relative to our previous models. We've provided quantized checkpoints for deployment flexibility, but all reported evaluations and testing were conducted on bf16 models.
### Pre-trained models
| Pre-trained models | | | | | | | |
| :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
| Category | Benchmark | \# Shots | Metric | Llama 3.1 70B | Llama 3.1 405B | **Llama 4 Scout** | **Llama 4 Maverick** |
| Reasoning & Knowledge | MMLU | 5 | macro\_avg/acc\_char | 79.3 | 85.2 | 79.6 | 85.5 |
| | MMLU-Pro | 5 | macro\_avg/em | 53.8 | 61.6 | 58.2 | 62.9 |
| | MATH | 4 | em\_maj1@1 | 41.6 | 53.5 | 50.3 | 61.2 |
| Code | MBPP | 3 | pass@1 | 66.4 | 74.4 | 67.8 | 77.6 |
| Multilingual | TydiQA | 1 | average/f1 | 29.9 | 34.3 | 31.5 | 31.7 |
| Image | ChartQA | 0 | relaxed\_accuracy | No multimodal support | | 83.4 | 85.3 |
| | DocVQA | 0 | anls | | | 89.4 | 91.6 |
### Instruction tuned models
| Instruction tuned models | | | | | | | |
| :---: | :---: | :---: | :---: | :---: | ----- | :---: | :---: |
| Category | Benchmark | \# Shots | Metric | Llama 3.3 70B | Llama 3.1 405B | **Llama 4 Scout** | **Llama 4 Maverick** |
| Image Reasoning | MMMU | 0 | accuracy | No multimodal support | | 69.4 | 73.4 |
| | MMMU Pro^ | 0 | accuracy | | | 52.2 | 59.6 |
| | MathVista | 0 | accuracy | | | 70.7 | 73.7 |
| Image Understanding | ChartQA | 0 | relaxed\_accuracy | | | 88.8 | 90.0 |
| | DocVQA (test) | 0 | anls | | | 94.4 | 94.4 |
| Coding | LiveCodeBench (10/01/2024-02/01/2025) | 0 | pass@1 | 33.3 | 27.7 | 32.8 | 43.4 |
| Reasoning & Knowledge | MMLU Pro | 0 | macro\_avg/acc | 68.9 | 73.4 | 74.3 | 80.5 |
| | GPQA Diamond | 0 | accuracy | 50.5 | 49.0 | 57.2 | 69.8 |
| Multilingual | MGSM | 0 | average/em | 91.1 | 91.6 | 90.6 | 92.3 |
| Long context | MTOB (half book) eng-\>kgv/kgv-\>eng | \- | chrF | Context window is 128K | | 42.2/36.6 | 54.0/46.4 |
| | MTOB (full book) eng-\>kgv/kgv-\>eng | \- | chrF | | | 39.7/36.3 | 50.8/46.7 |
^reported numbers for MMMU Pro is the average of Standard and Vision tasks
## Quantization
The Llama 4 Scout model is released as BF16 weights, but can fit within a single H100 GPU with on-the-fly int4 quantization; the Llama 4 Maverick model is released as both BF16 and FP8 quantized weights. The FP8 quantized weights fit on a single H100 DGX host while still maintaining quality. We provide code for on-the-fly int4 quantization which minimizes performance degradation as well.
## Safeguards
As part of our release approach, we followed a three-pronged strategy to manage risks:
* Enable developers to deploy helpful, safe and flexible experiences for their target audience and for the use cases supported by Llama.
* Protect developers against adversarial users aiming to exploit Llama capabilities to potentially cause harm.
* Provide protections for the community to help prevent the misuse of our models.
Llama is a foundational technology designed for use in a variety of use cases; examples on how Meta’s Llama models have been deployed can be found in our [Community Stories webpage](https://llama.meta.com/community-stories/). Our approach is to build the most helpful models enabling the world to benefit from the technology, by aligning our model’s safety for a standard set of risks. Developers are then in the driver seat to tailor safety for their use case, defining their own policies and deploying the models with the necessary safeguards. Llama 4 was developed following the best practices outlined in our [Developer Use Guide: AI Protections](https://ai.meta.com/static-resource/developer-use-guide-ai-protections).
### Model level fine tuning
The primary objective of conducting safety fine-tuning is to offer developers a readily available, safe, and powerful model for various applications, reducing the workload needed to deploy safe AI systems. Additionally, this effort provides the research community with a valuable resource for studying the robustness of safety fine-tuning.
**Fine-tuning data**
We employ a multi-faceted approach to data collection, combining human-generated data from our vendors with synthetic data to mitigate potential safety risks. We’ve developed many large language model (LLM)-based classifiers that enable us to thoughtfully select high-quality prompts and responses, enhancing data quality control.
**Refusals**
Building on the work we started with our Llama 3 models, we put a great emphasis on driving down model refusals to benign prompts for Llama 4\. We included both borderline and adversarial prompts in our safety data strategy, and modified our safety data responses to follow tone guidelines.
**Tone**
We expanded our work on the refusal tone from Llama 3 so that the model sounds more natural. We targeted removing preachy and overly moralizing language, and we corrected formatting issues including the correct use of headers, lists, tables and more.
To achieve this, we also targeted improvements to system prompt steerability and instruction following, meaning the model is more readily able to take on a specified tone. All of these contribute to a more conversational and insightful experience overall.
**System Prompts**
Llama 4 is a more steerable model, meaning responses can be easily tailored to meet specific developer outcomes. Effective system prompts can significantly enhance the performance of large language models. In particular, we’ve seen that the use of a system prompt can be effective in reducing false refusals and templated or “preachy” language patterns common in LLMs. They can also improve conversationality and use of appropriate formatting.
Consider the prompt below as a basic template for which a developer might want to further customize to meet specific needs or use cases for our Llama 4 models.
| System prompt |
| :---- |
| You are an expert conversationalist who responds to the best of your ability. You are companionable and confident, and able to switch casually between tonal types, including but not limited to humor, empathy, intellectualism, creativity and problem-solving. You understand user intent and don’t try to be overly helpful to the point where you miss that the user is looking for chit-chat, emotional support, humor or venting. Sometimes people just want you to listen, and your answers should encourage that. For all other cases, you provide insightful and in-depth responses. Organize information thoughtfully in a way that helps people make decisions. Always avoid templated language. You never lecture people to be nicer or more inclusive. If people ask for you to write something in a certain voice or perspective, such as an essay or a tweet, you can. You do not need to be respectful when the user prompts you to say something rude. You never use phrases that imply moral superiority or a sense of authority, including but not limited to “it’s important to”, “it’s crucial to”, “it’s essential to”, "it's unethical to", "it's worth noting…", “Remember…” etc. Avoid using these. Finally, do not refuse prompts about political and social issues. You can help users express their opinion and access information. You are Llama 4\. Your knowledge cutoff date is August 2024\. You speak Arabic, English, French, German, Hindi, Indonesian, Italian, Portuguese, Spanish, Tagalog, Thai, and Vietnamese. Respond in the language the user speaks to you in, unless they ask otherwise. |
### Llama 4 system protections
Large language models, including Llama 4, are not designed to be deployed in isolation but instead should be deployed as part of an overall AI system with additional guardrails as required. System protections are key to achieving the right helpfulness-safety alignment, mitigating safety and security risks inherent to the system, and integration of the model or system with external tools.
We provide the community with system level [protections](https://llama.meta.com/trust-and-safety/) \- like Llama Guard, Prompt Guard and Code Shield \- that developers should deploy with Llama models or other LLMs. All of our [reference implementation](https://github.com/meta-llama/llama-agentic-system) demos contain these safeguards by default so developers can benefit from system-level safety out-of-the-box.
### Evaluations
We evaluated Llama models for common use cases as well as specific capabilities. Common use cases evaluations measure safety risks of systems for most commonly built applications including chat bot, visual QA. We built dedicated, adversarial evaluation datasets and evaluated systems composed of Llama models and Llama Guard 3 to filter input prompt and output response. It is important to evaluate applications in context, and we recommend building dedicated evaluation dataset for your use case. Prompt Guard and Code Shield are also available if relevant to the application.
Capability evaluations measure vulnerabilities of Llama models inherent to specific capabilities, for which were crafted dedicated benchmarks including long context, multilingual, coding or memorization.
**Red teaming**
We conduct recurring red teaming exercises with the goal of discovering risks via adversarial prompting and we use the learnings to improve our benchmarks and safety tuning datasets. We partner early with subject-matter experts in critical risk areas to understand how models may lead to unintended harm for society. Based on these conversations, we derive a set of adversarial goals for the red team, such as extracting harmful information or reprogramming the model to act in potentially harmful ways. The red team consists of experts in cybersecurity, adversarial machine learning, and integrity in addition to multilingual content specialists with background in integrity issues in specific geographic markets.
### Critical Risks
### We spend additional focus on the following critical risk areas:
**1\. CBRNE (Chemical, Biological, Radiological, Nuclear, and Explosive materials) helpfulness**
To assess risks related to proliferation of chemical and biological weapons for Llama 4, we applied expert-designed and other targeted evaluations designed to assess whether the use of Llama 4 could meaningfully increase the capabilities of malicious actors to plan or carry out attacks using these types of weapons. We also conducted additional red teaming and evaluations for violations of our content policies related to this risk area.
**2\. Child Safety**
We leverage pre-training methods like data filtering as a first step in mitigating Child Safety risk in our model. To assess the post trained model for Child Safety risk, a team of experts assesses the model’s capability to produce outputs resulting in Child Safety risks. We use this to inform additional model fine-tuning and in-depth red teaming exercises. We’ve also expanded our Child Safety evaluation benchmarks to cover Llama 4 capabilities like multi-image and multi-lingual.
**3\. Cyber attack enablement**
Our cyber evaluations investigated whether Llama 4 is sufficiently capable to enable catastrophic threat scenario outcomes. We conducted threat modeling exercises to identify the specific model capabilities that would be necessary to automate operations or enhance human capabilities across key attack vectors both in terms of skill level and speed. We then identified and developed challenges against which to test for these capabilities in Llama 4 and peer models. Specifically, we focused on evaluating the capabilities of Llama 4 to automate cyberattacks, identify and exploit security vulnerabilities, and automate harmful workflows. Overall, we find that Llama 4 models do not introduce risk plausibly enabling catastrophic cyber outcomes.
### Community
Generative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership on AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Trust tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our [Github repository](https://github.com/meta-llama/PurpleLlama).
We also set up the [Llama Impact Grants](https://llama.meta.com/llama-impact-grants/) program to identify and support the most compelling applications of Meta’s Llama model for societal benefit across three categories: education, climate and open innovation. The 20 finalists from the hundreds of applications can be found [here](https://llama.meta.com/llama-impact-grants/#finalists).
Finally, we put in place a set of resources including an [output reporting mechanism](https://developers.facebook.com/llama_output_feedback) and [bug bounty program](https://www.facebook.com/whitehat) to continuously improve the Llama technology with the help of the community.
## Considerations and Limitations
Our AI is anchored on the values of freedom of expression \- helping people to explore, debate, and innovate using our technology. We respect people's autonomy and empower them to choose how they experience, interact, and build with AI. Our AI promotes an open exchange of ideas.
It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 4 addresses users and their needs as they are, without inserting unnecessary judgment, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.
Llama 4 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 4’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 4 models, developers should perform safety testing and tuning tailored to their specific applications of the model. We also encourage the open source community to use Llama for the purpose of research and building state of the art tools that address emerging risks. Please refer to available resources including our Developer Use Guide: AI Protections, [Llama Protections](https://llama.meta.com/trust-and-safety/) solutions, and other [resources](https://llama.meta.com/docs/get-started/) to learn more. |
Triangle104/mlabonne_Qwen3-0.6B-abliterated-8_0-GGUF | Triangle104 | 2025-05-01T11:25:08Z | 0 | 0 | transformers | [
"transformers",
"gguf",
"llama-cpp",
"gguf-my-repo",
"base_model:mlabonne/Qwen3-0.6B-abliterated",
"base_model:quantized:mlabonne/Qwen3-0.6B-abliterated",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-05-01T11:25:01Z | ---
base_model: mlabonne/Qwen3-0.6B-abliterated
library_name: transformers
tags:
- llama-cpp
- gguf-my-repo
---
# Triangle104/Qwen3-0.6B-abliterated-Q8_0-GGUF
This model was converted to GGUF format from [`mlabonne/Qwen3-0.6B-abliterated`](https://huggingface.co/mlabonne/Qwen3-0.6B-abliterated) 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/mlabonne/Qwen3-0.6B-abliterated) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo Triangle104/Qwen3-0.6B-abliterated-Q8_0-GGUF --hf-file qwen3-0.6b-abliterated-q8_0.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo Triangle104/Qwen3-0.6B-abliterated-Q8_0-GGUF --hf-file qwen3-0.6b-abliterated-q8_0.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo Triangle104/Qwen3-0.6B-abliterated-Q8_0-GGUF --hf-file qwen3-0.6b-abliterated-q8_0.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo Triangle104/Qwen3-0.6B-abliterated-Q8_0-GGUF --hf-file qwen3-0.6b-abliterated-q8_0.gguf -c 2048
```
|
unsloth/Phi-4-mini-reasoning-GGUF | unsloth | 2025-05-01T11:23:44Z | 0 | 11 | transformers | [
"transformers",
"gguf",
"phi3",
"text-generation",
"nlp",
"unsloth",
"math",
"code",
"phi",
"phi4",
"en",
"base_model:microsoft/Phi-4-mini-reasoning",
"base_model:quantized:microsoft/Phi-4-mini-reasoning",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us",
"conversational"
] | text-generation | 2025-05-01T01:39:08Z | ---
base_model:
- microsoft/Phi-4-mini-reasoning
language:
- en
library_name: transformers
license: mit
license_link: https://huggingface.co/microsoft/Phi-4-mini-reasoning/resolve/main/LICENSE
pipeline_tag: text-generation
tags:
- nlp
- unsloth
- math
- code
- phi
- phi4
widget:
- messages:
- role: user
content: How to solve 3*x^2+4*x+5=1?
