modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-08-02 18:27:42
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 549
values | tags
listlengths 1
4.05k
| pipeline_tag
stringclasses 55
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-08-02 18:24:50
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
Lansechen/Qwen2.5-3B-Instruct-Distill-bs17k-batch32-epoch3-8192-addthinktoken_new
|
Lansechen
| 2025-03-05T11:17:26Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen2",
"text-generation",
"generated_from_trainer",
"open-r1",
"trl",
"sft",
"conversational",
"dataset:HuggingFaceH4/Bespoke-Stratos-17k",
"base_model:Qwen/Qwen2.5-3B-Instruct",
"base_model:finetune:Qwen/Qwen2.5-3B-Instruct",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-03-05T09:16:21Z |
---
base_model: Qwen/Qwen2.5-3B-Instruct
datasets: HuggingFaceH4/Bespoke-Stratos-17k
library_name: transformers
model_name: Qwen2.5-3B-Instruct-Distill-bs17k-batch32-epoch3-8192-addthinktoken_new
tags:
- generated_from_trainer
- open-r1
- trl
- sft
licence: license
---
# Model Card for Qwen2.5-3B-Instruct-Distill-bs17k-batch32-epoch3-8192-addthinktoken_new
This model is a fine-tuned version of [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct) on the [HuggingFaceH4/Bespoke-Stratos-17k](https://huggingface.co/datasets/HuggingFaceH4/Bespoke-Stratos-17k) dataset.
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="Lansechen/Qwen2.5-3B-Instruct-Distill-bs17k-batch32-epoch3-8192-addthinktoken_new", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/chenran1995-the-chinese-university-of-hong-kong/huggingface/runs/ia7h9om9)
This model was trained with SFT.
### Framework versions
- TRL: 0.16.0.dev0
- Transformers: 4.49.0
- Pytorch: 2.5.1+cu121
- Datasets: 3.3.1
- Tokenizers: 0.21.0
## Citations
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}}
}
```
|
texanrangee/05336e8b-e235-4cf4-b015-6d23b43f1523
|
texanrangee
| 2025-03-05T11:15:49Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"unsloth",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-03-05T07:46:33Z |
---
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]
|
texanrangee/715dde75-751b-4778-b1ec-4b26a0ff8195
|
texanrangee
| 2025-03-05T11:09:08Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"unsloth",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-03-05T04:55:38Z |
---
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]
|
Wasco114/Wasco
|
Wasco114
| 2025-03-05T11:08:16Z | 0 | 0 | null |
[
"license:bigscience-openrail-m",
"region:us"
] | null | 2025-03-05T11:08:15Z |
---
license: bigscience-openrail-m
---
|
Juicesyo/model
|
Juicesyo
| 2025-03-05T11:08:02Z | 0 | 0 |
transformers
|
[
"transformers",
"pytorch",
"qwen2",
"text-generation",
"unsloth",
"trl",
"sft",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-03-05T11:01:07Z |
---
library_name: transformers
tags:
- unsloth
- trl
- sft
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
mradermacher/Magellanic-Qwen-25B-R999-GGUF
|
mradermacher
| 2025-03-05T11:07:40Z | 164 | 0 |
transformers
|
[
"transformers",
"gguf",
"text-generation-inference",
"RL",
"trl",
"Math",
"Code",
"en",
"zh",
"base_model:prithivMLmods/Magellanic-Qwen-25B-R999",
"base_model:quantized:prithivMLmods/Magellanic-Qwen-25B-R999",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-03-05T01:00:14Z |
---
base_model: prithivMLmods/Magellanic-Qwen-25B-R999
language:
- en
- zh
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- text-generation-inference
- RL
- trl
- Math
- Code
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/prithivMLmods/Magellanic-Qwen-25B-R999
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Magellanic-Qwen-25B-R999-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/Magellanic-Qwen-25B-R999-GGUF/resolve/main/Magellanic-Qwen-25B-R999.Q2_K.gguf) | Q2_K | 9.6 | |
| [GGUF](https://huggingface.co/mradermacher/Magellanic-Qwen-25B-R999-GGUF/resolve/main/Magellanic-Qwen-25B-R999.Q3_K_S.gguf) | Q3_K_S | 11.1 | |
| [GGUF](https://huggingface.co/mradermacher/Magellanic-Qwen-25B-R999-GGUF/resolve/main/Magellanic-Qwen-25B-R999.Q3_K_M.gguf) | Q3_K_M | 12.3 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Magellanic-Qwen-25B-R999-GGUF/resolve/main/Magellanic-Qwen-25B-R999.Q3_K_L.gguf) | Q3_K_L | 13.3 | |
| [GGUF](https://huggingface.co/mradermacher/Magellanic-Qwen-25B-R999-GGUF/resolve/main/Magellanic-Qwen-25B-R999.IQ4_XS.gguf) | IQ4_XS | 13.8 | |
| [GGUF](https://huggingface.co/mradermacher/Magellanic-Qwen-25B-R999-GGUF/resolve/main/Magellanic-Qwen-25B-R999.Q4_K_S.gguf) | Q4_K_S | 14.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Magellanic-Qwen-25B-R999-GGUF/resolve/main/Magellanic-Qwen-25B-R999.Q4_K_M.gguf) | Q4_K_M | 15.3 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Magellanic-Qwen-25B-R999-GGUF/resolve/main/Magellanic-Qwen-25B-R999.Q5_K_S.gguf) | Q5_K_S | 17.4 | |
| [GGUF](https://huggingface.co/mradermacher/Magellanic-Qwen-25B-R999-GGUF/resolve/main/Magellanic-Qwen-25B-R999.Q5_K_M.gguf) | Q5_K_M | 17.8 | |
| [GGUF](https://huggingface.co/mradermacher/Magellanic-Qwen-25B-R999-GGUF/resolve/main/Magellanic-Qwen-25B-R999.Q6_K.gguf) | Q6_K | 20.6 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Magellanic-Qwen-25B-R999-GGUF/resolve/main/Magellanic-Qwen-25B-R999.Q8_0.gguf) | Q8_0 | 26.6 | fast, best quality |
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 -->
|
dslighfdsl/Llama-3.1-8B-Instruct-SFT-15
|
dslighfdsl
| 2025-03-05T11:07:00Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"generated_from_trainer",
"open-r1",
"trl",
"sft",
"conversational",
"dataset:sciworld",
"base_model:meta-llama/Llama-3.1-8B-Instruct",
"base_model:finetune:meta-llama/Llama-3.1-8B-Instruct",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-03-05T10:21:05Z |
---
base_model: meta-llama/Llama-3.1-8B-Instruct
datasets: sciworld
library_name: transformers
model_name: Llama-3.1-8B-Instruct-SFT-15
tags:
- generated_from_trainer
- open-r1
- trl
- sft
licence: license
---
# Model Card for Llama-3.1-8B-Instruct-SFT-15
This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on the [sciworld](https://huggingface.co/datasets/sciworld) dataset.
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="dslighfdsl/Llama-3.1-8B-Instruct-SFT-15", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/pengliangji2023-carnegie-mellon-university/huggingface/runs/eh36nhb1)
This model was trained with SFT.
### Framework versions
- TRL: 0.15.2
- Transformers: 4.50.0.dev0
- Pytorch: 2.5.1
- Datasets: 3.3.2
- Tokenizers: 0.21.0
## Citations
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}}
}
```
|
yhkim9362/Qwen2.5-7B-Instruct-ko-qlora-nf4
|
yhkim9362
| 2025-03-05T11:06:28Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen2",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
] |
text-generation
| 2025-03-05T11:02:32Z |
---
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]
|
komleva/005
|
komleva
| 2025-03-05T11:06:01Z | 5 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen2",
"text-generation",
"mergekit",
"merge",
"conversational",
"arxiv:2306.01708",
"base_model:itorgov/dippy-roleplay-1739875661-0711603",
"base_model:merge:itorgov/dippy-roleplay-1739875661-0711603",
"base_model:itorgov/dippy-roleplay-1739875662-172876",
"base_model:merge:itorgov/dippy-roleplay-1739875662-172876",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-03-03T15:22:02Z |
---
base_model:
- itorgov/dippy-roleplay-1739875661-0711603
- itorgov/dippy-roleplay-1739875662-172876
library_name: transformers
tags:
- mergekit
- merge
---
# merged
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [itorgov/dippy-roleplay-1739875661-0711603](https://huggingface.co/itorgov/dippy-roleplay-1739875661-0711603) as a base.