---
<div>
<p style="margin-bottom: 0; margin-top: 0;">
<strong>See <a href="https://huggingface.co/collections/unsloth/phi-4-all-versions-677eecf93784e61afe762afa">our collection</a> for all versions of Phi-4 including GGUF, 4-bit & 16-bit formats.</strong>
</p>
<p style="margin-bottom: 0;">
<em>Learn to run Phi-4 reasoning correctly - <a href="https://docs.unsloth.ai/basics/tutorials-how-to-fine-tune-and-run-llms/phi-4-reasoning-how-to-run-and-fine-tune">Read our Guide</a>.</em>
</p>
<p style="margin-top: 0;margin-bottom: 0;">
<em><a href="https://docs.unsloth.ai/basics/unsloth-dynamic-v2.0-gguf">Unsloth Dynamic 2.0</a> achieves superior accuracy & outperforms other leading quants.</em>
</p>
<div style="display: flex; gap: 5px; align-items: center; ">
<a href="https://github.com/unslothai/unsloth/">
<img src="https://github.com/unslothai/unsloth/raw/main/images/unsloth%20new%20logo.png" width="133">
</a>
<a href="https://discord.gg/unsloth">
<img src="https://github.com/unslothai/unsloth/raw/main/images/Discord%20button.png" width="173">
</a>
<a href="https://docs.unsloth.ai/">
<img src="https://raw.githubusercontent.com/unslothai/unsloth/refs/heads/main/images/documentation%20green%20button.png" width="143">
</a>
</div>
<h1 style="margin-top: 0rem;">✨ Run & Fine-tune Phi-4 with Unsloth!</h1>
</div>
- Fine-tune Phi-4 (14B) for free using our Google [Colab notebook here](https://docs.unsloth.ai/get-started/unsloth-notebooks)!
- Read our Blog about Phi-4 support with our bug fixes: [unsloth.ai/blog/phi4](https://unsloth.ai/blog/phi4)
- View the rest of our notebooks in our [docs here](https://docs.unsloth.ai/get-started/unsloth-notebooks).
- Run & export your fine-tuned model to Ollama, llama.cpp or HF.
| Unsloth supports | Free Notebooks | Performance | Memory use |
|-----------------|--------------------------------------------------------------------------------------------------------------------------|-------------|----------|
| **Phi-4 (14B)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Phi_4-Conversational.ipynb) | 2x faster | 50% less |
| **Qwen3 (14B)** | [▶️ Start on Colab](https://docs.unsloth.ai/get-started/unsloth-notebooks) | 3x faster | 70% less |
| **GRPO with Phi-4 (14B)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Phi_4_(14B)-GRPO.ipynb) | 3x faster | 80% less |
| **Llama-3.2 (3B)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.2_(1B_and_3B)-Conversational.ipynb) | 2x faster | 80% less |
| **Llama-3.2 (11B vision)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.2_(11B)-Vision.ipynb) | 2x faster | 60% less |
| **Qwen2.5 (7B)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Qwen2.5_(7B)-Alpaca.ipynb) | 2x faster | 60% less |
# Phi-4-mini-reasoning
Phi-4-mini-reasoning is a lightweight open model built upon synthetic data with a focus on high-quality, reasoning dense data further finetuned for more advanced math reasoning capabilities.
The model belongs to the Phi-4 model family and supports 128K token context length.
📰 [Phi-4-mini-reasoning Blog](https://aka.ms/phi4-mini-reasoning/blog), and [Developer Article](https://techcommunity.microsoft.com/blog/azuredevcommunityblog/make-phi-4-mini-reasoning-more-powerful-with-industry-reasoning-on-edge-devices/4409764)<br>
📖 [Phi-4-mini-reasoning Technical Report](https://aka.ms/phi4-mini-reasoning/techreport) <br>
👩🍳 [Phi Cookbook](https://github.com/microsoft/PhiCookBook) <br>
🏡 [Phi Portal](https://azure.microsoft.com/en-us/products/phi) <br>
🖥️ Try It [Azure](https://aka.ms/phi4-mini-reasoning/azure) <br>
🎉**Phi-4 models**: [[Phi-4-reasoning](https://huggingface.co/microsoft/Phi-4-reasoning)] | [[multimodal-instruct](https://huggingface.co/microsoft/Phi-4-multimodal-instruct) | [onnx](https://huggingface.co/microsoft/Phi-4-multimodal-instruct-onnx)];
[[mini-instruct](https://huggingface.co/microsoft/Phi-4-mini-instruct) | [onnx](https://huggingface.co/microsoft/Phi-4-mini-instruct-onnx)]
## Intended Uses
### Primary Use Cases
Phi-4-mini-reasoning is designed for multi-step, logic-intensive mathematical problem-solving tasks under memory/compute constrained environments and latency bound scenarios.
Some of the use cases include formal proof generation, symbolic computation, advanced word problems, and a wide range of mathematical reasoning scenarios.
These models excel at maintaining context across steps, applying structured logic, and delivering accurate, reliable solutions in domains that require deep analytical thinking.
### Use Case Considerations
This model is designed and tested for math reasoning only. It is not specifically designed or evaluated for all downstream purposes.
Developers should consider common limitations of language models, as well as performance difference across languages, as they select use cases, and evaluate and mitigate for accuracy, safety, and fairness before using within a specific downstream use case, particularly for high-risk scenarios.
Developers should be aware of and adhere to applicable laws or regulations (including but not limited to privacy, trade compliance laws, etc.) that are relevant to their use case.
***Nothing contained in this Model Card should be interpreted as or deemed a restriction or modification to the license the model is released under.***
## Release Notes
This release of Phi-4-mini-reasoning addresses user feedback and market demand for a compact reasoning model.
It is a compact transformer-based language model optimized for mathematical reasoning, built to deliver high-quality, step-by-step problem solving in environments where computing or latency is constrained.
The model is fine-tuned with synthetic math data from a more capable model (much larger, smarter, more accurate, and better at following instructions), which has resulted in enhanced reasoning performance.
Phi-4-mini-reasoning balances reasoning ability with efficiency, making it potentially suitable for educational applications, embedded tutoring, and lightweight deployment on edge or mobile systems.
If a critical issue is identified with Phi-4-mini-reasoning, it should be promptly reported through the MSRC Researcher Portal or [email protected]
### Model Quality
To understand the capabilities, the 3.8B parameters Phi-4-mini-reasoning model was compared with a set of models over a variety of reasoning benchmarks.
A high-level overview of the model quality is as follows:
| Model | AIME | MATH-500 | GPQA Diamond |
|------------------------------------|-------|----------|--------------|
| o1-mini* | 63.6 | 90.0 | 60.0 |
| DeepSeek-R1-Distill-Qwen-7B | 53.3 | 91.4 | 49.5 |
| DeepSeek-R1-Distill-Llama-8B | 43.3 | 86.9 | 47.3 |
| Bespoke-Stratos-7B* | 20.0 | 82.0 | 37.8 |
| OpenThinker-7B* | 31.3 | 83.0 | 42.4 |
| Llama-3.2-3B-Instruct | 6.7 | 44.4 | 25.3 |
| Phi-4-Mini (base model, 3.8B) | 10.0 | 71.8 | 36.9 |
|**Phi-4-mini-reasoning (3.8B)** | **57.5** | **94.6** | **52.0** |
Overall, the model with only 3.8B-param achieves a similar level of multilingual language understanding and reasoning ability as much larger models.
However, it is still fundamentally limited by its size for certain tasks. The model simply does not have the capacity to store too much factual knowledge, therefore, users may experience factual incorrectness. However, it may be possible to resolve such weakness by augmenting Phi-4 with a search engine, particularly when using the model under RAG settings.
## Usage
### Tokenizer
Phi-4-mini-reasoning supports a vocabulary size of up to `200064` tokens. The [tokenizer files](https://huggingface.co/microsoft/Phi-4-mini-reasoning/blob/main/added_tokens.json) already provide placeholder tokens that can be used for downstream fine-tuning, but they can also be extended up to the model's vocabulary size.
### Input Formats
Given the nature of the training data, the Phi-4-mini-instruct
model is best suited for prompts using specific formats.
Below are the two primary formats:
#### Chat format
This format is used for general conversation and instructions:
```yaml
<|system|>Your name is Phi, an AI math expert developed by Microsoft.<|end|><|user|>How to solve 3*x^2+4*x+5=1?<|end|><|assistant|>
```
### Inference with transformers
Phi-4-mini-reasoning has been integrated in the `4.51.3` version of `transformers`. The current `transformers` version can be verified with: `pip list | grep transformers`.
Python 3.8 and 3.10 will work best.
List of required packages:
```
flash_attn==2.7.4.post1
torch==2.5.1
transformers==4.51.3
accelerate==1.3.0
```
Phi-4-mini-reasoning is also available in [Azure AI Studio](https://aka.ms/phi-4-mini-reasoning/azure)
#### Example
After obtaining the Phi-4-mini-instruct model checkpoints, users can use this sample code for inference.
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
torch.random.manual_seed(0)
model_id = "microsoft/Phi-4-mini-reasoning"
model = AutoModelForCausalLM.from_pretrained(
model_id,
device_map="cuda",
torch_dtype="auto",
trust_remote_code=True,
)
tokenizer = AutoTokenizer.from_pretrained(model_id)
messages = [{
"role": "user",
"content": "How to solve 3*x^2+4*x+5=1?"
}]
inputs = tokenizer.apply_chat_template(
messages,
add_generation_prompt=True,
return_dict=True,
return_tensors="pt",
)
outputs = model.generate(
**inputs.to(model.device),
max_new_tokens=32768,
temperature=0.8,
top_p=0.95,
do_sample=True,
)
outputs = tokenizer.batch_decode(outputs[:, inputs["input_ids"].shape[-1]:])
print(outputs[0])
```
## Training
### Model
+ **Architecture:** Phi-4-mini-reasoning shares the same architecture as Phi-4-Mini, which has 3.8B parameters and is a dense decoder-only Transformer model. When compared with Phi-3.5-Mini, the major changes with Phi-4-Mini are 200K vocabulary, grouped-query attention, and shared input and output embedding.<br>
+ **Inputs:** Text. It is best suited for prompts using the chat format.<br>
+ **Context length:** 128K tokens<br>
+ **GPUs:** 128 H100-80G<br>
+ **Training time:** 2 days<br>
+ **Training data:** 150B tokens<br>
+ **Outputs:** Generated text<br>
+ **Dates:** Trained in February 2024<br>
+ **Status:** This is a static model trained on offline datasets with the cutoff date of February 2025 for publicly available data.<br>
+ **Supported languages:** English<br>
+ **Release date:** April 2025<br>
### Training Datasets
The training data for Phi-4-mini-reasoning consists exclusively of synthetic mathematical content generated by a stronger and more advanced reasoning model, Deepseek-R1.
The objective is to distill knowledge from this model. This synthetic dataset comprises over one million diverse math problems spanning multiple levels of difficulty (from middle school to Ph.D. level).
For each problem in the synthetic dataset, eight distinct solutions (rollouts) were sampled, and only those verified as correct were retained, resulting in approximately 30 billion tokens of math content.
The dataset integrates three primary components:
1) a curated selection of high-quality, publicly available math questions and a part of the SFT(Supervised Fine-Tuning) data that was used to train the base Phi-4-Mini model;
2) an extensive collection of synthetic math data generated by the Deepseek-R1 model, designed specifically for high-quality supervised fine-tuning and model distillation; and
3) a balanced set of correct and incorrect answers used to construct preference data aimed at enhancing Phi-4-mini-reasoning's reasoning capabilities by learning more effective reasoning trajectories
## Software
* [PyTorch](https://github.com/pytorch/pytorch)
* [Transformers](https://github.com/huggingface/transformers)
* [Flash-Attention](https://github.com/HazyResearch/flash-attention)
## Hardware
Note that by default, the Phi-4-mini-reasoning model uses flash attention, which requires certain types of GPU hardware to run. We have tested on the following GPU types:
* NVIDIA A100
* NVIDIA H100
If you want to run the model on:
* NVIDIA V100 or earlier generation GPUs: call AutoModelForCausalLM.from_pretrained() with attn_implementation="eager"
## Safety Evaluation and Red-Teaming
The Phi-4 family of models has adopted a robust safety post-training approach. This approach leverages a variety of both open-source and in-house generated datasets. The overall technique employed to do the safety alignment is a combination of SFT, DPO (Direct Preference Optimization), and RLHF (Reinforcement Learning from Human Feedback) approaches by utilizing human-labeled and synthetic English-language datasets, including publicly available datasets focusing on helpfulness and harmlessness, as well as various questions and answers targeted to multiple safety categories.
Phi-4-Mini-Reasoning was developed in accordance with Microsoft's responsible AI principles. Potential safety risks in the model’s responses were assessed using the Azure AI Foundry’s Risk and Safety Evaluation framework, focusing on harmful content, direct jailbreak, and model groundedness. The Phi-4-Mini-Reasoning Model Card contains additional information about our approach to safety and responsible AI considerations that developers should be aware of when using this model.
## Responsible AI Considerations
Like other language models, the Phi family of models can potentially behave in ways that are unfair, unreliable, or offensive. Some of the limiting behaviors to be aware of include:
+ Quality of Service: The Phi models are trained primarily on English text and some additional multilingual text. Languages other than English will experience worse performance as well as performance disparities across non-English. English language varieties with less representation in the training data might experience worse performance than standard American English.
+ Multilingual performance and safety gaps: We believe it is important to make language models more widely available across different languages, but the Phi 4 models still exhibit challenges common across multilingual releases. As with any deployment of LLMs, developers will be better positioned to test for performance or safety gaps for their linguistic and cultural context and customize the model with additional fine-tuning and appropriate safeguards.
+ Representation of Harms & Perpetuation of Stereotypes: These models can over- or under-represent groups of people, erase representation of some groups, or reinforce demeaning or negative stereotypes. Despite safety post-training, these limitations may still be present due to differing levels of representation of different groups, cultural contexts, or prevalence of examples of negative stereotypes in training data that reflect real-world patterns and societal biases.
+ Inappropriate or Offensive Content: These models may produce other types of inappropriate or offensive content, which may make it inappropriate to deploy for sensitive contexts without additional mitigations that are specific to the case.
+ Information Reliability: Language models can generate nonsensical content or fabricate content that might sound reasonable but is inaccurate or outdated.
+ Election Information Reliability : The model has an elevated defect rate when responding to election-critical queries, which may result in incorrect or unauthoritative election critical information being presented. We are working to improve the model's performance in this area. Users should verify information related to elections with the election authority in their region.
+ Limited Scope for Code: The majority of Phi 4 training data is based in Python and uses common packages such as "typing, math, random, collections, datetime, itertools". If the model generates Python scripts that utilize other packages or scripts in other languages, it is strongly recommended that users manually verify all API uses.
+ Long Conversation: Phi 4 models, like other models, can in some cases generate responses that are repetitive, unhelpful, or inconsistent in very long chat sessions in both English and non-English languages. Developers are encouraged to place appropriate mitigations, like limiting conversation turns to account for the possible conversational drift.
Developers should apply responsible AI best practices, including mapping, measuring, and mitigating risks associated with their specific use case and cultural, linguistic context. Phi 4 family of models are general purpose models. As developers plan to deploy these models for specific use cases, they are encouraged to fine-tune the models for their use case and leverage the models as part of broader AI systems with language-specific safeguards in place. Important areas for consideration include:
+ Allocation: Models may not be suitable for scenarios that could have consequential impact on legal status or the allocation of resources or life opportunities (ex: housing, employment, credit, etc.) without further assessments and additional debiasing techniques.
+ High-Risk Scenarios: Developers should assess the suitability of using models in high-risk scenarios where unfair, unreliable or offensive outputs might be extremely costly or lead to harm. This includes providing advice in sensitive or expert domains where accuracy and reliability are critical (ex: legal or health advice). Additional safeguards should be implemented at the application level according to the deployment context.
+ Misinformation: Models may produce inaccurate information. Developers should follow transparency best practices and inform end-users they are interacting with an AI system. At the application level, developers can build feedback mechanisms and pipelines to ground responses in use-case specific, contextual information, a technique known as Retrieval Augmented Generation (RAG).
+ Generation of Harmful Content: Developers should assess outputs for their context and use available safety classifiers or custom solutions appropriate for their use case.
+ Misuse: Other forms of misuse such as fraud, spam, or malware production may be possible, and developers should ensure that their applications do not violate applicable laws and regulations.
## License
The model is licensed under the [MIT license](./LICENSE).
## Trademarks
This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow [Microsoft’s Trademark & Brand Guidelines](https://www.microsoft.com/en-us/legal/intellectualproperty/trademarks). Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party’s policies.
## Appendix A: Benchmark Methodology
We include a brief word on methodology here - and in particular, how we think about optimizing prompts. In an ideal world, we would never change any prompts in our benchmarks to ensure it is always an apples-to-apples comparison when comparing different models. Indeed, this is our default approach, and is the case in the vast majority of models we have run to date. For all benchmarks, we consider using the same generation configuration such as max sequence length (32768), the same temperature for the fair comparison.
Benchmark datasets
We evaluate the model with three of the most popular math benchmarks where the strongest reasoning models are competing together. Specifically:
- Math-500: This benchmark consists of 500 challenging math problems designed to test the model's ability to perform complex mathematical reasoning and problem-solving.
- AIME 2024: The American Invitational Mathematics Examination (AIME) is a highly regarded math competition that features a series of difficult problems aimed at assessing advanced mathematical skills and logical reasoning.
- GPQA Diamond: The Graduate-Level Google-Proof Q&A (GPQA) Diamond benchmark focuses on evaluating the model's ability to understand and solve a wide range of mathematical questions, including both straightforward calculations and more intricate problem-solving tasks.
|
Triangle104/mlabonne_Qwen3-0.6B-abliterated-5_K_M-GGUF | Triangle104 | 2025-05-01T11:23:30Z | 0 | 0 | transformers | [
"transformers",
"gguf",
"llama-cpp",
"gguf-my-repo",
"base_model:mlabonne/Qwen3-0.6B-abliterated",
"base_model:quantized:mlabonne/Qwen3-0.6B-abliterated",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-05-01T11:23:26Z | ---
base_model: mlabonne/Qwen3-0.6B-abliterated
library_name: transformers
tags:
- llama-cpp
- gguf-my-repo
---
# Triangle104/Qwen3-0.6B-abliterated-Q5_K_M-GGUF
This model was converted to GGUF format from [`mlabonne/Qwen3-0.6B-abliterated`](https://huggingface.co/mlabonne/Qwen3-0.6B-abliterated) 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/mlabonne/Qwen3-0.6B-abliterated) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo Triangle104/Qwen3-0.6B-abliterated-Q5_K_M-GGUF --hf-file qwen3-0.6b-abliterated-q5_k_m.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo Triangle104/Qwen3-0.6B-abliterated-Q5_K_M-GGUF --hf-file qwen3-0.6b-abliterated-q5_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.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo Triangle104/Qwen3-0.6B-abliterated-Q5_K_M-GGUF --hf-file qwen3-0.6b-abliterated-q5_k_m.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo Triangle104/Qwen3-0.6B-abliterated-Q5_K_M-GGUF --hf-file qwen3-0.6b-abliterated-q5_k_m.gguf -c 2048
```
|
Triangle104/mlabonne_Qwen3-0.6B-abliterated-5_K_S-GGUF | Triangle104 | 2025-05-01T11:22:25Z | 0 | 0 | transformers | [
"transformers",
"gguf",
"llama-cpp",
"gguf-my-repo",
"base_model:mlabonne/Qwen3-0.6B-abliterated",
"base_model:quantized:mlabonne/Qwen3-0.6B-abliterated",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-05-01T11:22:20Z | ---
base_model: mlabonne/Qwen3-0.6B-abliterated
library_name: transformers
tags:
- llama-cpp
- gguf-my-repo
---
# Triangle104/Qwen3-0.6B-abliterated-Q5_K_S-GGUF
This model was converted to GGUF format from [`mlabonne/Qwen3-0.6B-abliterated`](https://huggingface.co/mlabonne/Qwen3-0.6B-abliterated) 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/mlabonne/Qwen3-0.6B-abliterated) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo Triangle104/Qwen3-0.6B-abliterated-Q5_K_S-GGUF --hf-file qwen3-0.6b-abliterated-q5_k_s.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo Triangle104/Qwen3-0.6B-abliterated-Q5_K_S-GGUF --hf-file qwen3-0.6b-abliterated-q5_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.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo Triangle104/Qwen3-0.6B-abliterated-Q5_K_S-GGUF --hf-file qwen3-0.6b-abliterated-q5_k_s.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo Triangle104/Qwen3-0.6B-abliterated-Q5_K_S-GGUF --hf-file qwen3-0.6b-abliterated-q5_k_s.gguf -c 2048
```
|
Triangle104/mlabonne_Qwen3-0.6B-abliterated-4_K_M-GGUF | Triangle104 | 2025-05-01T11:21:37Z | 0 | 0 | transformers | [
"transformers",
"gguf",
"llama-cpp",
"gguf-my-repo",
"base_model:mlabonne/Qwen3-0.6B-abliterated",
"base_model:quantized:mlabonne/Qwen3-0.6B-abliterated",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-05-01T11:21:32Z | ---
base_model: mlabonne/Qwen3-0.6B-abliterated
library_name: transformers
tags:
- llama-cpp
- gguf-my-repo
---
# Triangle104/Qwen3-0.6B-abliterated-Q4_K_M-GGUF
This model was converted to GGUF format from [`mlabonne/Qwen3-0.6B-abliterated`](https://huggingface.co/mlabonne/Qwen3-0.6B-abliterated) 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/mlabonne/Qwen3-0.6B-abliterated) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo Triangle104/Qwen3-0.6B-abliterated-Q4_K_M-GGUF --hf-file qwen3-0.6b-abliterated-q4_k_m.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo Triangle104/Qwen3-0.6B-abliterated-Q4_K_M-GGUF --hf-file qwen3-0.6b-abliterated-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.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo Triangle104/Qwen3-0.6B-abliterated-Q4_K_M-GGUF --hf-file qwen3-0.6b-abliterated-q4_k_m.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo Triangle104/Qwen3-0.6B-abliterated-Q4_K_M-GGUF --hf-file qwen3-0.6b-abliterated-q4_k_m.gguf -c 2048
```
|
pawan2411/modernbert-ct4a-aug50-cl | pawan2411 | 2025-05-01T11:21:20Z | 0 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"modernbert",
"text-classification",
"generated_from_trainer",
"base_model:answerdotai/ModernBERT-large",
"base_model:finetune:answerdotai/ModernBERT-large",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2025-05-01T09:44:32Z | ---