### Models Merged
The following models were included in the merge:
* [itorgov/dippy-roleplay-1739875662-172876](https://huggingface.co/itorgov/dippy-roleplay-1739875662-172876)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
base_model: itorgov/dippy-roleplay-1739875661-0711603
dtype: float16
merge_method: ties
slices:
- sources:
- layer_range: [0, 64]
model: itorgov/dippy-roleplay-1739875661-0711603
parameters:
density: [1.0, 0.7, 0.1]
weight: 1.0
- layer_range: [0, 64]
model: itorgov/dippy-roleplay-1739875662-172876
parameters:
density: 0.3
weight: 0.0001
```
|
Rinnnt/dqn-SpaceInvadersNoFrameskip-v4
|
Rinnnt
| 2025-03-05T11:05:42Z | 2 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"SpaceInvadersNoFrameskip-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2025-03-04T11:31:35Z |
---
library_name: stable-baselines3
tags:
- SpaceInvadersNoFrameskip-v4
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: DQN
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: SpaceInvadersNoFrameskip-v4
type: SpaceInvadersNoFrameskip-v4
metrics:
- type: mean_reward
value: 318.50 +/- 118.68
name: mean_reward
verified: false
---
# **DQN** Agent playing **SpaceInvadersNoFrameskip-v4**
This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
The RL Zoo is a training framework for Stable Baselines3
reinforcement learning agents,
with hyperparameter optimization and pre-trained agents included.
## Usage (with SB3 RL Zoo)
RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
SB3: https://github.com/DLR-RM/stable-baselines3<br/>
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
SBX (SB3 + Jax): https://github.com/araffin/sbx
Install the RL Zoo (with SB3 and SB3-Contrib):
```bash
pip install rl_zoo3
```
```
# Download model and save it into the logs/ folder
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga Rinnnt -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
```
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga Rinnnt -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
## Training (with the RL Zoo)
```
python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga Rinnnt
```
## Hyperparameters
```python
OrderedDict([('batch_size', 32),
('buffer_size', 100000),
('env_wrapper',
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
('exploration_final_eps', 0.01),
('exploration_fraction', 0.1),
('frame_stack', 4),
('gradient_steps', 1),
('learning_rate', 0.0001),
('learning_starts', 100000),
('n_timesteps', 200000.0),
('optimize_memory_usage', False),
('policy', 'CnnPolicy'),
('target_update_interval', 1000),
('train_freq', 4),
('normalize', False)])
```
# Environment Arguments
```python
{'render_mode': 'rgb_array'}
```
|
PurvaTijare/PPTStab
|
PurvaTijare
| 2025-03-05T11:05:26Z | 0 | 0 |
transformers
|
[
"transformers",
"biology",
"proteomics",
"thermostability",
"PLM",
"tabular-regression",
"en",
"license:mit",
"endpoints_compatible",
"region:us"
] |
tabular-regression
| 2025-03-05T10:58:09Z |
---
license: mit
language:
- en
metrics:
- r_squared
- mse
- mae
- pearsonr
pipeline_tag: tabular-regression
library_name: transformers
tags:
- biology
- proteomics
- thermostability
- PLM
---
# PPTStab
[](https://huggingface.co/PurvaTijare/PPTStab)
PPTStab: Prediction and Designing of thermostable proteins with a desired melting temperature
PPTStab is an ANN+MLP based ensemble regressor model developed to predict the melting temperature of long protein sequences and also design thermostable proteins.
It integrates state-of-the-art LLMs like ProtBert, ProtT5-XL-UniRef50, Ankh, ProtGPT2, ProstT5 based embeddings into the architecture to advance the predictive modeling capabilities.
It is designed for seamless usage, available via a webserver at https://webs.iiitd.edu.in/raghava/pptstab.
Please read/ cite the content about the PPTStab for complete information including working methodology and algorithm behind the approach.
- Paper: [Link](https://www.biorxiv.org/content/10.1101/2024.09.21.614294v1)
- Repository: [GitHub](https://github.com/raghavagps/pptstab)
## Citation
If you use this method in your research, please cite:
```bibtex
@article
{Tijare2024.09.21.614294,
author = {Tijare, Purva and Kumar, Nishant and Raghava, Gajendra P. S.},
title = {Designing of thermostable proteins with a desired melting temperature},
year = {2024},
doi = {10.1101/2024.09.21.614294},
eprint = {https://www.biorxiv.org/content/early/2024/09/24/2024.09.21.614294.full.pdf},
journal = {bioRxiv}
}
```
## Contact
For questions, do not hesitate to reach out and open an issue on here or on our **[GitHub](https://github.com/raghavagps/pptstab)**.
---
|
plumpyfield/any-1
|
plumpyfield
| 2025-03-05T11:05:06Z | 0 | 0 | null |
[
"safetensors",
"any-to-any",
"omega",
"omegalabs",
"bittensor",
"agi",
"license:mit",
"region:us"
] |
any-to-any
| 2025-03-04T19:54:26Z |
---
license: mit
tags:
- any-to-any
- omega
- omegalabs
- bittensor
- agi
---
This is an Any-to-Any model checkpoint for the OMEGA Labs x Bittensor Any-to-Any subnet.
Check out the [git repo](https://github.com/omegalabsinc/omegalabs-anytoany-bittensor) and find OMEGA on X: [@omegalabsai](https://x.com/omegalabsai).
|
lironcohen16/liron
|
lironcohen16
| 2025-03-05T11:03:27Z | 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
| 2025-03-05T10:48:06Z |
---
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: liron2
---
# Liron
<Gallery />
Trained on Replicate using:
https://replicate.com/ostris/flux-dev-lora-trainer/train
## Trigger words
You should use `liron2` to trigger the image generation.
## 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('lironcohen16/liron', weight_name='lora.safetensors')
image = pipeline('your prompt').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)
|
mradermacher/Llama-3.1-8B-uncensored_SQLi-i1-GGUF
|
mradermacher
| 2025-03-05T11:02:25Z | 0 | 1 |
transformers
|
[
"transformers",
"gguf",
"en",
"base_model:PurpleAILAB/Llama-3.1-8B-uncensored_SQLi",
"base_model:quantized:PurpleAILAB/Llama-3.1-8B-uncensored_SQLi",
"endpoints_compatible",
"region:us",
"imatrix",
"conversational"
] | null | 2025-03-05T09:40:03Z |
---
base_model: PurpleAILAB/Llama-3.1-8B-uncensored_SQLi
language:
- en
library_name: transformers
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: nicoboss -->
weighted/imatrix quants of https://huggingface.co/PurpleAILAB/Llama-3.1-8B-uncensored_SQLi
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/Llama-3.1-8B-uncensored_SQLi-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/Llama-3.1-8B-uncensored_SQLi-i1-GGUF/resolve/main/Llama-3.1-8B-uncensored_SQLi.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-uncensored_SQLi-i1-GGUF/resolve/main/Llama-3.1-8B-uncensored_SQLi.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-uncensored_SQLi-i1-GGUF/resolve/main/Llama-3.1-8B-uncensored_SQLi.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-uncensored_SQLi-i1-GGUF/resolve/main/Llama-3.1-8B-uncensored_SQLi.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-uncensored_SQLi-i1-GGUF/resolve/main/Llama-3.1-8B-uncensored_SQLi.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-uncensored_SQLi-i1-GGUF/resolve/main/Llama-3.1-8B-uncensored_SQLi.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-uncensored_SQLi-i1-GGUF/resolve/main/Llama-3.1-8B-uncensored_SQLi.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-uncensored_SQLi-i1-GGUF/resolve/main/Llama-3.1-8B-uncensored_SQLi.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-uncensored_SQLi-i1-GGUF/resolve/main/Llama-3.1-8B-uncensored_SQLi.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-uncensored_SQLi-i1-GGUF/resolve/main/Llama-3.1-8B-uncensored_SQLi.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-uncensored_SQLi-i1-GGUF/resolve/main/Llama-3.1-8B-uncensored_SQLi.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-uncensored_SQLi-i1-GGUF/resolve/main/Llama-3.1-8B-uncensored_SQLi.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-uncensored_SQLi-i1-GGUF/resolve/main/Llama-3.1-8B-uncensored_SQLi.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-uncensored_SQLi-i1-GGUF/resolve/main/Llama-3.1-8B-uncensored_SQLi.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-uncensored_SQLi-i1-GGUF/resolve/main/Llama-3.1-8B-uncensored_SQLi.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-uncensored_SQLi-i1-GGUF/resolve/main/Llama-3.1-8B-uncensored_SQLi.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-uncensored_SQLi-i1-GGUF/resolve/main/Llama-3.1-8B-uncensored_SQLi.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-uncensored_SQLi-i1-GGUF/resolve/main/Llama-3.1-8B-uncensored_SQLi.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-uncensored_SQLi-i1-GGUF/resolve/main/Llama-3.1-8B-uncensored_SQLi.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-uncensored_SQLi-i1-GGUF/resolve/main/Llama-3.1-8B-uncensored_SQLi.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-uncensored_SQLi-i1-GGUF/resolve/main/Llama-3.1-8B-uncensored_SQLi.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-uncensored_SQLi-i1-GGUF/resolve/main/Llama-3.1-8B-uncensored_SQLi.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-uncensored_SQLi-i1-GGUF/resolve/main/Llama-3.1-8B-uncensored_SQLi.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-uncensored_SQLi-i1-GGUF/resolve/main/Llama-3.1-8B-uncensored_SQLi.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | practically like static Q6_K |
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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
<!-- end -->
|
juhw/uiop78
|
juhw
| 2025-03-05T11:01:48Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-03-05T10:58:14Z |
---
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]
|
AImused/cold38
|
AImused
| 2025-03-05T11:01:47Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-03-05T10:43:57Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
mradermacher/Llama-3.1-8B-uncensored_SQLi-GGUF
|
mradermacher
| 2025-03-05T11:00:19Z | 322 | 1 |
transformers
|
[
"transformers",
"gguf",
"en",
"base_model:PurpleAILAB/Llama-3.1-8B-uncensored_SQLi",
"base_model:quantized:PurpleAILAB/Llama-3.1-8B-uncensored_SQLi",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-03-01T18:02:11Z |
---
base_model: PurpleAILAB/Llama-3.1-8B-uncensored_SQLi
language:
- en
library_name: transformers
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/PurpleAILAB/Llama-3.1-8B-uncensored_SQLi
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.1-8B-uncensored_SQLi-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/Llama-3.1-8B-uncensored_SQLi-GGUF/resolve/main/Llama-3.1-8B-uncensored_SQLi.Q2_K.gguf) | Q2_K | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-uncensored_SQLi-GGUF/resolve/main/Llama-3.1-8B-uncensored_SQLi.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-uncensored_SQLi-GGUF/resolve/main/Llama-3.1-8B-uncensored_SQLi.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-uncensored_SQLi-GGUF/resolve/main/Llama-3.1-8B-uncensored_SQLi.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-uncensored_SQLi-GGUF/resolve/main/Llama-3.1-8B-uncensored_SQLi.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-uncensored_SQLi-GGUF/resolve/main/Llama-3.1-8B-uncensored_SQLi.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-uncensored_SQLi-GGUF/resolve/main/Llama-3.1-8B-uncensored_SQLi.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-uncensored_SQLi-GGUF/resolve/main/Llama-3.1-8B-uncensored_SQLi.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-uncensored_SQLi-GGUF/resolve/main/Llama-3.1-8B-uncensored_SQLi.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-uncensored_SQLi-GGUF/resolve/main/Llama-3.1-8B-uncensored_SQLi.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-uncensored_SQLi-GGUF/resolve/main/Llama-3.1-8B-uncensored_SQLi.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-uncensored_SQLi-GGUF/resolve/main/Llama-3.1-8B-uncensored_SQLi.f16.gguf) | f16 | 16.2 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
QAdottech/qwen2.5-7b-custom
|
QAdottech
| 2025-03-05T10:56:23Z | 7 | 0 | null |
[
"safetensors",
"qwen2_5_vl",
"region:us"
] | null | 2025-02-25T17:44:22Z |
# Qwen2.5-7B Custom Model
This is a fine-tuned version of Qwen2.5-7B-Instruct optimized for agent tasks.
## Dataset Information
- Train Dataset Size: 380 examples
- Test Dataset Size: 94 examples
## Model Performance
- Test Accuracy: 0.8811
- Train Accuracy: 0.9912
## Training Configuration
- Base Model: Qwen/Qwen2.5-VL-7B-Instruct
- Checkpoint: checkpoints_27feb/run_20250302_224224/checkpoint-5035
- Dataset: AgentEvalDatapointDataset
- Training Script: [train_transformer.py](train_transformer.py)
- DeepSpeed Config: [deepspeed_config.json](deepspeed_config.json)
The training configuration files are included in this model repository for reproducibility.
|
kk-aivio/fa7bd893-129d-48f7-89a1-51e6252bb4c6
|
kk-aivio
| 2025-03-05T10:55:06Z | 0 | 0 |
peft
|
[
"peft",
"generated_from_trainer",
"base_model:unsloth/Qwen2.5-1.5B",
"base_model:adapter:unsloth/Qwen2.5-1.5B",
"region:us"
] | null | 2025-03-05T10:54:54Z |
---
library_name: peft
tags:
- generated_from_trainer
base_model: unsloth/Qwen2.5-1.5B
model-index:
- name: kk-aivio/fa7bd893-129d-48f7-89a1-51e6252bb4c6
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. -->
# kk-aivio/fa7bd893-129d-48f7-89a1-51e6252bb4c6
This model was trained from scratch on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0037
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
### Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1
|
mobeidat/c4ai-command-r7b-arabic-02-2025-Q4_K_M-GGUF
|
mobeidat
| 2025-03-05T10:54:45Z | 0 | 0 |
transformers
|
[
"transformers",
"gguf",
"llama-cpp",
"gguf-my-repo",
"en",
"fr",
"de",
"es",
"it",
"pt",
"ja",
"ko",
"zh",
"ar",
"el",
"fa",
"pl",
"id",
"cs",
"he",
"hi",
"nl",
"ro",
"ru",
"tr",
"uk",
"vi",
"base_model:CohereForAI/c4ai-command-r7b-arabic-02-2025",
"base_model:quantized:CohereForAI/c4ai-command-r7b-arabic-02-2025",
"license:cc-by-nc-4.0",
"region:us",
"conversational"
] | null | 2025-03-05T10:54:20Z |
---
inference: false
library_name: transformers
language:
- en
- fr
- de
- es
- it
- pt
- ja
- ko
- zh
- ar
- el
- fa
- pl
- id
- cs
- he
- hi
- nl
- ro
- ru
- tr
- uk
- vi
license: cc-by-nc-4.0
extra_gated_prompt: By submitting this form, you agree to the [License Agreement](https://cohere.com/c4ai-cc-by-nc-license) and
acknowledge that the information you provide will be collected, used, and shared
in accordance with Cohere’s [Privacy Policy]( https://cohere.com/privacy). You’ll
receive email updates about C4AI and Cohere research, events, products and services.
You can unsubscribe at any time.
extra_gated_fields:
Name: text
Affiliation: text
Country: country
I agree to use this model for non-commercial use ONLY: checkbox
base_model: CohereForAI/c4ai-command-r7b-arabic-02-2025
tags:
- llama-cpp
- gguf-my-repo
---
# mobeidat/c4ai-command-r7b-arabic-02-2025-Q4_K_M-GGUF
This model was converted to GGUF format from [`CohereForAI/c4ai-command-r7b-arabic-02-2025`](https://huggingface.co/CohereForAI/c4ai-command-r7b-arabic-02-2025) 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/CohereForAI/c4ai-command-r7b-arabic-02-2025) 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 mobeidat/c4ai-command-r7b-arabic-02-2025-Q4_K_M-GGUF --hf-file c4ai-command-r7b-arabic-02-2025-q4_k_m.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo mobeidat/c4ai-command-r7b-arabic-02-2025-Q4_K_M-GGUF --hf-file c4ai-command-r7b-arabic-02-2025-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 mobeidat/c4ai-command-r7b-arabic-02-2025-Q4_K_M-GGUF --hf-file c4ai-command-r7b-arabic-02-2025-q4_k_m.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo mobeidat/c4ai-command-r7b-arabic-02-2025-Q4_K_M-GGUF --hf-file c4ai-command-r7b-arabic-02-2025-q4_k_m.gguf -c 2048
```
|
shrey123354/prince
|
shrey123354
| 2025-03-05T10:53:31Z | 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
| 2025-03-05T10:28:58Z |
---
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
---
# Prince
<Gallery />
Trained on Replicate using:
https://replicate.com/ostris/flux-dev-lora-trainer/train
## Trigger words
You should use `Sid` to trigger the image generation.
## 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('shrey123354/prince', weight_name='lora.safetensors')
image = pipeline('your prompt').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)
|
shrey123354/mrunal
|
shrey123354
| 2025-03-05T10:51:25Z | 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
| 2025-03-05T10:26:14Z |
---
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: Sidf
---
# Mrunal
<Gallery />
Trained on Replicate using:
https://replicate.com/ostris/flux-dev-lora-trainer/train
## Trigger words
You should use `Sidf` to trigger the image generation.
## 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('shrey123354/mrunal', weight_name='lora.safetensors')
image = pipeline('your prompt').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)
|
shrey123354/kusha
|
shrey123354
| 2025-03-05T10:49:43Z | 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
| 2025-03-05T10:24:38Z |
---
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
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: Sidf
---
# Kusha
<Gallery />
Trained on Replicate using:
https://replicate.com/ostris/flux-dev-lora-trainer/train
## Trigger words
You should use `Sidf` to trigger the image generation.