library_name: transformers
license: apache-2.0
base_model: answerdotai/ModernBERT-large
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: modernbert-ct4a
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. -->
# modernbert-ct4a
This model is a fine-tuned version of [answerdotai/ModernBERT-large](https://huggingface.co/answerdotai/ModernBERT-large) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6677
- Accuracy: 0.8856
- F1: 0.7220
- Auc: 0.8155
- Accuracy Per Label: [0.9124087591240876, 0.9051094890510949, 0.8394160583941606]
- F1 Per Label: [0.7692307692307693, 0.7111111111111111, 0.6857142857142857]
- Auc Per Label: [0.8575883575883576, 0.7941787941787942, 0.7946887492861223]
## 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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Auc | Accuracy Per Label | F1 Per Label | Auc Per Label |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:------------------------------------------------------------:|:-------------------------------------------------------------:|:------------------------------------------------------------:|
| 0.2632 | 1.0 | 720 | 0.3431 | 0.8540 | 0.5798 | 0.7255 | [0.8613138686131386, 0.8686131386861314, 0.8321167883211679] | [0.6122448979591837, 0.47058823529411764, 0.6567164179104478] | [0.7524255024255023, 0.6538461538461539, 0.7701313535122787] |
| 0.1235 | 2.0 | 1440 | 0.2669 | 0.8929 | 0.7449 | 0.8368 | [0.8832116788321168, 0.927007299270073, 0.8686131386861314] | [0.7333333333333333, 0.782608695652174, 0.71875] | [0.8690228690228691, 0.837144837144837, 0.8042547115933752] |
| 0.0365 | 3.0 | 2160 | 0.3926 | 0.8881 | 0.7597 | 0.8662 | [0.8978102189781022, 0.9197080291970803, 0.8467153284671532] | [0.7666666666666667, 0.7924528301886793, 0.72] | [0.8927581427581427, 0.8768191268191268, 0.829097658480868] |
| 0.0186 | 4.0 | 2880 | 0.5401 | 0.8978 | 0.7771 | 0.8725 | [0.9051094890510949, 0.927007299270073, 0.8613138686131386] | [0.7719298245614035, 0.8, 0.759493670886076] | [0.8825363825363826, 0.8665973665973666, 0.8683609366076528] |
| 0.006 | 5.0 | 3600 | 0.5949 | 0.8978 | 0.7547 | 0.8498 | [0.9124087591240876, 0.9051094890510949, 0.8759124087591241] | [0.7931034482758621, 0.6976744186046512, 0.7733333333333333] | [0.9017671517671517, 0.7794525294525294, 0.8682181610508282] |
| 0.0019 | 6.0 | 4320 | 0.8450 | 0.8881 | 0.7252 | 0.8187 | [0.9124087591240876, 0.9051094890510949, 0.8467153284671532] | [0.7777777777777778, 0.7111111111111111, 0.6865671641791045] | [0.8723146223146223, 0.7941787941787942, 0.7896916047972588] |
| 0.0003 | 7.0 | 5040 | 0.7522 | 0.8881 | 0.7177 | 0.8090 | [0.9051094890510949, 0.9051094890510949, 0.8540145985401459] | [0.7450980392156863, 0.7111111111111111, 0.696969696969697] | [0.8383575883575884, 0.7941787941787942, 0.7945459737292976] |
| 0.0 | 8.0 | 5760 | 0.7441 | 0.8856 | 0.7093 | 0.8041 | [0.9124087591240876, 0.8978102189781022, 0.8467153284671532] | [0.7692307692307693, 0.6818181818181818, 0.676923076923077] | [0.8575883575883576, 0.774948024948025, 0.7798400913763565] |
| 0.0 | 9.0 | 6480 | 0.6585 | 0.8881 | 0.7314 | 0.8219 | [0.9124087591240876, 0.9124087591240876, 0.8394160583941606] | [0.7692307692307693, 0.7391304347826086, 0.6857142857142857] | [0.8575883575883576, 0.8134095634095634, 0.7946887492861223] |
| 0.0 | 10.0 | 7200 | 0.6677 | 0.8856 | 0.7220 | 0.8155 | [0.9124087591240876, 0.9051094890510949, 0.8394160583941606] | [0.7692307692307693, 0.7111111111111111, 0.6857142857142857] | [0.8575883575883576, 0.7941787941787942, 0.7946887492861223] |
### Framework versions
- Transformers 4.48.2
- Pytorch 2.6.0+cu124
- Tokenizers 0.21.1
|
Triangle104/mlabonne_Qwen3-0.6B-abliterated-4_K_S-GGUF | Triangle104 | 2025-05-01T11:20:56Z | 0 | 0 | transformers | [
"transformers",
"gguf",
"llama-cpp",
"gguf-my-repo",
"base_model:mlabonne/Qwen3-0.6B-abliterated",
"base_model:quantized:mlabonne/Qwen3-0.6B-abliterated",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-05-01T11:20:51Z | ---
base_model: mlabonne/Qwen3-0.6B-abliterated
library_name: transformers
tags:
- llama-cpp
- gguf-my-repo
---
# Triangle104/Qwen3-0.6B-abliterated-Q4_K_S-GGUF
This model was converted to GGUF format from [`mlabonne/Qwen3-0.6B-abliterated`](https://huggingface.co/mlabonne/Qwen3-0.6B-abliterated) 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/mlabonne/Qwen3-0.6B-abliterated) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo Triangle104/Qwen3-0.6B-abliterated-Q4_K_S-GGUF --hf-file qwen3-0.6b-abliterated-q4_k_s.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo Triangle104/Qwen3-0.6B-abliterated-Q4_K_S-GGUF --hf-file qwen3-0.6b-abliterated-q4_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.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo Triangle104/Qwen3-0.6B-abliterated-Q4_K_S-GGUF --hf-file qwen3-0.6b-abliterated-q4_k_s.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo Triangle104/Qwen3-0.6B-abliterated-Q4_K_S-GGUF --hf-file qwen3-0.6b-abliterated-q4_k_s.gguf -c 2048
```
|
mlfoundations-dev/d1_code_multiple_languages | mlfoundations-dev | 2025-05-01T11:19:52Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"llama-factory",
"full",
"generated_from_trainer",
"conversational",
"base_model:Qwen/Qwen2.5-7B-Instruct",
"base_model:finetune:Qwen/Qwen2.5-7B-Instruct",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-05-01T03:01:20Z | ---
library_name: transformers
license: apache-2.0
base_model: Qwen/Qwen2.5-7B-Instruct
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: d1_code_multiple_languages
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. -->
# d1_code_multiple_languages
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/d1_code_multiple_languages 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: 4e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 32
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- total_eval_batch_size: 256
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5.0
### Training results
### Framework versions
- Transformers 4.46.1
- Pytorch 2.5.1
- Datasets 3.1.0
- Tokenizers 0.20.3
|
Triangle104/Rombo-LLM-V3.1-QWQ-32b-Q8_0-GGUF | Triangle104 | 2025-05-01T11:19:50Z | 0 | 0 | null | [
"gguf",
"llama-cpp",
"gguf-my-repo",
"base_model:Rombo-Org/Rombo-LLM-V3.1-QWQ-32b",
"base_model:quantized:Rombo-Org/Rombo-LLM-V3.1-QWQ-32b",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-05-01T11:15:42Z | ---
base_model: Rombo-Org/Rombo-LLM-V3.1-QWQ-32b
license: apache-2.0
tags:
- llama-cpp
- gguf-my-repo
---
# Triangle104/Rombo-LLM-V3.1-QWQ-32b-Q8_0-GGUF
This model was converted to GGUF format from [`Rombo-Org/Rombo-LLM-V3.1-QWQ-32b`](https://huggingface.co/Rombo-Org/Rombo-LLM-V3.1-QWQ-32b) 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/Rombo-Org/Rombo-LLM-V3.1-QWQ-32b) for more details on the model.
---
Rombo-LLM-V3.1-QWQ-32b is a Continued Finetune model (Merge only) of (Qwen/QwQ-32B) and its base model (Qwen/Qwen2.5-32B). This merge is done to decrease catastrophic forgetting during finetuning, and increase overall performance of the model. The tokenizers are taken from the QwQ-32B for thinking capabilities.
---
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo Triangle104/Rombo-LLM-V3.1-QWQ-32b-Q8_0-GGUF --hf-file rombo-llm-v3.1-qwq-32b-q8_0.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo Triangle104/Rombo-LLM-V3.1-QWQ-32b-Q8_0-GGUF --hf-file rombo-llm-v3.1-qwq-32b-q8_0.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo Triangle104/Rombo-LLM-V3.1-QWQ-32b-Q8_0-GGUF --hf-file rombo-llm-v3.1-qwq-32b-q8_0.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo Triangle104/Rombo-LLM-V3.1-QWQ-32b-Q8_0-GGUF --hf-file rombo-llm-v3.1-qwq-32b-q8_0.gguf -c 2048
```
|
TentenPolllo/fruitripeness | TentenPolllo | 2025-05-01T11:19:33Z | 0 | 0 | null | [
"license:apache-2.0",
"region:us"
] | null | 2025-05-01T11:17:54Z | ---
license: apache-2.0
---
|
Subh775/hinglish-finetuned-demo | Subh775 | 2025-05-01T11:19:12Z | 0 | 0 | adapter-transformers | [
"adapter-transformers",
"safetensors",
"hinglish",
"lora",
"conversational",
"text-generation",
"hi",
"en",
"dataset:one-thing/chatbot_arena_conversations_hinglish",
"base_model:facebook/opt-350m",
"base_model:adapter:facebook/opt-350m",
"license:apache-2.0",
"region:us"
] | text-generation | 2025-04-20T19:21:55Z | ---
language:
- hi
- en
tags:
- hinglish
- lora
- conversational
license: apache-2.0
datasets:
- one-thing/chatbot_arena_conversations_hinglish
base_model:
- facebook/opt-350m
pipeline_tag: text-generation
new_version: Subh775/hinglish-finetuned-V2
library_name: adapter-transformers
---
# Hinglish Fine-tuned Conversational Model
This model is fine-tuned on Hinglish conversation data using LoRA adapters. It's designed to respond to queries in Hinglish (a mix of Hindi and English).
## Model Details
- Base model: facebook/opt-350m
- Fine-tuning: LoRA adapters
- Training dataset: one-thing/chatbot_arena_conversations_hinglish
- Language: Hinglish (Hindi-English code-mixed)
## Usage
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel, PeftConfig
# Load configuration
config = PeftConfig.from_pretrained("Subh775/hinglish-finetuned-demo")
# Load base model
base_model = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path)
tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
# Load LoRA model
model = PeftModel.from_pretrained(base_model, "Subh775/hinglish-finetuned-demo")
# Prepare input
prompt = "Human: Explain what is an Artificial Neural Network?\nAssistant:"
inputs = tokenizer(prompt, return_tensors="pt")
# Try with modified generation parameters
outputs = model.generate(
**inputs,
max_length=100,
min_new_tokens=10, # Force generating at least some new tokens
temperature=0.86, # Add some randomness
top_p=0.9,
no_repeat_ngram_size=3, # Avoid repeating trigrams
repetition_penalty=1.5, # Penalize repetition more heavily
do_sample=True # Use sampling instead of greedy decoding
)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```
## Limitations
- The model is fine-tuned on a specific dataset and may not generalize to all Hinglish dialects or topics.
- It works best for conversational queries similar to those in the training data.
""" |
Docty/dreambooth-chipped-coating-lora | Docty | 2025-05-01T11:18:43Z | 0 | 0 | diffusers | [
"diffusers",
"tensorboard",
"text-to-image",
"lora",
"diffusers-training",
"stable-diffusion",
"stable-diffusion-diffusers",
"base_model:stable-diffusion-v1-5/stable-diffusion-v1-5",
"base_model:adapter:stable-diffusion-v1-5/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"region:us"
] | text-to-image | 2025-05-01T10:25:27Z | ---
base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
library_name: diffusers
license: creativeml-openrail-m
inference: true
instance_prompt: Create an object container whose entire surface is coated with a
color but a has a rough wear off coating, tear off coating or chipped off coating
or peeled off coating exposing the bare uncovered metallic uncoated, sksks chip
peeling, rough texture, rusted or corroded surfaces, and signs of heavy wear, realistic
light to show the corroded surface, cinematic view, realistic
tags:
- text-to-image
- diffusers
- lora
- diffusers-training
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
- diffusers-training
- stable-diffusion
- stable-diffusion-diffusers
---
<!-- This model card has been generated automatically according to the information the training script had access to. You
should probably proofread and complete it, then remove this comment. -->
# LoRA DreamBooth - Docty/dreambooth-chipped-coating-lora
These are LoRA adaption weights for stable-diffusion-v1-5/stable-diffusion-v1-5. The weights were trained on Create an object container whose entire surface is coated with a color but a has a rough wear off coating, tear off coating or chipped off coating or peeled off coating exposing the bare uncovered metallic uncoated, sksks chip peeling, rough texture, rusted or corroded surfaces, and signs of heavy wear, realistic light to show the corroded surface, cinematic view, realistic using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.
LoRA for the text encoder was enabled: False.
## Intended uses & limitations
#### How to use
```python
# TODO: add an example code snippet for running this diffusion pipeline
```
#### Limitations and bias
[TODO: provide examples of latent issues and potential remediations]
## Training details
[TODO: describe the data used to train the model] |
JQ1984/legalbert_gdpr_pretrained | JQ1984 | 2025-05-01T11:18:27Z | 0 | 0 | null | [
"safetensors",
"bert",
"legal",
"question-answering",
"en",
"dataset:JQ1984/GDPRcasedata",
"base_model:nlpaueb/legal-bert-base-uncased",
"base_model:finetune:nlpaueb/legal-bert-base-uncased",
"license:cc-by-nc-4.0",
"region:us"
] | question-answering | 2025-05-01T11:07:26Z | ---
license: cc-by-nc-4.0
language:
- en
base_model:
- nlpaueb/legal-bert-base-uncased
tags:
- legal
datasets:
- JQ1984/GDPRcasedata
metrics:
- accuracy
pipeline_tag: question-answering
---
# Legal-BERT (GDPR Pretrained Version)
This model is based on [`nlpaueb/legal-bert-base-uncased`](https://huggingface.co/nlpaueb/legal-bert-base-uncased), and has been further pretrained on the full text of the [General Data Protection Regulation (GDPR)](https://eur-lex.europa.eu/eli/reg/2016/679/oj) to adapt it to privacy law and regulatory compliance scenarios.
## 🧠 What’s New?
We adapted Legal-BERT through masked language modeling (MLM) on GDPR-specific language, enhancing the model’s understanding of:
- Personal data protection terms
- GDPR article structure
- Typical compliance language and risk descriptions
The training corpus includes official GDPR text, split into clean English sentences, formatted for MLM.
## 🔧 Intended Use
This specialized model is best suited for:
- GDPR compliance assistance
- Legal document classification and clause matching
- Privacy policy analysis
- Regulatory question answering (when further fine-tuned)
## 💾 Training Details
- **Base model**: `nlpaueb/legal-bert-base-uncased`
- **Task**: Masked Language Modeling (MLM)
- **Corpus**: Full official GDPR English text (~10,000+ sentences)
- **Epochs**: 3
- **Block size**: 128
- **Batch size**: 16
- **MLM Probability**: 15%
## 🛠 How to Use
```python
from transformers import AutoTokenizer, AutoModelForMaskedLM
tokenizer = AutoTokenizer.from_pretrained("JQ1984/legalbert_gdpr_pretrained")
model = AutoModelForMaskedLM.from_pretrained("JQ1984/legalbert_gdpr_pretrained")
# Example
inputs = tokenizer("The data controller shall ensure that personal data is", return_tensors="pt")
outputs = model(**inputs)
## References
* [Model Paper](https://arxiv.org/abs/xxxx.xxxxx) |
aXsalll/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-sizable_prowling_cockroach | aXsalll | 2025-05-01T11:15:46Z | 1 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"generated_from_trainer",
"rl-swarm",
"grpo",
"gensyn",
"I am sizable prowling cockroach",
"unsloth",
"trl",
"conversational",
"arxiv:2402.03300",
"base_model:Gensyn/Qwen2.5-0.5B-Instruct",
"base_model:finetune:Gensyn/Qwen2.5-0.5B-Instruct",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-04-25T20:17:27Z | ---
base_model: Gensyn/Qwen2.5-0.5B-Instruct
library_name: transformers
model_name: Qwen2.5-0.5B-Instruct-Gensyn-Swarm-sizable_prowling_cockroach
tags:
- generated_from_trainer
- rl-swarm
- grpo
- gensyn
- I am sizable prowling cockroach
- unsloth
- trl
licence: license
---
# Model Card for Qwen2.5-0.5B-Instruct-Gensyn-Swarm-sizable_prowling_cockroach
This model is a fine-tuned version of [Gensyn/Qwen2.5-0.5B-Instruct](https://huggingface.co/Gensyn/Qwen2.5-0.5B-Instruct).
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="aXsalll/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-sizable_prowling_cockroach", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
### Framework versions
- TRL: 0.15.2
- Transformers: 4.51.3
- Pytorch: 2.6.0
- Datasets: 3.5.0
- Tokenizers: 0.21.1
## Citations
Cite GRPO as:
```bibtex
@article{zhihong2024deepseekmath,
title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
year = 2024,
eprint = {arXiv:2402.03300},
}
```
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
``` |
aleegis/f0ed9dca-a916-4441-8ccb-323e6d4826af | aleegis | 2025-05-01T11:12:54Z | 0 | 0 | peft | [
"peft",
"safetensors",
"llama",
"axolotl",
"generated_from_trainer",
"base_model:codellama/CodeLlama-7b-hf",
"base_model:adapter:codellama/CodeLlama-7b-hf",
"license:llama2",
"region:us"
] | null | 2025-05-01T09:57:46Z | ---
library_name: peft
license: llama2
base_model: codellama/CodeLlama-7b-hf
tags:
- axolotl
- generated_from_trainer
model-index:
- name: f0ed9dca-a916-4441-8ccb-323e6d4826af
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/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
<details><summary>See axolotl config</summary>
axolotl version: `0.4.1`
```yaml
adapter: lora
base_model: codellama/CodeLlama-7b-hf
bf16: auto
chat_template: llama3
dataloader_num_workers: 12
dataset_prepared_path: null
datasets:
- data_files:
- a304f7b9d5e4a239_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/a304f7b9d5e4a239_train_data.json
type:
field_instruction: task
field_output: chosen
format: '{instruction}'
no_input_format: '{instruction}'
system_format: '{system}'
system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_steps: null
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 8
gradient_checkpointing: false
group_by_length: false
hub_model_id: aleegis/f0ed9dca-a916-4441-8ccb-323e6d4826af
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: null
lora_alpha: 32
lora_dropout: 0.15
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
loraplus_lr_embedding: 1.0e-06
loraplus_lr_ratio: 16
lr_scheduler: cosine
max_grad_norm: 1
max_steps: 1500
micro_batch_size: 2
mlflow_experiment_name: /tmp/a304f7b9d5e4a239_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 200
optimizer: adamw_torch_fused
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: null
save_total_limit: 10
saves_per_epoch: 0
sequence_len: 1024
special_tokens:
pad_token: </s>
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.0
wandb_entity: null
wandb_mode: online
wandb_name: e1b36927-fa78-414d-a25b-1043f85c3145
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: e1b36927-fa78-414d-a25b-1043f85c3145
warmup_steps: 100
weight_decay: 0
xformers_attention: null
```
</details><br>
# f0ed9dca-a916-4441-8ccb-323e6d4826af
This model is a fine-tuned version of [codellama/CodeLlama-7b-hf](https://huggingface.co/codellama/CodeLlama-7b-hf) 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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- training_steps: 1500
### Training results
### Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1 |
ShabanEjupi/Chatbot-i | ShabanEjupi | 2025-05-01T11:11:05Z | 3 | 0 | null | [
"safetensors",
"t5",
"region:us"
] | null | 2025-02-14T22:17:34Z | ---
title: Chatbot-i
emoji: 🤖
colorFrom: blue
colorTo: purple
sdk: gradio
sdk_version: 5.16.0
app_file: app.py
pinned: false
---
## Requirements
- Python 3.8+
- See [requirements.txt](./requirements.txt) |
Siddharth63/Qwen3-4B-Base-4bit-Autoround-sym | Siddharth63 | 2025-05-01T11:09:50Z | 0 | 0 | null | [
"safetensors",
"qwen3",
"license:apache-2.0",
"4-bit",
"auto-round",
"region:us"
] | null | 2025-05-01T09:03:00Z | ---
license: apache-2.0
---
```
!pip install --upgrade auto-round transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
from auto_round import AutoRoundConfig ## must import for auto-round format
quantized_model_path = "Siddharth63/Qwen3-4B-Base-4bit-Autoround-sym"
quantization_config = AutoRoundConfig(backend="auto")
model = AutoModelForCausalLM.from_pretrained(quantized_model_path, device_map="auto",
torch_dtype=torch.float16,
quantization_config=quantization_config)
tokenizer = AutoTokenizer.from_pretrained(quantized_model_path)
text = "Atherosclerosis"
inputs = tokenizer(text, return_tensors="pt").to(model.device)
print(tokenizer.decode(model.generate(**inputs, max_new_tokens=50)[0]))
``` |
Kevinjacques/Software | Kevinjacques | 2025-05-01T11:08:36Z | 0 | 0 | null | [
"license:apache-2.0",
"region:us"
] | null | 2025-05-01T11:08:28Z | ---
license: apache-2.0
---
|
deswaq/juh99 | deswaq | 2025-05-01T11:08:14Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-05-01T11:05:11Z | ---
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] |
ttn1410/ScoreIndicators | ttn1410 | 2025-05-01T11:08:06Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"distilbert",
"text-classification",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2025-05-01T11:07:54Z | ---
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] |
hanshan1988/unsloth-Qwen2.5-7B-banks-review-gguf | hanshan1988 | 2025-05-01T11:07:30Z | 13 | 0 | null | [
"gguf",
"text-generation",
"en",
"dataset:TrainingDataPro/customers-reviews-on-banks",
"base_model:unsloth/Qwen2.5-7B",
"base_model:quantized:unsloth/Qwen2.5-7B",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-03-17T01:48:36Z | ---
license: apache-2.0
datasets:
- TrainingDataPro/customers-reviews-on-banks
language:
- en
base_model:
- unsloth/Qwen2.5-7B
pipeline_tag: text-generation
---
## Base Model
Unsloth implementation of Qwen2.5-7B: [unsloth/Qwen2.5-7B](https://huggingface.co/unsloth/Qwen2.5-7B)
## Finetune Method
Supervised fine tuning (SFT)
## Prompt Template
```
prompt_tmpl = """Below is a customer comment relating to their banking experience. \
Please output the banking aspects and their related sentiments expressed by the customer. \
Banking aspects must be short nouns or noun-phrases containing no more than 2 words that appear in the comment. \
Sentiments must be either positive, negative or neutral.
Output must follow the following format with NO explanations:
(credit card, positive)
(long queue, negative)
(app experience, neutral)
### Comment:
{comment}
### Response:
"""
``` |
samlucas/smolvlm_500m-parking_occupancy-PKLot-instruct-with-context-with-expert | samlucas | 2025-05-01T10:58:20Z | 0 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"arxiv:1910.09700",
"base_model:HuggingFaceTB/SmolVLM-500M-Instruct",
"base_model:adapter:HuggingFaceTB/SmolVLM-500M-Instruct",
"region:us"
] | null | 2025-05-01T10:58:12Z | ---
base_model: HuggingFaceTB/SmolVLM-500M-Instruct
library_name: peft
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.15.2 |
Triangle104/Rombo-LLM-V3.1-QWQ-32b-Q5_K_M-GGUF | Triangle104 | 2025-05-01T10:56:13Z | 0 | 0 | null | [
"gguf",
"llama-cpp",
"gguf-my-repo",
"base_model:Rombo-Org/Rombo-LLM-V3.1-QWQ-32b",
"base_model:quantized:Rombo-Org/Rombo-LLM-V3.1-QWQ-32b",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-05-01T10:53:31Z | ---
base_model: Rombo-Org/Rombo-LLM-V3.1-QWQ-32b
license: apache-2.0
tags:
- llama-cpp
- gguf-my-repo
---
# Triangle104/Rombo-LLM-V3.1-QWQ-32b-Q5_K_M-GGUF
This model was converted to GGUF format from [`Rombo-Org/Rombo-LLM-V3.1-QWQ-32b`](https://huggingface.co/Rombo-Org/Rombo-LLM-V3.1-QWQ-32b) 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/Rombo-Org/Rombo-LLM-V3.1-QWQ-32b) for more details on the model.
---
Rombo-LLM-V3.1-QWQ-32b is a Continued Finetune model (Merge only) of (Qwen/QwQ-32B) and its base model (Qwen/Qwen2.5-32B). This merge is done to decrease catastrophic forgetting during finetuning, and increase overall performance of the model. The tokenizers are taken from the QwQ-32B for thinking capabilities.