## 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('shrey123354/kusha', weight_name='lora.safetensors')
image = pipeline('your prompt').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)
|
PharynxAI/rechargePlan_finetune_testing
|
PharynxAI
| 2025-03-05T10:48:49Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-02-28T12:45:04Z |
---
base_model: base_model/Meta-Llama-3.1-8B-Instruct
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** PharynxAI
- **License:** apache-2.0
- **Finetuned from model :** base_model/Meta-Llama-3.1-8B-Instruct
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)
|
DevQuasar/sauravpanda.BAI-Qwen-2.5-1.5B-reasoning-GGUF
|
DevQuasar
| 2025-03-05T10:48:43Z | 0 | 0 | null |
[
"gguf",
"text-generation",
"base_model:sauravpanda/BAI-Qwen-2.5-1.5B-reasoning",
"base_model:quantized:sauravpanda/BAI-Qwen-2.5-1.5B-reasoning",
"endpoints_compatible",
"region:us",
"conversational"
] |
text-generation
| 2025-03-05T10:37:38Z |
---
base_model:
- sauravpanda/BAI-Qwen-2.5-1.5B-reasoning
pipeline_tag: text-generation
---
[<img src="https://raw.githubusercontent.com/csabakecskemeti/devquasar/main/dq_logo_black-transparent.png" width="200"/>](https://devquasar.com)
Quantized version of: [sauravpanda/BAI-Qwen-2.5-1.5B-reasoning](https://huggingface.co/sauravpanda/BAI-Qwen-2.5-1.5B-reasoning)
'Make knowledge free for everyone'
<p align="center">
Made with <br>
<a href="https://www.civo.com/" target="_blank">
<img src="https://www.civo.com/assets/public/brand-assets/civo-logo-colour-60cc1622dedf346f7afde1fff760523f731b0aac106a5465af98ff4073114b74.svg" width="100"/>
</a>
</p>
<a href='https://ko-fi.com/L4L416YX7C' target='_blank'><img height='36' style='border:0px;height:36px;' src='https://storage.ko-fi.com/cdn/kofi6.png?v=6' border='0' alt='Buy Me a Coffee at ko-fi.com' /></a>
|
TheBlueObserver/Llama-3.2-3B-Instruct__gr-r128-a128-epoch2
|
TheBlueObserver
| 2025-03-05T10:48:01Z | 0 | 0 | null |
[
"safetensors",
"region:us"
] | null | 2025-03-05T10:47:38Z |
# TheBlueObserver/Llama-3.2-3B-Instruct__gr-r128-a128-epoch2 Model Card
## LoRA Details
- **Rank**: 128
- **Alpha**: 128
## Training Details
- **Datasets**: gr_medical
- **Limit**: -1
- **Max Steps**: default
- **Epochs**: 2
|
Abhikhade/stella_en_400M_v5_aquabotica
|
Abhikhade
| 2025-03-05T10:47:00Z | 0 | 0 |
sentence-transformers
|
[
"sentence-transformers",
"safetensors",
"new",
"feature-extraction",
"mteb",
"transformers",
"sentence-similarity",
"custom_code",
"arxiv:2205.13147",
"license:mit",
"model-index",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] |
sentence-similarity
| 2025-03-05T10:11:33Z |
---
model-index:
- name: stella_en_400M_v5
results:
- dataset:
config: en
name: MTEB AmazonCounterfactualClassification (en)
revision: e8379541af4e31359cca9fbcf4b00f2671dba205
split: test
type: mteb/amazon_counterfactual
metrics:
- type: accuracy
value: 92.35820895522387
- type: ap
value: 70.81322736988783
- type: ap_weighted
value: 70.81322736988783
- type: f1
value: 88.9505466159595
- type: f1_weighted
value: 92.68630932872613
- type: main_score
value: 92.35820895522387
task:
type: Classification
- dataset:
config: default
name: MTEB AmazonPolarityClassification
revision: e2d317d38cd51312af73b3d32a06d1a08b442046
split: test
type: mteb/amazon_polarity
metrics:
- type: accuracy
value: 97.1945
- type: ap
value: 96.08192192244094
- type: ap_weighted
value: 96.08192192244094
- type: f1
value: 97.1936887167346
- type: f1_weighted
value: 97.1936887167346
- type: main_score
value: 97.1945
task:
type: Classification
- dataset:
config: en
name: MTEB AmazonReviewsClassification (en)
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
split: test
type: mteb/amazon_reviews_multi
metrics:
- type: accuracy
value: 59.528000000000006
- type: f1
value: 59.21016819840188
- type: f1_weighted
value: 59.21016819840188
- type: main_score
value: 59.528000000000006
task:
type: Classification
- dataset:
config: default
name: MTEB ArguAna
revision: c22ab2a51041ffd869aaddef7af8d8215647e41a
split: test
type: mteb/arguana
metrics:
- type: main_score
value: 64.24
- type: map_at_1
value: 40.398
- type: map_at_10
value: 56.215
- type: map_at_100
value: 56.833999999999996
- type: map_at_1000
value: 56.835
- type: map_at_20
value: 56.747
- type: map_at_3
value: 52.181
- type: map_at_5
value: 54.628
- type: mrr_at_1
value: 41.25177809388336
- type: mrr_at_10
value: 56.570762491815216
- type: mrr_at_100
value: 57.17548614361504
- type: mrr_at_1000
value: 57.176650626377466
- type: mrr_at_20
value: 57.08916253512566
- type: mrr_at_3
value: 52.47747747747754
- type: mrr_at_5
value: 54.94547178757718
- type: nauc_map_at_1000_diff1
value: 22.408086887100158
- type: nauc_map_at_1000_max
value: -8.730419096847543
- type: nauc_map_at_1000_std
value: -17.789262741255737
- type: nauc_map_at_100_diff1
value: 22.407371684274025
- type: nauc_map_at_100_max
value: -8.732263549026266
- type: nauc_map_at_100_std
value: -17.79550515579994
- type: nauc_map_at_10_diff1
value: 21.925005073301246
- type: nauc_map_at_10_max
value: -8.990323944492134
- type: nauc_map_at_10_std
value: -18.199246301671458
- type: nauc_map_at_1_diff1
value: 26.23276644969203
- type: nauc_map_at_1_max
value: -12.376511389571245
- type: nauc_map_at_1_std
value: -18.11411715207284
- type: nauc_map_at_20_diff1
value: 22.32455790850922
- type: nauc_map_at_20_max
value: -8.664671547236034
- type: nauc_map_at_20_std
value: -17.8290016125137
- type: nauc_map_at_3_diff1
value: 22.395462147465064
- type: nauc_map_at_3_max
value: -8.206580750918844
- type: nauc_map_at_3_std
value: -17.604490446911484
- type: nauc_map_at_5_diff1
value: 21.95307379904799
- type: nauc_map_at_5_max
value: -8.03958102978443
- type: nauc_map_at_5_std
value: -17.36578866595004
- type: nauc_mrr_at_1000_diff1
value: 20.124236798365587
- type: nauc_mrr_at_1000_max
value: -9.587376069575898
- type: nauc_mrr_at_1000_std
value: -17.79191612151833
- type: nauc_mrr_at_100_diff1
value: 20.123612603474033
- type: nauc_mrr_at_100_max
value: -9.589187218607831
- type: nauc_mrr_at_100_std
value: -17.7981617777748
- type: nauc_mrr_at_10_diff1
value: 19.723683875738075
- type: nauc_mrr_at_10_max
value: -9.774151729178815
- type: nauc_mrr_at_10_std
value: -18.168668675495162
- type: nauc_mrr_at_1_diff1
value: 23.945332059908132
- type: nauc_mrr_at_1_max
value: -12.260461466152819
- type: nauc_mrr_at_1_std
value: -18.007194922921148
- type: nauc_mrr_at_20_diff1
value: 20.04819461810257
- type: nauc_mrr_at_20_max
value: -9.518368283588936
- type: nauc_mrr_at_20_std
value: -17.831608149836136
- type: nauc_mrr_at_3_diff1
value: 19.8571785245832
- type: nauc_mrr_at_3_max
value: -9.464375021240478
- type: nauc_mrr_at_3_std
value: -17.728533927330453
- type: nauc_mrr_at_5_diff1
value: 19.670313652167827
- type: nauc_mrr_at_5_max
value: -8.966372585728434
- type: nauc_mrr_at_5_std
value: -17.468955834324817
- type: nauc_ndcg_at_1000_diff1
value: 21.863049281767417
- type: nauc_ndcg_at_1000_max
value: -8.18698520924057
- type: nauc_ndcg_at_1000_std