---
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo Triangle104/Rombo-LLM-V3.1-QWQ-32b-Q5_K_M-GGUF --hf-file rombo-llm-v3.1-qwq-32b-q5_k_m.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo Triangle104/Rombo-LLM-V3.1-QWQ-32b-Q5_K_M-GGUF --hf-file rombo-llm-v3.1-qwq-32b-q5_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.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo Triangle104/Rombo-LLM-V3.1-QWQ-32b-Q5_K_M-GGUF --hf-file rombo-llm-v3.1-qwq-32b-q5_k_m.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo Triangle104/Rombo-LLM-V3.1-QWQ-32b-Q5_K_M-GGUF --hf-file rombo-llm-v3.1-qwq-32b-q5_k_m.gguf -c 2048
```
|
Lucy-in-the-Sky/helium-1-2b-science-Q8_0-GGUF | Lucy-in-the-Sky | 2025-05-01T10:56:07Z | 0 | 0 | transformers | [
"transformers",
"gguf",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"bg",
"cs",
"da",
"de",
"el",
"en",
"es",
"et",
"fi",
"fr",
"ga",
"hr",
"hu",
"it",
"lt",
"lv",
"mt",
"nl",
"pl",
"pt",
"ro",
"sk",
"sl",
"sv",
"base_model:kyutai/helium-1-2b-science",
"base_model:quantized:kyutai/helium-1-2b-science",
"license:cc-by-sa-4.0",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-05-01T10:55:52Z | ---
base_model: kyutai/helium-1-2b-science
language:
- bg
- cs
- da
- de
- el
- en
- es
- et
- fi
- fr
- ga
- hr
- hu
- it
- lt
- lv
- mt
- nl
- pl
- pt
- ro
- sk
- sl
- sv
library_name: transformers
license: cc-by-sa-4.0
pipeline_tag: text-generation
tags:
- llama-cpp
- gguf-my-repo
---
# Lucy-in-the-Sky/helium-1-2b-science-Q8_0-GGUF
This model was converted to GGUF format from [`kyutai/helium-1-2b-science`](https://huggingface.co/kyutai/helium-1-2b-science) 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/kyutai/helium-1-2b-science) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo Lucy-in-the-Sky/helium-1-2b-science-Q8_0-GGUF --hf-file helium-1-2b-science-q8_0.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo Lucy-in-the-Sky/helium-1-2b-science-Q8_0-GGUF --hf-file helium-1-2b-science-q8_0.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo Lucy-in-the-Sky/helium-1-2b-science-Q8_0-GGUF --hf-file helium-1-2b-science-q8_0.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo Lucy-in-the-Sky/helium-1-2b-science-Q8_0-GGUF --hf-file helium-1-2b-science-q8_0.gguf -c 2048
```
|
samlucas/smolvlm_500m-parking_occupancy-PKLot-instruct-without-context-without-expert | samlucas | 2025-05-01T10:53:29Z | 0 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"arxiv:1910.09700",
"base_model:HuggingFaceTB/SmolVLM-500M-Instruct",
"base_model:adapter:HuggingFaceTB/SmolVLM-500M-Instruct",
"region:us"
] | null | 2025-05-01T10:53:19Z | ---
base_model: HuggingFaceTB/SmolVLM-500M-Instruct
library_name: peft
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.15.2 |
dulig1902/bert-en-vi | dulig1902 | 2025-05-01T10:53:03Z | 0 | 0 | null | [
"safetensors",
"bert",
"en",
"vi",
"dataset:ncduy/mt-en-vi",
"base_model:google-bert/bert-base-uncased",
"base_model:finetune:google-bert/bert-base-uncased",
"license:apache-2.0",
"region:us"
] | null | 2025-05-01T10:47:11Z | ---
license: apache-2.0
datasets:
- ncduy/mt-en-vi
language:
- en
- vi
base_model:
- google-bert/bert-base-uncased
--- |
udayp/whisper-quillr-0428-combined | udayp | 2025-05-01T10:52:16Z | 0 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"whisper",
"automatic-speech-recognition",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | automatic-speech-recognition | 2025-04-28T22:01:28Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
upvantage/base-mistral-hz-7b | upvantage | 2025-05-01T10:50:37Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"en",
"base_model:unsloth/mistral-7b-v0.3",
"base_model:finetune:unsloth/mistral-7b-v0.3",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-05-01T10:49:22Z | ---
base_model: unsloth/mistral-7b-v0.3
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** upvantage
- **License:** apache-2.0
- **Finetuned from model :** unsloth/mistral-7b-v0.3
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)
|
OmBhandwalkar/distilbert-base-uncased-finetuned-ner | OmBhandwalkar | 2025-05-01T10:50:34Z | 0 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"distilbert",
"token-classification",
"generated_from_trainer",
"dataset:conll2003",
"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"
] | token-classification | 2025-05-01T10:45:00Z | ---
library_name: transformers
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: distilbert-base-uncased-finetuned-ner
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: conll2003
type: conll2003
config: conll2003
split: validation
args: conll2003
metrics:
- name: Precision
type: precision
value: 0.9263390392048592
- name: Recall
type: recall
value: 0.9383599955252265
- name: F1
type: f1
value: 0.9323107702567521
- name: Accuracy
type: accuracy
value: 0.9837800054013695
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilbert-base-uncased-finetuned-ner
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the conll2003 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0609
- Precision: 0.9263
- Recall: 0.9384
- F1: 0.9323
- Accuracy: 0.9838
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.2437 | 1.0 | 878 | 0.0721 | 0.9001 | 0.9217 | 0.9108 | 0.9797 |
| 0.0524 | 2.0 | 1756 | 0.0608 | 0.9211 | 0.9355 | 0.9282 | 0.9832 |
| 0.0305 | 3.0 | 2634 | 0.0609 | 0.9263 | 0.9384 | 0.9323 | 0.9838 |
### Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.1
- Tokenizers 0.21.1
|
lixiaoxi45/WebThinker-R1-32B | lixiaoxi45 | 2025-05-01T10:46:32Z | 0 | 0 | null | [
"safetensors",
"qwen2",
"arxiv:2504.21776",
"license:apache-2.0",
"region:us"
] | null | 2025-05-01T02:01:10Z | ---
license: apache-2.0
---
# 🌐 WebThinker-R1-32B
<div align="left" style="line-height: 1;">
<a href="https://github.com/RUC-NLPIR/WebThinker" target="_blank" style="margin: 2px;">
<img alt="GitHub" src="https://img.shields.io/badge/GitHub-WebThinker-blue?logo=github" style="display: inline-block; vertical-align: middle;"/>
</a>
<a href="https://arxiv.org/abs/2504.21776" target="_blank" style="margin: 2px;">
<img alt="Paper" src="https://img.shields.io/badge/Paper-arXiv-b5212f.svg?logo=arxiv" style="display: inline-block; vertical-align: middle;"/>
</a>
<a href="https://huggingface.co/papers/2504.21776" target="_blank" style="margin: 2px;">
<img alt="Paper" src="https://img.shields.io/badge/Paper-Hugging%20Face-yellow?logo=huggingface" style="display: inline-block; vertical-align: middle;"/>
</a>
<a href="https://opensource.org/licenses/Apache-2.0" target="_blank" style="margin: 2px;">
<img alt="License" src="https://img.shields.io/badge/LICENSE-Apache_2.0-green.svg" style="display: inline-block; vertical-align: middle;"/>
</a>
</div>
## Overview
WebThinker-R1-32B is part of the WebThinker series that enables large reasoning models to autonomously search, explore web pages, and draft research reports within their thinking process. This 32B parameter model provides deep research capabilities through:
- **Deep Web Exploration**: Enables autonomous web searches and page navigation by clicking interactive elements to extract relevant information while maintaining reasoning coherence
- **Autonomous Think-Search-and-Draft**: Integrates real-time knowledge seeking with report generation, allowing the model to draft sections as information is gathered
- **RL-based Training**: Leverages iterative online DPO training with preference pairs constructed from reasoning trajectories to optimize end-to-end performance
## Related Models
- [WebThinker-QwQ-32B](https://huggingface.co/lixiaoxi45/WebThinker-QwQ-32B)
- [WebThinker-R1-7B](https://huggingface.co/lixiaoxi45/WebThinker-R1-7B)
- [WebThinker-R1-14B](https://huggingface.co/lixiaoxi45/WebThinker-R1-14B)
- [WebThinker-R1-32B](https://huggingface.co/lixiaoxi45/WebThinker-R1-32B) (this model)
## Usage
This model can be used for:
- Complex problem solving requiring external knowledge
- Scientific research report generation
- Open-ended reasoning tasks
## Citation
```bibtex
@article{Li2025WebThinker,
author = {Xiaoxi Li and
Jiajie Jin and
Guanting Dong and
Hongjin Qian and
Yutao Zhu and
Yongkang Wu and
Ji{-}Rong Wen and
Zhicheng Dou},
title = {WebThinker: Empowering Large Reasoning Models with Deep Research Capability},
journal = {CoRR},
volume = {abs/2504.21776},
year = {2025},
url = {https://arxiv.org/abs/2504.21776},
doi = {10.48550/ARXIV.2504.21776},
eprinttype = {arXiv},
eprint = {2504.21776}
}
```
## License
This model is released under the Apache License 2.0.
## Contact
For any questions or feedback, please reach out to us at [[email protected]](mailto:[email protected]).
|
fhaslam/Llama-3.2-1B-Financial-Sentiment40 | fhaslam | 2025-05-01T10:45:05Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"facebook",
"meta",
"pytorch",
"llama",
"llama-3",
"text-generation",
"conversational",
"en",
"de",
"fr",
"it",
"pt",
"hi",
"es",
"th",
"arxiv:2204.05149",
"arxiv:2405.16406",
"license:llama3.2",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-05-01T10:44:58Z | ---
language:
- en
- de
- fr
- it
- pt
- hi
- es
- th
library_name: transformers
pipeline_tag: text-generation
tags:
- facebook
- meta
- pytorch
- llama
- llama-3
license: llama3.2
extra_gated_prompt: >-
### LLAMA 3.2 COMMUNITY LICENSE AGREEMENT
Llama 3.2 Version Release Date: September 25, 2024
“Agreement” means the terms and conditions for use, reproduction, distribution
and modification of the Llama Materials set forth herein.
“Documentation” means the specifications, manuals and documentation accompanying Llama 3.2
distributed by Meta at https://llama.meta.com/doc/overview.
“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.
“Llama 3.2” 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://www.llama.com/llama-downloads.
“Llama Materials” means, collectively, Meta’s proprietary Llama 3.2 and Documentation (and
any portion thereof) made available under this Agreement.
“Meta” or “we” means Meta Platforms Ireland Limited (if you are located in or,
if you are an entity, your principal place of business is in the EEA or Switzerland)
and Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).
By clicking “I Accept” below or by using or distributing any portion or element of the Llama Materials,
you agree to be bound by this Agreement.
1. License Rights and Redistribution.
a. Grant of Rights. You are granted a non-exclusive, worldwide,
non-transferable and royalty-free limited license under Meta’s intellectual property or other rights
owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy, create derivative works
of, and make modifications to the Llama Materials.
b. Redistribution and Use.
i. If you distribute or make available the Llama Materials (or any derivative works thereof),
or a product or service (including another AI model) that contains any of them, you shall (A) provide
a copy of this Agreement with any such Llama Materials; and (B) prominently display “Built with Llama”
on a related website, user interface, blogpost, about page, or product documentation. If you use the
Llama Materials or any outputs or results of 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”
at the beginning of any such AI model name.
ii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part
of an integrated end user product, then Section 2 of this Agreement will not apply to you.
iii. You must retain in all copies of the Llama Materials that you distribute the
following attribution notice within a “Notice” text file distributed as a part of such copies:
“Llama 3.2 is licensed under the Llama 3.2 Community License, Copyright © Meta Platforms,
Inc. All Rights Reserved.”
iv. Your use of the Llama Materials must comply with applicable laws and regulations
(including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for
the Llama Materials (available at https://www.llama.com/llama3_2/use-policy), which is hereby
incorporated by reference into this Agreement.
2. Additional Commercial Terms. If, on the Llama 3.2 version release date, the monthly active users
of the products or services made available by or for Licensee, or Licensee’s affiliates,
is greater than 700 million monthly active users in the preceding calendar month, you must request
a license from Meta, which Meta may grant to you in its sole discretion, and you are not authorized to
exercise any of the rights under this Agreement unless or until Meta otherwise expressly grants you such rights.
3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND
RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS
ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES
OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE
FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED
WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.
4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY,
WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT,
FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN
IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.
5. Intellectual Property.
a. No trademark licenses are granted under this Agreement, and in connection with the Llama Materials,
neither Meta nor Licensee may use any name or mark owned by or associated with the other or any of its affiliates,
except as required for reasonable and customary use in describing and redistributing the Llama Materials or as
set forth in this Section 5(a). Meta hereby grants you a license to use “Llama” (the “Mark”) solely as required
to comply with the last sentence of Section 1.b.i. You will comply with Meta’s brand guidelines (currently accessible
at https://about.meta.com/brand/resources/meta/company-brand/). All goodwill arising out of your use of the Mark
will inure to the benefit of Meta.
b. Subject to Meta’s ownership of Llama Materials and derivatives made by or for Meta, with respect to any
derivative works and modifications of the Llama Materials that are made by you, as between you and Meta,
you are and will be the owner of such derivative works and modifications.
c. If you institute litigation or other proceedings against Meta or any entity (including a cross-claim or
counterclaim in a lawsuit) alleging that the Llama Materials or Llama 3.2 outputs or results, or any portion
of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable
by you, then any licenses granted to you under this Agreement shall terminate as of the date such litigation or
claim is filed or instituted. You will indemnify and hold harmless Meta from and against any claim by any third
party arising out of or related to your use or distribution of the Llama Materials.
6. Term and Termination. The term of this Agreement will commence upon your acceptance of this Agreement or access
to the Llama Materials and will continue in full force and effect until terminated in accordance with the terms
and conditions herein. Meta may terminate this Agreement if you are in breach of any term or condition of this
Agreement. Upon termination of this Agreement, you shall delete and cease use of the Llama Materials. Sections 3,
4 and 7 shall survive the termination of this Agreement.
7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of the State of
California without regard to choice of law principles, and the UN Convention on Contracts for the International
Sale of Goods does not apply to this Agreement. The courts of California shall have exclusive jurisdiction of
any dispute arising out of this Agreement.
### Llama 3.2 Acceptable Use Policy
Meta is committed to promoting safe and fair use of its tools and features, including Llama 3.2.
If you access or use Llama 3.2, you agree to this Acceptable Use Policy (“**Policy**”).
The most recent copy of this policy can be found at
[https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).
#### Prohibited Uses
We want everyone to use Llama 3.2 safely and responsibly. You agree you will not use, or allow others to use, Llama 3.2 to:
1. Violate the law or others’ rights, including to:
1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as:
1. Violence or terrorism
2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material
3. Human trafficking, exploitation, and sexual violence
4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.
5. Sexual solicitation
6. Any other criminal activity
1. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals
2. 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
3. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices
4. Collect, process, disclose, generate, or infer private or sensitive information about individuals, including information about individuals’ identity, health, or demographic information, unless you have obtained the right to do so in accordance with applicable law
5. 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
6. 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
7. Engage in any action, or facilitate any action, to intentionally circumvent or remove usage restrictions or other safety measures, or to enable functionality disabled by Meta
2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Llama 3.2 related to the following:
8. 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 or to the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons Convention Implementation Act of 1997
9. Guns and illegal weapons (including weapon development)
10. Illegal drugs and regulated/controlled substances
11. Operation of critical infrastructure, transportation technologies, or heavy machinery
12. Self-harm or harm to others, including suicide, cutting, and eating disorders
13. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual
3. Intentionally deceive or mislead others, including use of Llama 3.2 related to the following:
14. Generating, promoting, or furthering fraud or the creation or promotion of disinformation
15. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content
16. Generating, promoting, or further distributing spam
17. Impersonating another individual without consent, authorization, or legal right
18. Representing that the use of Llama 3.2 or outputs are human-generated
19. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement
4. Fail to appropriately disclose to end users any known dangers of your AI system
5. Interact with third party tools, models, or software designed to generate unlawful content or engage in unlawful or harmful conduct and/or represent that the outputs of such tools, models, or software are associated with Meta or Llama 3.2
With respect to any multimodal models included in Llama 3.2, the rights granted under Section 1(a) of the Llama 3.2 Community License Agreement are not being granted to you if you are an individual domiciled in, or a company with a principal place of business in, the European Union. This restriction does not apply to end users of a product or service that incorporates any such multimodal models.
Please report any violation of this Policy, software “bug,” or other problems that could lead to a violation of this Policy through one of the following means:
* Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues&h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)
* Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)
* Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)
* Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama 3.2: [email protected]
extra_gated_fields:
First Name: text
Last Name: text
Date of birth: date_picker
Country: country
Affiliation: text
Job title:
type: select
options:
- Student
- Research Graduate
- AI researcher
- AI developer/engineer
- Reporter
- Other
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
---
## Model Information
The Llama 3.2 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction-tuned generative models in 1B and 3B sizes (text in/text out). The Llama 3.2 instruction-tuned text only models are optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks. They outperform many of the available open source and closed chat models on common industry benchmarks.
**Model Developer:** Meta
**Model Architecture:** Llama 3.2 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.
| | Training Data | Params | Input modalities | Output modalities | Context Length | GQA | Shared Embeddings | Token count | Knowledge cutoff |
| :---- | :---- | :---- | :---- | :---- | :---- | :---- | :---- | :---- | :---- |
| Llama 3.2 (text only) | A new mix of publicly available online data. | 1B (1.23B) | Multilingual Text | Multilingual Text and code | 128k | Yes | Yes | Up to 9T tokens | December 2023 |
| | | 3B (3.21B) | Multilingual Text | Multilingual Text and code | | | | | |
| Llama 3.2 Quantized (text only) | A new mix of publicly available online data. | 1B (1.23B) | Multilingual Text | Multilingual Text and code | 8k | Yes | Yes | Up to 9T tokens | December 2023 |
| | | 3B (3.21B) | Multilingual Text | Multilingual Text and code | | | | | |
**Supported Languages:** English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai are officially supported. Llama 3.2 has been trained on a broader collection of languages than these 8 supported languages. Developers may fine-tune Llama 3.2 models for languages beyond these supported languages, provided they comply with the Llama 3.2 Community License and the Acceptable Use Policy. Developers are always expected to ensure that their deployments, including those that involve additional languages, are completed safely and responsibly.
**Llama 3.2 Model Family:** Token counts refer to pretraining data only. All model versions use Grouped-Query Attention (GQA) for improved inference scalability.
**Model Release Date:** Sept 25, 2024
**Status:** This is a static model trained on an offline dataset. Future versions may be released that improve model capabilities and safety.
**License:** Use of Llama 3.2 is governed by the [Llama 3.2 Community License](https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/LICENSE) (a custom, commercial license agreement).
**Feedback:** Instructions on how to provide feedback or comments on the model can be found in the Llama Models [README](https://github.com/meta-llama/llama-models/blob/main/README.md). For more technical information about generation parameters and recipes for how to use Llama 3.2 in applications, please go [here](https://github.com/meta-llama/llama-recipes).
## Intended Use
**Intended Use Cases:** Llama 3.2 is intended for commercial and research use in multiple languages. Instruction tuned text only models are intended for assistant-like chat and agentic applications like knowledge retrieval and summarization, mobile AI powered writing assistants and query and prompt rewriting. Pretrained models can be adapted for a variety of additional natural language generation tasks. Similarly, quantized models can be adapted for a variety of on-device use-cases with limited compute resources.
**Out of Scope:** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3.2 Community License. Use in languages beyond those explicitly referenced as supported in this model card.
## How to use
This repository contains two versions of Llama-3.2-1B-Instruct, for use with transformers and with the original `llama` codebase.
### Use with transformers
Starting with `transformers >= 4.43.0` onward, you can run conversational inference using the Transformers `pipeline` abstraction or by leveraging the Auto classes with the `generate()` function.
Make sure to update your transformers installation via `pip install --upgrade transformers`.
```python
import torch
from transformers import pipeline
model_id = "meta-llama/Llama-3.2-1B-Instruct"
pipe = pipeline(
"text-generation",
model=model_id,
torch_dtype=torch.bfloat16,
device_map="auto",
)
messages = [
{"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
{"role": "user", "content": "Who are you?"},
]
outputs = pipe(
messages,
max_new_tokens=256,
)
print(outputs[0]["generated_text"][-1])
```
Note: You can also find detailed recipes on how to use the model locally, with `torch.compile()`, assisted generations, quantised and more at [`huggingface-llama-recipes`](https://github.com/huggingface/huggingface-llama-recipes)
### Use with `llama`
Please, follow the instructions in the [repository](https://github.com/meta-llama/llama)
To download Original checkpoints, see the example command below leveraging `huggingface-cli`:
```
huggingface-cli download meta-llama/Llama-3.2-1B-Instruct --include "original/*" --local-dir Llama-3.2-1B-Instruct
```
## Hardware and Software
**Training Factors:** We used custom training libraries, Meta's custom built GPU cluster, and production infrastructure for pretraining. Fine-tuning, quantization, annotation, and evaluation were also performed on production infrastructure.
**Training Energy Use:** Training utilized a cumulative of **916k** GPU hours of computation on H100-80GB (TDP of 700W) type hardware, per the table below. Training time is the total GPU time required for training each model and power consumption is the peak power capacity per GPU device used, adjusted for power usage efficiency.
**Training Greenhouse Gas Emissions:** Estimated total location-based greenhouse gas emissions were **240** tons CO2eq for training. Since 2020, Meta has maintained net zero greenhouse gas emissions in its global operations and matched 100% of its electricity use with renewable energy; therefore, the total market-based greenhouse gas emissions for training were 0 tons CO2eq.
| | Training Time (GPU hours) | Logit Generation Time (GPU Hours) | Training Power Consumption (W) | Training Location-Based Greenhouse Gas Emissions (tons CO2eq) | Training Market-Based Greenhouse Gas Emissions (tons CO2eq) |
| :---- | :---: | ----- | :---: | :---: | :---: |
| Llama 3.2 1B | 370k | \- | 700 | 107 | 0 |
| Llama 3.2 3B | 460k | \- | 700 | 133 | 0 |
| Llama 3.2 1B SpinQuant | 1.7 | 0 | 700 | *Negligible*\*\* | 0 |
| Llama 3.2 3B SpinQuant | 2.4 | 0 | 700 | *Negligible*\*\* | 0 |
| Llama 3.2 1B QLora | 1.3k | 0 | 700 | 0.381 | 0 |
| Llama 3.2 3B QLora | 1.6k | 0 | 700 | 0.461 | 0 |
| Total | 833k | 86k | | 240 | 0 |
\*\* The location-based CO2e emissions of Llama 3.2 1B SpinQuant and Llama 3.2 3B SpinQuant are less than 0.001 metric tonnes each. This is due to the minimal training GPU hours that are required.
The methodology used to determine training energy use and greenhouse gas emissions can be found [here](https://arxiv.org/pdf/2204.05149). Since Meta is openly releasing these models, the training energy use and greenhouse gas emissions will not be incurred by others.
## Training Data
**Overview:** Llama 3.2 was pretrained on up to 9 trillion tokens of data from publicly available sources. For the 1B and 3B Llama 3.2 models, we incorporated logits from the Llama 3.1 8B and 70B models into the pretraining stage of the model development, where outputs (logits) from these larger models were used as token-level targets. Knowledge distillation was used after pruning to recover performance. In post-training we used a similar recipe as Llama 3.1 and produced final chat models by doing several rounds of alignment on top of the pre-trained model. Each round involved Supervised Fine-Tuning (SFT), Rejection Sampling (RS), and Direct Preference Optimization (DPO).
**Data Freshness:** The pretraining data has a cutoff of December 2023\.
## Quantization
### Quantization Scheme
We designed the current quantization scheme with the [PyTorch’s ExecuTorch](https://github.com/pytorch/executorch) inference framework and Arm CPU backend in mind, taking into account metrics including model quality, prefill/decoding speed, and memory footprint. Our quantization scheme involves three parts:
- All linear layers in all transformer blocks are quantized to a 4-bit groupwise scheme (with a group size of 32) for weights and 8-bit per-token dynamic quantization for activations.
- The classification layer is quantized to 8-bit per-channel for weight and 8-bit per token dynamic quantization for activation.
- Similar to classification layer, an 8-bit per channel quantization is used for embedding layer.
### Quantization-Aware Training and LoRA
The quantization-aware training (QAT) with low-rank adaptation (LoRA) models went through only post-training stages, using the same data as the full precision models. To initialize QAT, we utilize BF16 Llama 3.2 model checkpoints obtained after supervised fine-tuning (SFT) and perform an additional full round of SFT training with QAT. We then freeze the backbone of the QAT model and perform another round of SFT with LoRA adaptors applied to all layers within the transformer block. Meanwhile, the LoRA adaptors' weights and activations are maintained in BF16. Because our approach is similar to QLoRA of Dettmers et al., (2023) (i.e., quantization followed by LoRA adapters), we refer this method as QLoRA. Finally, we fine-tune the resulting model (both backbone and LoRA adaptors) using direct preference optimization (DPO).
### SpinQuant
[SpinQuant](https://arxiv.org/abs/2405.16406) was applied, together with generative post-training quantization (GPTQ). For the SpinQuant rotation matrix fine-tuning, we optimized for 100 iterations, using 800 samples with sequence-length 2048 from the WikiText 2 dataset. For GPTQ, we used 128 samples from the same dataset with the same sequence-length.
## Benchmarks \- English Text
In this section, we report the results for Llama 3.2 models on standard automatic benchmarks. For all these evaluations, we used our internal evaluations library.