value: -17.634483364794804
- type: nauc_ndcg_at_100_diff1
value: 21.849924385738586
- type: nauc_ndcg_at_100_max
value: -8.226437560889345
- type: nauc_ndcg_at_100_std
value: -17.774648478087002
- type: nauc_ndcg_at_10_diff1
value: 19.888395590413573
- type: nauc_ndcg_at_10_max
value: -8.968706085632382
- type: nauc_ndcg_at_10_std
value: -19.31386964628115
- type: nauc_ndcg_at_1_diff1
value: 26.23276644969203
- type: nauc_ndcg_at_1_max
value: -12.376511389571245
- type: nauc_ndcg_at_1_std
value: -18.11411715207284
- type: nauc_ndcg_at_20_diff1
value: 21.38413342416933
- type: nauc_ndcg_at_20_max
value: -7.636238194084164
- type: nauc_ndcg_at_20_std
value: -17.946390844693028
- type: nauc_ndcg_at_3_diff1
value: 21.29169165029195
- type: nauc_ndcg_at_3_max
value: -6.793840499730093
- type: nauc_ndcg_at_3_std
value: -17.52359001586737
- type: nauc_ndcg_at_5_diff1
value: 20.238297656671364
- type: nauc_ndcg_at_5_max
value: -6.424992706950072
- type: nauc_ndcg_at_5_std
value: -17.082391132291356
- type: nauc_precision_at_1000_diff1
value: -7.05195108528572
- type: nauc_precision_at_1000_max
value: 34.439879624882145
- type: nauc_precision_at_1000_std
value: 68.72436351659353
- type: nauc_precision_at_100_diff1
value: -2.769464113932605
- type: nauc_precision_at_100_max
value: 9.89562961226698
- type: nauc_precision_at_100_std
value: -0.5880967482224028
- type: nauc_precision_at_10_diff1
value: 2.1371544726832323
- type: nauc_precision_at_10_max
value: -11.93051325147756
- type: nauc_precision_at_10_std
value: -30.83144187392059
- type: nauc_precision_at_1_diff1
value: 26.23276644969203
- type: nauc_precision_at_1_max
value: -12.376511389571245
- type: nauc_precision_at_1_std
value: -18.11411715207284
- type: nauc_precision_at_20_diff1
value: 3.780146814257504
- type: nauc_precision_at_20_max
value: 17.06527540214615
- type: nauc_precision_at_20_std
value: -20.36832563035565
- type: nauc_precision_at_3_diff1
value: 17.63894384012077
- type: nauc_precision_at_3_max
value: -2.0220490624638887
- type: nauc_precision_at_3_std
value: -17.285601413493918
- type: nauc_precision_at_5_diff1
value: 12.557855071944601
- type: nauc_precision_at_5_max
value: 0.5840236463956658
- type: nauc_precision_at_5_std
value: -15.827224420217846
- type: nauc_recall_at_1000_diff1
value: -7.051951085286463
- type: nauc_recall_at_1000_max
value: 34.43987962487738
- type: nauc_recall_at_1000_std
value: 68.724363516591
- type: nauc_recall_at_100_diff1
value: -2.769464113930314
- type: nauc_recall_at_100_max
value: 9.895629612270017
- type: nauc_recall_at_100_std
value: -0.58809674821745
- type: nauc_recall_at_10_diff1
value: 2.1371544726834495
- type: nauc_recall_at_10_max
value: -11.930513251477253
- type: nauc_recall_at_10_std
value: -30.83144187392047
- type: nauc_recall_at_1_diff1
value: 26.23276644969203
- type: nauc_recall_at_1_max
value: -12.376511389571245
- type: nauc_recall_at_1_std
value: -18.11411715207284
- type: nauc_recall_at_20_diff1
value: 3.7801468142575922
- type: nauc_recall_at_20_max
value: 17.0652754021456
- type: nauc_recall_at_20_std
value: -20.36832563035559
- type: nauc_recall_at_3_diff1
value: 17.63894384012074
- type: nauc_recall_at_3_max
value: -2.02204906246383
- type: nauc_recall_at_3_std
value: -17.28560141349386
- type: nauc_recall_at_5_diff1
value: 12.55785507194463
- type: nauc_recall_at_5_max
value: 0.5840236463957296
- type: nauc_recall_at_5_std
value: -15.827224420217856
- type: ndcg_at_1
value: 40.398
- type: ndcg_at_10
value: 64.24
- type: ndcg_at_100
value: 66.631
- type: ndcg_at_1000
value: 66.65100000000001
- type: ndcg_at_20
value: 66.086
- type: ndcg_at_3
value: 55.938
- type: ndcg_at_5
value: 60.370000000000005
- type: precision_at_1
value: 40.398
- type: precision_at_10
value: 8.962
- type: precision_at_100
value: 0.9950000000000001
- type: precision_at_1000
value: 0.1
- type: precision_at_20
value: 4.836
- type: precision_at_3
value: 22.262
- type: precision_at_5
value: 15.519
- type: recall_at_1
value: 40.398
- type: recall_at_10
value: 89.616
- type: recall_at_100
value: 99.502
- type: recall_at_1000
value: 99.644
- type: recall_at_20
value: 96.72800000000001
- type: recall_at_3
value: 66.78500000000001
- type: recall_at_5
value: 77.596
task:
type: Retrieval
- dataset:
config: default
name: MTEB ArxivClusteringP2P
revision: a122ad7f3f0291bf49cc6f4d32aa80929df69d5d
split: test
type: mteb/arxiv-clustering-p2p
metrics:
- type: main_score
value: 55.1564333205451
- type: v_measure
value: 55.1564333205451
- type: v_measure_std
value: 14.696883012214512
task:
type: Clustering
- dataset:
config: default
name: MTEB ArxivClusteringS2S
revision: f910caf1a6075f7329cdf8c1a6135696f37dbd53
split: test
type: mteb/arxiv-clustering-s2s
metrics:
- type: main_score
value: 49.823698316694795
- type: v_measure
value: 49.823698316694795
- type: v_measure_std
value: 14.951660654298186
task:
type: Clustering
- dataset:
config: default
name: MTEB AskUbuntuDupQuestions
revision: 2000358ca161889fa9c082cb41daa8dcfb161a54
split: test
type: mteb/askubuntudupquestions-reranking
metrics:
- type: main_score
value: 66.15294503553424
- type: map
value: 66.15294503553424
- type: mrr
value: 78.53438420612935
- type: nAUC_map_diff1
value: 12.569697092717997
- type: nAUC_map_max
value: 21.50670312412572
- type: nAUC_map_std
value: 16.943786429229064
- type: nAUC_mrr_diff1
value: 15.590272897361238
- type: nAUC_mrr_max
value: 34.96072022474653
- type: nAUC_mrr_std
value: 21.649217605241045
task:
type: Reranking
- dataset:
config: default
name: MTEB BIOSSES
revision: d3fb88f8f02e40887cd149695127462bbcf29b4a
split: test
type: mteb/biosses-sts
metrics:
- type: cosine_pearson
value: 85.7824546319275
- type: cosine_spearman
value: 83.29587385660628
- type: euclidean_pearson
value: 84.58764190565167
- type: euclidean_spearman
value: 83.30069324352772
- type: main_score
value: 83.29587385660628
- type: manhattan_pearson
value: 84.95996839947179
- type: manhattan_spearman
value: 83.87480271054358
- type: pearson
value: 85.7824546319275
- type: spearman
value: 83.29587385660628
task:
type: STS
- dataset:
config: default
name: MTEB Banking77Classification
revision: 0fd18e25b25c072e09e0d92ab615fda904d66300
split: test
type: mteb/banking77
metrics:
- type: accuracy
value: 89.30194805194806
- type: f1
value: 89.26182507266391
- type: f1_weighted
value: 89.26182507266391
- type: main_score
value: 89.30194805194806
task:
type: Classification
- dataset:
config: default
name: MTEB BiorxivClusteringP2P
revision: 65b79d1d13f80053f67aca9498d9402c2d9f1f40
split: test
type: mteb/biorxiv-clustering-p2p
metrics:
- type: main_score
value: 50.67972171889736
- type: v_measure
value: 50.67972171889736
- type: v_measure_std
value: 0.7687409980036303
task:
type: Clustering
- dataset:
config: default
name: MTEB BiorxivClusteringS2S
revision: 258694dd0231531bc1fd9de6ceb52a0853c6d908
split: test
type: mteb/biorxiv-clustering-s2s
metrics:
- type: main_score
value: 45.80539715556144
- type: v_measure
value: 45.80539715556144
- type: v_measure_std
value: 0.9601346216579142
task:
type: Clustering
- dataset:
config: default
name: MTEB CQADupstackRetrieval
revision: 4ffe81d471b1924886b33c7567bfb200e9eec5c4
split: test
type: mteb/cqadupstack
metrics:
- type: main_score
value: 44.361250000000005
- type: map_at_1
value: 28.304499999999997
- type: map_at_10
value: 38.54841666666666
- type: map_at_100
value: 39.83141666666667
- type: map_at_1000
value: 39.944750000000006
- type: map_at_20
value: 39.25341666666667
- type: map_at_3
value: 35.406749999999995
- type: map_at_5
value: 37.15558333333333
- type: mrr_at_1
value: 34.09077232860122
- type: mrr_at_10
value: 43.15445393211421
- type: mrr_at_100
value: 43.98645286848257
- type: mrr_at_1000
value: 44.037631313469404
- type: mrr_at_20
value: 43.64045813249614
- type: mrr_at_3
value: 40.674138648480486
- type: mrr_at_5
value: 42.106251182620255
- type: nauc_map_at_1000_diff1
value: 46.250011739434996
- type: nauc_map_at_1000_max
value: 30.13664446260598
- type: nauc_map_at_1000_std
value: 5.422301791618935
- type: nauc_map_at_100_diff1
value: 46.253631351999395
- type: nauc_map_at_100_max
value: 30.12612918885181
- type: nauc_map_at_100_std
value: 5.367077019987172
- type: nauc_map_at_10_diff1
value: 46.328171341741346
- type: nauc_map_at_10_max
value: 29.80274612581464
- type: nauc_map_at_10_std
value: 4.62996685176396
- type: nauc_map_at_1_diff1
value: 51.56118117729493
- type: nauc_map_at_1_max
value: 27.94885243863768
- type: nauc_map_at_1_std
value: 1.700366508927356
- type: nauc_map_at_20_diff1
value: 46.286750260299094
- type: nauc_map_at_20_max
value: 29.979205290353278
- type: nauc_map_at_20_std
value: 5.010588412441873
- type: nauc_map_at_3_diff1
value: 47.10018183619064
- type: nauc_map_at_3_max
value: 29.062318206078753
- type: nauc_map_at_3_std
value: 3.2235696254694197
- type: nauc_map_at_5_diff1
value: 46.41971733050039
- type: nauc_map_at_5_max
value: 29.456798617695657
- type: nauc_map_at_5_std
value: 4.0921691023077145
- type: nauc_mrr_at_1000_diff1
value: 45.88888977975723
- type: nauc_mrr_at_1000_max
value: 32.162138978089544
- type: nauc_mrr_at_1000_std
value: 6.2811943424217915
- type: nauc_mrr_at_100_diff1
value: 45.87480433011124
- type: nauc_mrr_at_100_max
value: 32.16011334212834
- type: nauc_mrr_at_100_std
value: 6.2865717772421785
- type: nauc_mrr_at_10_diff1
value: 45.849652904658825
- type: nauc_mrr_at_10_max
value: 32.13847916232293
- type: nauc_mrr_at_10_std
value: 6.105718728141999
- type: nauc_mrr_at_1_diff1
value: 51.013730325062156
- type: nauc_mrr_at_1_max
value: 32.77457396492779
- type: nauc_mrr_at_1_std
value: 4.415684893471724
- type: nauc_mrr_at_20_diff1
value: 45.86663046255274
- type: nauc_mrr_at_20_max
value: 32.15219360697865
- type: nauc_mrr_at_20_std
value: 6.19603046412763
- type: nauc_mrr_at_3_diff1
value: 46.522376582423185
- type: nauc_mrr_at_3_max
value: 32.18259009733714
- type: nauc_mrr_at_3_std
value: 5.288000648220897
- type: nauc_mrr_at_5_diff1
value: 45.86611481369745
- type: nauc_mrr_at_5_max
value: 32.14261639054921
- type: nauc_mrr_at_5_std
value: 5.8811238177073735
- type: nauc_ndcg_at_1000_diff1
value: 44.5055097547565
- type: nauc_ndcg_at_1000_max
value: 31.149682057975458
- type: nauc_ndcg_at_1000_std
value: 8.157937194901333
- type: nauc_ndcg_at_100_diff1
value: 44.12398363638596
- type: nauc_ndcg_at_100_max
value: 30.878064321409994
- type: nauc_ndcg_at_100_std
value: 8.40493441452808
- type: nauc_ndcg_at_10_diff1
value: 44.200093505221474
- type: nauc_ndcg_at_10_max
value: 30.15267107733158
- type: nauc_ndcg_at_10_std
value: 6.407495361566107
- type: nauc_ndcg_at_1_diff1
value: 51.013730325062156
- type: nauc_ndcg_at_1_max
value: 32.77457396492779
- type: nauc_ndcg_at_1_std
value: 4.415684893471724
- type: nauc_ndcg_at_20_diff1
value: 44.16988321564116
- type: nauc_ndcg_at_20_max
value: 30.333532500651213
- type: nauc_ndcg_at_20_std
value: 7.10024701386895
- type: nauc_ndcg_at_3_diff1
value: 45.35982873879988
- type: nauc_ndcg_at_3_max
value: 30.288312457948702
- type: nauc_ndcg_at_3_std
value: 4.653900898293395
- type: nauc_ndcg_at_5_diff1
value: 44.324558115380185
- type: nauc_ndcg_at_5_max
value: 30.048149698941373
- type: nauc_ndcg_at_5_std
value: 5.6684459618413205
- type: nauc_precision_at_1000_diff1
value: -7.282175798304458
- type: nauc_precision_at_1000_max
value: 7.820142031765352
- type: nauc_precision_at_1000_std
value: 11.736131836431172
- type: nauc_precision_at_100_diff1
value: 1.0222940256506976
- type: nauc_precision_at_100_max
value: 16.12346497070298
- type: nauc_precision_at_100_std
value: 18.202607395247874
- type: nauc_precision_at_10_diff1
value: 18.289439185857837
- type: nauc_precision_at_10_max
value: 26.116517399154375
- type: nauc_precision_at_10_std
value: 13.921214069982302
- type: nauc_precision_at_1_diff1
value: 51.013730325062156
- type: nauc_precision_at_1_max
value: 32.77457396492779
- type: nauc_precision_at_1_std
value: 4.415684893471724
- type: nauc_precision_at_20_diff1
value: 12.365165405210886
- type: nauc_precision_at_20_max
value: 22.946297258937367
- type: nauc_precision_at_20_std
value: 16.13862870358933
- type: nauc_precision_at_3_diff1
value: 32.063423642849685
- type: nauc_precision_at_3_max
value: 30.140965811989407
- type: nauc_precision_at_3_std
value: 8.501746262550146
- type: nauc_precision_at_5_diff1
value: 24.777203357717948
- type: nauc_precision_at_5_max
value: 28.401579566848472
- type: nauc_precision_at_5_std
value: 11.643246774390914
- type: nauc_recall_at_1000_diff1
value: 30.04216463401409
- type: nauc_recall_at_1000_max
value: 34.98067760563842
- type: nauc_recall_at_1000_std
value: 48.01453905250591
- type: nauc_recall_at_100_diff1
value: 31.193415507513972
- type: nauc_recall_at_100_max
value: 28.69740149270981
- type: nauc_recall_at_100_std
value: 25.20960758920368
- type: nauc_recall_at_10_diff1
value: 36.18870823636506
- type: nauc_recall_at_10_max
value: 26.005625231341238
- type: nauc_recall_at_10_std
value: 8.891983977041376
- type: nauc_recall_at_1_diff1
value: 51.56118117729493
- type: nauc_recall_at_1_max
value: 27.94885243863768
- type: nauc_recall_at_1_std
value: 1.700366508927356
- type: nauc_recall_at_20_diff1
value: 34.93996118564803
- type: nauc_recall_at_20_max
value: 26.149961715956138
- type: nauc_recall_at_20_std
value: 12.0657502367633
- type: nauc_recall_at_3_diff1
value: 40.80743946709512
- type: nauc_recall_at_3_max
value: 26.443127773025783
- type: nauc_recall_at_3_std
value: 3.7011448604241477
- type: nauc_recall_at_5_diff1
value: 37.608535157055776
- type: nauc_recall_at_5_max
value: 26.168016189725822
- type: nauc_recall_at_5_std
value: 6.344191564595316
- type: ndcg_at_1
value: 34.09083333333333
- type: ndcg_at_10
value: 44.361250000000005
- type: ndcg_at_100
value: 49.586166666666664
- type: ndcg_at_1000
value: 51.623583333333336
- type: ndcg_at_20
value: 46.40158333333333
- type: ndcg_at_3
value: 39.27733333333333
- type: ndcg_at_5
value: 41.662333333333336
- type: precision_at_1
value: 34.09083333333333
- type: precision_at_10
value: 7.957000000000002