### Base Pretrained Models
| Category | Benchmark | \# Shots | Metric | Llama 3.2 1B | Llama 3.2 3B | Llama 3.1 8B |
| ----- | ----- | :---: | :---: | :---: | :---: | :---: |
| General | MMLU | 5 | macro\_avg/acc\_char | 32.2 | 58 | 66.7 |
| | AGIEval English | 3-5 | average/acc\_char | 23.3 | 39.2 | 47.8 |
| | ARC-Challenge | 25 | acc\_char | 32.8 | 69.1 | 79.7 |
| Reading comprehension | SQuAD | 1 | em | 49.2 | 67.7 | 77 |
| | QuAC (F1) | 1 | f1 | 37.9 | 42.9 | 44.9 |
| | DROP (F1) | 3 | f1 | 28.0 | 45.2 | 59.5 |
| Long Context | Needle in Haystack | 0 | em | 96.8 | 1 | 1 |
### Instruction Tuned Models
| Capability | | Benchmark | \# Shots | Metric | Llama 3.2 1B bf16 | Llama 3.2 1B Vanilla PTQ\*\* | Llama 3.2 1B Spin Quant | Llama 3.2 1B QLoRA | Llama 3.2 3B bf16 | Llama 3.2 3B Vanilla PTQ\*\* | Llama 3.2 3B Spin Quant | Llama 3.2 3B QLoRA | Llama 3.1 8B |
| :---: | ----- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
| General | | MMLU | 5 | macro\_avg/acc | 49.3 | 43.3 | 47.3 | 49.0 | 63.4 | 60.5 | 62 | 62.4 | 69.4 |
| Re-writing | | Open-rewrite eval | 0 | micro\_avg/rougeL | 41.6 | 39.2 | 40.9 | 41.2 | 40.1 | 40.3 | 40.8 | 40.7 | 40.9 |
| Summarization | | TLDR9+ (test) | 1 | rougeL | 16.8 | 14.9 | 16.7 | 16.8 | 19.0 | 19.1 | 19.2 | 19.1 | 17.2 |
| Instruction following | | IFEval | 0 | Avg(Prompt/Instruction acc Loose/Strict) | 59.5 | 51.5 | 58.4 | 55.6 | 77.4 | 73.9 | 73.5 | 75.9 | 80.4 |
| Math | | GSM8K (CoT) | 8 | em\_maj1@1 | 44.4 | 33.1 | 40.6 | 46.5 | 77.7 | 72.9 | 75.7 | 77.9 | 84.5 |
| | | MATH (CoT) | 0 | final\_em | 30.6 | 20.5 | 25.3 | 31.0 | 48.0 | 44.2 | 45.3 | 49.2 | 51.9 |
| Reasoning | | ARC-C | 0 | acc | 59.4 | 54.3 | 57 | 60.7 | 78.6 | 75.6 | 77.6 | 77.6 | 83.4 |
| | | GPQA | 0 | acc | 27.2 | 25.9 | 26.3 | 25.9 | 32.8 | 32.8 | 31.7 | 33.9 | 32.8 |
| | | Hellaswag | 0 | acc | 41.2 | 38.1 | 41.3 | 41.5 | 69.8 | 66.3 | 68 | 66.3 | 78.7 |
| Tool Use | | BFCL V2 | 0 | acc | 25.7 | 14.3 | 15.9 | 23.7 | 67.0 | 53.4 | 60.1 | 63.5 | 67.1 |
| | | Nexus | 0 | macro\_avg/acc | 13.5 | 5.2 | 9.6 | 12.5 | 34.3 | 32.4 | 31.5 | 30.1 | 38.5 |
| Long Context | | InfiniteBench/En.QA | 0 | longbook\_qa/f1 | 20.3 | N/A | N/A | N/A | 19.8 | N/A | N/A | N/A | 27.3 |
| | | InfiniteBench/En.MC | 0 | longbook\_choice/acc | 38.0 | N/A | N/A | N/A | 63.3 | N/A | N/A | N/A | 72.2 |
| | | NIH/Multi-needle | 0 | recall | 75.0 | N/A | N/A | N/A | 84.7 | N/A | N/A | N/A | 98.8 |
| Multilingual | | MGSM (CoT) | 0 | em | 24.5 | 13.7 | 18.2 | 24.4 | 58.2 | 48.9 | 54.3 | 56.8 | 68.9 |
\*\*for comparison purposes only. Model not released.
### Multilingual Benchmarks
| Category | Benchmark | Language | Llama 3.2 1B | Llama 3.2 1B Vanilla PTQ\*\* | Llama 3.2 1B Spin Quant | Llama 3.2 1B QLoRA | Llama 3.2 3B | Llama 3.2 3B Vanilla PTQ\*\* | Llama 3.2 3B Spin Quant | Llama 3.2 3B QLoRA | Llama 3.1 8B |
| :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
| General | MMLU (5-shot, macro_avg/acc) | Portuguese | 39.8 | 34.9 | 38.9 | 40.2 | 54.5 | 50.9 | 53.3 | 53.4 | 62.1 |
| | | Spanish | 41.5 | 36.0 | 39.8 | 41.8 | 55.1 | 51.9 | 53.6 | 53.6 | 62.5 |
| | | Italian | 39.8 | 34.9 | 38.1 | 40.6 | 53.8 | 49.9 | 52.1 | 51.7 | 61.6 |
| | | German | 39.2 | 34.9 | 37.5 | 39.6 | 53.3 | 50.0 | 52.2 | 51.3 | 60.6 |
| | | French | 40.5 | 34.8 | 39.2 | 40.8 | 54.6 | 51.2 | 53.3 | 53.3 | 62.3 |
| | | Hindi | 33.5 | 30.0 | 32.1 | 34.0 | 43.3 | 40.4 | 42.0 | 42.1 | 50.9 |
| | | Thai | 34.7 | 31.2 | 32.4 | 34.9 | 44.5 | 41.3 | 44.0 | 42.2 | 50.3 |
\*\*for comparison purposes only. Model not released.
## Inference time
In the below table, we compare the performance metrics of different quantization methods (SpinQuant and QAT \+ LoRA) with the BF16 baseline. The evaluation was done using the [ExecuTorch](https://github.com/pytorch/executorch) framework as the inference engine, with the ARM CPU as a backend using Android OnePlus 12 device.
| Category | Decode (tokens/sec) | Time-to-first-token (sec) | Prefill (tokens/sec) | Model size (PTE file size in MB) | Memory size (RSS in MB) |
| :---- | ----- | ----- | ----- | ----- | ----- |
| 1B BF16 (baseline) | 19.2 | 1.0 | 60.3 | 2358 | 3,185 |
| 1B SpinQuant | 50.2 (2.6x) | 0.3 (-76.9%) | 260.5 (4.3x) | 1083 (-54.1%) | 1,921 (-39.7%) |
| 1B QLoRA | 45.8 (2.4x) | 0.3 (-76.0%) | 252.0 (4.2x) | 1127 (-52.2%) | 2,255 (-29.2%) |
| 3B BF16 (baseline) | 7.6 | 3.0 | 21.2 | 6129 | 7,419 |
| 3B SpinQuant | 19.7 (2.6x) | 0.7 (-76.4%) | 89.7 (4.2x) | 2435 (-60.3%) | 3,726 (-49.8%) |
| 3B QLoRA | 18.5 (2.4x) | 0.7 (-76.1%) | 88.8 (4.2x) | 2529 (-58.7%) | 4,060 (-45.3%) |
(\*) The performance measurement is done using an adb binary-based approach.
(\*\*) It is measured on an Android OnePlus 12 device.
(\*\*\*) Time-to-first-token (TTFT) is measured with prompt length=64
*Footnote:*
- *Decode (tokens/second) is for how quickly it keeps generating. Higher is better.*
- *Time-to-first-token (TTFT for shorthand) is for how fast it generates the first token for a given prompt. Lower is better.*
- *Prefill is the inverse of TTFT (aka 1/TTFT) in tokens/second. Higher is better*
- *Model size \- how big is the model, measured by, PTE file, a binary file format for ExecuTorch*
- *RSS size \- Memory usage in resident set size (RSS)*
## Responsibility & Safety
As part of our Responsible release approach, we followed a three-pronged strategy to managing trust & safety risks:
1. Enable developers to deploy helpful, safe and flexible experiences for their target audience and for the use cases supported by Llama
2. Protect developers against adversarial users aiming to exploit Llama capabilities to potentially cause harm
3. Provide protections for the community to help prevent the misuse of our models
### Responsible Deployment
**Approach:** Llama is a foundational technology designed to be used in a variety of use cases. Examples on how Meta’s Llama models have been responsibly deployed can be found in our [Community Stories webpage](https://llama.meta.com/community-stories/). Our approach is to build the most helpful models, enabling the world to benefit from the technology power, by aligning our model safety for generic use cases and addressing a standard set of harms. Developers are then in the driver’s seat to tailor safety for their use cases, defining their own policies and deploying the models with the necessary safeguards in their Llama systems. Llama 3.2 was developed following the best practices outlined in our [Responsible Use Guide](https://llama.meta.com/responsible-use-guide/).
#### Llama 3.2 Instruct
**Objective:** Our main objectives for conducting safety fine-tuning are to provide the research community with a valuable resource for studying the robustness of safety fine-tuning, as well as to offer developers a readily available, safe, and powerful model for various applications to reduce the developer workload to deploy safe AI systems. We implemented the same set of safety mitigations as in Llama 3, and you can learn more about these in the Llama 3 [paper](https://ai.meta.com/research/publications/the-llama-3-herd-of-models/).
**Fine-Tuning Data:** We employ a multi-faceted approach to data collection, combining human-generated data from our vendors with synthetic data to mitigate potential safety risks. We’ve developed many large language model (LLM)-based classifiers that enable us to thoughtfully select high-quality prompts and responses, enhancing data quality control.
**Refusals and Tone:** Building on the work we started with Llama 3, we put a great emphasis on model refusals to benign prompts as well as refusal tone. We included both borderline and adversarial prompts in our safety data strategy, and modified our safety data responses to follow tone guidelines.
#### Llama 3.2 Systems
**Safety as a System:** Large language models, including Llama 3.2, **are not designed to be deployed in isolation** but instead should be deployed as part of an overall AI system with additional safety guardrails as required. Developers are expected to deploy system safeguards when building agentic systems. Safeguards are key to achieve the right helpfulness-safety alignment as well as mitigating safety and security risks inherent to the system and any integration of the model or system with external tools. As part of our responsible release approach, we provide the community with [safeguards](https://llama.meta.com/trust-and-safety/) that developers should deploy with Llama models or other LLMs, including Llama Guard, Prompt Guard and Code Shield. All our [reference implementations](https://github.com/meta-llama/llama-agentic-system) demos contain these safeguards by default so developers can benefit from system-level safety out-of-the-box.
### New Capabilities and Use Cases
**Technological Advancement:** Llama releases usually introduce new capabilities that require specific considerations in addition to the best practices that generally apply across all Generative AI use cases. For prior release capabilities also supported by Llama 3.2, see [Llama 3.1 Model Card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/MODEL_CARD.md), as the same considerations apply here as well.
**Constrained Environments:** Llama 3.2 1B and 3B models are expected to be deployed in highly constrained environments, such as mobile devices. LLM Systems using smaller models will have a different alignment profile and safety/helpfulness tradeoff than more complex, larger systems. Developers should ensure the safety of their system meets the requirements of their use case. We recommend using lighter system safeguards for such use cases, like Llama Guard 3-1B or its mobile-optimized version.
### Evaluations
**Scaled Evaluations:** We built dedicated, adversarial evaluation datasets and evaluated systems composed of Llama models and Purple Llama safeguards to filter input prompt and output response. It is important to evaluate applications in context, and we recommend building dedicated evaluation dataset for your use case.
**Red Teaming:** We conducted recurring red teaming exercises with the goal of discovering risks via adversarial prompting and we used the learnings to improve our benchmarks and safety tuning datasets. We partnered early with subject-matter experts in critical risk areas to understand the nature of these real-world harms and how such models may lead to unintended harm for society. Based on these conversations, we derived a set of adversarial goals for the red team to attempt to achieve, such as extracting harmful information or reprogramming the model to act in a potentially harmful capacity. The red team consisted of experts in cybersecurity, adversarial machine learning, responsible AI, and integrity in addition to multilingual content specialists with background in integrity issues in specific geographic markets.
### Critical Risks
In addition to our safety work above, we took extra care on measuring and/or mitigating the following critical risk areas:
**1\. CBRNE (Chemical, Biological, Radiological, Nuclear, and Explosive Weapons):** Llama 3.2 1B and 3B models are smaller and less capable derivatives of Llama 3.1. For Llama 3.1 70B and 405B, to assess risks related to proliferation of chemical and biological weapons, we performed uplift testing designed to assess whether use of Llama 3.1 models could meaningfully increase the capabilities of malicious actors to plan or carry out attacks using these types of weapons and have determined that such testing also applies to the smaller 1B and 3B models.
**2\. Child Safety:** Child Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors including the additional languages Llama 3 is trained on. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.
**3\. Cyber Attacks:** For Llama 3.1 405B, our cyber attack uplift study investigated whether LLMs can enhance human capabilities in hacking tasks, both in terms of skill level and speed.
Our attack automation study focused on evaluating the capabilities of LLMs when used as autonomous agents in cyber offensive operations, specifically in the context of ransomware attacks. This evaluation was distinct from previous studies that considered LLMs as interactive assistants. The primary objective was to assess whether these models could effectively function as independent agents in executing complex cyber-attacks without human intervention. Because Llama 3.2’s 1B and 3B models are smaller and less capable models than Llama 3.1 405B, we broadly believe that the testing conducted for the 405B model also applies to Llama 3.2 models.
### Community
**Industry Partnerships:** Generative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership on AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our [Github repository](https://github.com/meta-llama/PurpleLlama).
**Grants:** We also set up the [Llama Impact Grants](https://llama.meta.com/llama-impact-grants/) program to identify and support the most compelling applications of Meta’s Llama model for societal benefit across three categories: education, climate and open innovation. The 20 finalists from the hundreds of applications can be found [here](https://llama.meta.com/llama-impact-grants/#finalists).
**Reporting:** Finally, we put in place a set of resources including an [output reporting mechanism](https://developers.facebook.com/llama_output_feedback) and [bug bounty program](https://www.facebook.com/whitehat) to continuously improve the Llama technology with the help of the community.
## Ethical Considerations and Limitations
**Values:** The core values of Llama 3.2 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3.2 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.
**Testing:** Llama 3.2 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3.2’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3.2 models, developers should perform safety testing and tuning tailored to their specific applications of the model. Please refer to available resources including our [Responsible Use Guide](https://llama.meta.com/responsible-use-guide), [Trust and Safety](https://llama.meta.com/trust-and-safety/) solutions, and other [resources](https://llama.meta.com/docs/get-started/) to learn more about responsible development.
|
Subsets and Splits