- type: precision_at_100
value: 1.2521666666666669
- type: precision_at_1000
value: 0.16125
- type: precision_at_20
value: 4.6755
- type: precision_at_3
value: 18.402083333333334
- type: precision_at_5
value: 13.104333333333335
- type: recall_at_1
value: 28.304499999999997
- type: recall_at_10
value: 56.80666666666667
- type: recall_at_100
value: 79.66208333333334
- type: recall_at_1000
value: 93.6455
- type: recall_at_20
value: 64.2495
- type: recall_at_3
value: 42.431333333333335
- type: recall_at_5
value: 48.665416666666665
task:
type: Retrieval
- dataset:
config: default
name: MTEB ClimateFEVER
revision: 47f2ac6acb640fc46020b02a5b59fdda04d39380
split: test
type: mteb/climate-fever
metrics:
- type: main_score
value: 43.525999999999996
- type: map_at_1
value: 19.291
- type: map_at_10
value: 33.471000000000004
- type: map_at_100
value: 35.388999999999996
- type: map_at_1000
value: 35.568
- type: map_at_20
value: 34.496
- type: map_at_3
value: 28.713
- type: map_at_5
value: 31.384
- type: mrr_at_1
value: 43.77850162866449
- type: mrr_at_10
value: 56.28576598934912
- type: mrr_at_100
value: 56.8588518168194
- type: mrr_at_1000
value: 56.878236725973544
- type: mrr_at_20
value: 56.6409328120183
- type: mrr_at_3
value: 53.56134636264935
- type: mrr_at_5
value: 55.27795874049956
- type: nauc_map_at_1000_diff1
value: 27.262513153363876
- type: nauc_map_at_1000_max
value: 40.099398684385584
- type: nauc_map_at_1000_std
value: 18.847812394005512
- type: nauc_map_at_100_diff1
value: 27.238993503030745
- type: nauc_map_at_100_max
value: 40.07730434492169
- type: nauc_map_at_100_std
value: 18.795349250833684
- type: nauc_map_at_10_diff1
value: 27.70929180366227
- type: nauc_map_at_10_max
value: 39.55987024970173
- type: nauc_map_at_10_std
value: 17.214881544648996
- type: nauc_map_at_1_diff1
value: 43.34155892182403
- type: nauc_map_at_1_max
value: 38.23324890148018
- type: nauc_map_at_1_std
value: 6.0781444393516075
- type: nauc_map_at_20_diff1
value: 27.311577477800103
- type: nauc_map_at_20_max
value: 39.624414083413456
- type: nauc_map_at_20_std
value: 18.149811054163287
- type: nauc_map_at_3_diff1
value: 30.475965062734367
- type: nauc_map_at_3_max
value: 38.49324825043695
- type: nauc_map_at_3_std
value: 13.357656038648487
- type: nauc_map_at_5_diff1
value: 28.425110095017747
- type: nauc_map_at_5_max
value: 39.017894870747796
- type: nauc_map_at_5_std
value: 15.543817194122564
- type: nauc_mrr_at_1000_diff1
value: 33.16689354701644
- type: nauc_mrr_at_1000_max
value: 41.70755363247148
- type: nauc_mrr_at_1000_std
value: 24.61667417463176
- type: nauc_mrr_at_100_diff1
value: 33.147229262917506
- type: nauc_mrr_at_100_max
value: 41.712455697170725
- type: nauc_mrr_at_100_std
value: 24.6418922043652
- type: nauc_mrr_at_10_diff1
value: 32.94185191112572
- type: nauc_mrr_at_10_max
value: 41.64272730141954
- type: nauc_mrr_at_10_std
value: 24.663391015702707
- type: nauc_mrr_at_1_diff1
value: 39.571969559016395
- type: nauc_mrr_at_1_max
value: 39.396249211263495
- type: nauc_mrr_at_1_std
value: 16.984149923258357
- type: nauc_mrr_at_20_diff1
value: 33.10040770334742
- type: nauc_mrr_at_20_max
value: 41.807565560083034
- type: nauc_mrr_at_20_std
value: 24.8064180365271
- type: nauc_mrr_at_3_diff1
value: 33.065406161485704
- type: nauc_mrr_at_3_max
value: 41.049510969934694
- type: nauc_mrr_at_3_std
value: 23.18371458928609
- type: nauc_mrr_at_5_diff1
value: 33.2389593543916
- type: nauc_mrr_at_5_max
value: 41.629486918949915
- type: nauc_mrr_at_5_std
value: 24.5777253036149
- type: nauc_ndcg_at_1000_diff1
value: 25.868840609197637
- type: nauc_ndcg_at_1000_max
value: 42.79564910784761
- type: nauc_ndcg_at_1000_std
value: 27.035091271680113
- type: nauc_ndcg_at_100_diff1
value: 25.019789319579942
- type: nauc_ndcg_at_100_max
value: 42.482345143533735
- type: nauc_ndcg_at_100_std
value: 26.76872010731345
- type: nauc_ndcg_at_10_diff1
value: 25.949464660653238
- type: nauc_ndcg_at_10_max
value: 40.79769544643906
- type: nauc_ndcg_at_10_std
value: 22.486116508973204
- type: nauc_ndcg_at_1_diff1
value: 39.571969559016395
- type: nauc_ndcg_at_1_max
value: 39.396249211263495
- type: nauc_ndcg_at_1_std
value: 16.984149923258357
- type: nauc_ndcg_at_20_diff1
value: 25.173455685962214
- type: nauc_ndcg_at_20_max
value: 40.88873540662413
- type: nauc_ndcg_at_20_std
value: 24.4451041955519
- type: nauc_ndcg_at_3_diff1
value: 28.185416070726333
- type: nauc_ndcg_at_3_max
value: 39.10600031163912
- type: nauc_ndcg_at_3_std
value: 18.42694044215541
- type: nauc_ndcg_at_5_diff1
value: 27.112647584005583
- type: nauc_ndcg_at_5_max
value: 40.154045682322526
- type: nauc_ndcg_at_5_std
value: 20.26822517176828
- type: nauc_precision_at_1000_diff1
value: -16.42087927044017
- type: nauc_precision_at_1000_max
value: 3.5326295053913
- type: nauc_precision_at_1000_std
value: 24.406810708493197
- type: nauc_precision_at_100_diff1
value: -12.17648135724982
- type: nauc_precision_at_100_max
value: 15.895489260126183
- type: nauc_precision_at_100_std
value: 32.48346122610907
- type: nauc_precision_at_10_diff1
value: -1.2493131347748072
- type: nauc_precision_at_10_max
value: 26.409459305604376
- type: nauc_precision_at_10_std
value: 31.115432019300016
- type: nauc_precision_at_1_diff1
value: 39.571969559016395
- type: nauc_precision_at_1_max
value: 39.396249211263495
- type: nauc_precision_at_1_std
value: 16.984149923258357
- type: nauc_precision_at_20_diff1
value: -6.597509397240593
- type: nauc_precision_at_20_max
value: 21.461984620659695
- type: nauc_precision_at_20_std
value: 32.9450259748889
- type: nauc_precision_at_3_diff1
value: 9.46378764865453
- type: nauc_precision_at_3_max
value: 32.03650819375425
- type: nauc_precision_at_3_std
value: 26.489382638510765
- type: nauc_precision_at_5_diff1
value: 3.5987036728169537
- type: nauc_precision_at_5_max
value: 30.633955978579703
- type: nauc_precision_at_5_std
value: 30.532430088014443
- type: nauc_recall_at_1000_diff1
value: 10.714633106872254
- type: nauc_recall_at_1000_max
value: 43.94958623961
- type: nauc_recall_at_1000_std
value: 51.78914468954123
- type: nauc_recall_at_100_diff1
value: 9.63781472255557
- type: nauc_recall_at_100_max
value: 38.50917465255336
- type: nauc_recall_at_100_std
value: 37.78623984642377
- type: nauc_recall_at_10_diff1
value: 16.480342820841688
- type: nauc_recall_at_10_max
value: 35.982566867357406
- type: nauc_recall_at_10_std
value: 23.30688188788895
- type: nauc_recall_at_1_diff1
value: 43.34155892182403
- type: nauc_recall_at_1_max
value: 38.23324890148018
- type: nauc_recall_at_1_std
value: 6.0781444393516075
- type: nauc_recall_at_20_diff1
value: 13.521048985146367
- type: nauc_recall_at_20_max
value: 34.62462209239834
- type: nauc_recall_at_20_std
value: 27.85924191501618
- type: nauc_recall_at_3_diff1
value: 23.57032748533523
- type: nauc_recall_at_3_max
value: 36.32703197635613
- type: nauc_recall_at_3_std
value: 15.730238734014337
- type: nauc_recall_at_5_diff1
value: 19.61387036368584
- type: nauc_recall_at_5_max
value: 36.22030835529556
- type: nauc_recall_at_5_std
value: 19.76310648649897
- type: ndcg_at_1
value: 43.779
- type: ndcg_at_10
value: 43.525999999999996
- type: ndcg_at_100
value: 50.138000000000005
- type: ndcg_at_1000
value: 52.991
- type: ndcg_at_20
value: 46.083
- type: ndcg_at_3
value: 38.002
- type: ndcg_at_5
value: 39.842
- type: precision_at_1
value: 43.779
- type: precision_at_10
value: 13.205
- type: precision_at_100
value: 2.051
- type: precision_at_1000
value: 0.259
- type: precision_at_20
value: 7.722999999999999
- type: precision_at_3
value: 28.903000000000002
- type: precision_at_5
value: 21.368000000000002
- type: recall_at_1
value: 19.291
- type: recall_at_10
value: 48.754
- type: recall_at_100
value: 70.97200000000001
- type: recall_at_1000
value: 86.611
- type: recall_at_20
value: 55.884
- type: recall_at_3
value: 34.101
- type: recall_at_5
value: 40.784
task:
type: Retrieval
- dataset:
config: default
name: MTEB DBPedia
revision: c0f706b76e590d620bd6618b3ca8efdd34e2d659
split: test
type: mteb/dbpedia
metrics:
- type: main_score
value: 49.884
- type: map_at_1
value: 9.913
- type: map_at_10
value: 23.186999999999998
- type: map_at_100
value: 34.207
- type: map_at_1000
value: 36.318
- type: map_at_20
value: 27.419
- type: map_at_3
value: 15.656
- type: map_at_5
value: 18.945999999999998
- type: mrr_at_1
value: 75.75
- type: mrr_at_10
value: 82.16279761904761
- type: mrr_at_100
value: 82.48445635330299
- type: mrr_at_1000
value: 82.4870246719901
- type: mrr_at_20
value: 82.36203632968338
- type: mrr_at_3
value: 81.29166666666666
- type: mrr_at_5
value: 82.02916666666667
- type: nauc_map_at_1000_diff1
value: 17.0739966990996
- type: nauc_map_at_1000_max
value: 28.440065298437133
- type: nauc_map_at_1000_std
value: 20.83498154003865
- type: nauc_map_at_100_diff1
value: 17.75982086107111
- type: nauc_map_at_100_max
value: 26.87850835673573
- type: nauc_map_at_100_std
value: 18.350282298599275
- type: nauc_map_at_10_diff1
value: 17.15984258564116
- type: nauc_map_at_10_max
value: 10.846179132675553
- type: nauc_map_at_10_std
value: -6.263534464094614
- type: nauc_map_at_1_diff1
value: 24.014897777973694
- type: nauc_map_at_1_max
value: -4.556638938723358
- type: nauc_map_at_1_std
value: -22.7844467526989
- type: nauc_map_at_20_diff1
value: 16.3179372493187
- type: nauc_map_at_20_max
value: 17.176378915498915
- type: nauc_map_at_20_std
value: 1.9378637630340372
- type: nauc_map_at_3_diff1
value: 19.12786794046792
- type: nauc_map_at_3_max
value: 0.09063919305677291
- type: nauc_map_at_3_std
value: -16.713143158330492
- type: nauc_map_at_5_diff1
value: 18.76504725420023
- type: nauc_map_at_5_max
value: 5.040867712207419
- type: nauc_map_at_5_std
value: -12.382578318931165
- type: nauc_mrr_at_1000_diff1
value: 54.61266255011247
- type: nauc_mrr_at_1000_max
value: 60.83961280977112
- type: nauc_mrr_at_1000_std
value: 32.70429260443016
- type: nauc_mrr_at_100_diff1
value: 54.61346236538542
- type: nauc_mrr_at_100_max
value: 60.8407974416647
- type: nauc_mrr_at_100_std
value: 32.69272843993462
- type: nauc_mrr_at_10_diff1
value: 54.74633685810871
- type: nauc_mrr_at_10_max
value: 61.084525933097865
- type: nauc_mrr_at_10_std
value: 33.001220210025565
- type: nauc_mrr_at_1_diff1
value: 56.12708423835806
- type: nauc_mrr_at_1_max
value: 58.9314540998289
- type: nauc_mrr_at_1_std
value: 27.39422607651012
- type: nauc_mrr_at_20_diff1
value: 54.58896150245695
- type: nauc_mrr_at_20_max
value: 60.890929983464815
- type: nauc_mrr_at_20_std
value: 32.65559641276393
- type: nauc_mrr_at_3_diff1
value: 54.38229071443791
- type: nauc_mrr_at_3_max
value: 59.987849044098596
- type: nauc_mrr_at_3_std
value: 33.439813880719974
- type: nauc_mrr_at_5_diff1
value: 54.961790262449824
- type: nauc_mrr_at_5_max
value: 61.17705173908951
- type: nauc_mrr_at_5_std
value: 33.30939850734856
- type: nauc_ndcg_at_1000_diff1
value: 29.27465932507067
- type: nauc_ndcg_at_1000_max
value: 47.952543312315214
- type: nauc_ndcg_at_1000_std
value: 36.17132236391485
- type: nauc_ndcg_at_100_diff1
value: 28.63072328980134
- type: nauc_ndcg_at_100_max
value: 41.460833419186564
- type: nauc_ndcg_at_100_std
value: 27.157100358988135
- type: nauc_ndcg_at_10_diff1
value: 23.41488013023301
- type: nauc_ndcg_at_10_max
value: 39.27798133072349
- type: nauc_ndcg_at_10_std
value: 21.979241438928312
- type: nauc_ndcg_at_1_diff1
value: 46.12120543657642
- type: nauc_ndcg_at_1_max
value: 47.28452124039853
- type: nauc_ndcg_at_1_std
value: 19.799884708952543
- type: nauc_ndcg_at_20_diff1
value: 23.627669045115574
- type: nauc_ndcg_at_20_max
value: 35.88225062457673
- type: nauc_ndcg_at_20_std
value: 18.218628030529498
- type: nauc_ndcg_at_3_diff1
value: 25.37309228946118
- type: nauc_ndcg_at_3_max
value: 40.64426332992231
- type: nauc_ndcg_at_3_std
value: 24.608330645901482
- type: nauc_ndcg_at_5_diff1
value: 24.055798594999654
- type: nauc_ndcg_at_5_max
value: 41.16180524175431
- type: nauc_ndcg_at_5_std
value: 24.048305528761315
- type: nauc_precision_at_1000_diff1
value: -18.234943251015576
- type: nauc_precision_at_1000_max
value: 0.48708502364659184
- type: nauc_precision_at_1000_std
value: 2.4473601543134027
- type: nauc_precision_at_100_diff1
value: -3.0077810947381227
- type: nauc_precision_at_100_max
value: 25.27249321108913
- type: nauc_precision_at_100_std
value: 37.36575792126928
- type: nauc_precision_at_10_diff1
value: -0.2393778190297635
- type: nauc_precision_at_10_max
value: 36.40513293547299
- type: nauc_precision_at_10_std
value: 37.4827885766009
- type: nauc_precision_at_1_diff1
value: 56.12708423835806
- type: nauc_precision_at_1_max
value: 58.9314540998289
- type: nauc_precision_at_1_std
value: 27.39422607651012
- type: nauc_precision_at_20_diff1
value: -1.2010133229402933
- type: nauc_precision_at_20_max
value: 34.117541814385966
- type: nauc_precision_at_20_std
value: 39.13273254177449
- type: nauc_precision_at_3_diff1
value: 11.757378092198486
- type: nauc_precision_at_3_max
value: 42.637962482588875
- type: nauc_precision_at_3_std
value: 37.42465077352342
- type: nauc_precision_at_5_diff1
value: 7.233177203405101
- type: nauc_precision_at_5_max
value: 43.1663582897407
- type: nauc_precision_at_5_std
value: 38.848449220750055
- type: nauc_recall_at_1000_diff1
value: 27.33938551969145
- type: nauc_recall_at_1000_max
value: 45.5614254479334
- type: nauc_recall_at_1000_std
value: 50.58528916250458
- type: nauc_recall_at_100_diff1
value: 23.610383761920097
- type: nauc_recall_at_100_max
value: 31.422168485847184
- type: nauc_recall_at_100_std
value: 25.58649926458304
- type: nauc_recall_at_10_diff1
value: 14.62495111808408
- type: nauc_recall_at_10_max
value: 7.4295041277681095
- type: nauc_recall_at_10_std
value: -9.32297089600654
- type: nauc_recall_at_1_diff1
value: 24.014897777973694
- type: nauc_recall_at_1_max
value: -4.556638938723358
- type: nauc_recall_at_1_std
value: -22.7844467526989
- type: nauc_recall_at_20_diff1
value: 14.027862330014662
- type: nauc_recall_at_20_max
value: 12.437478731690844
- type: nauc_recall_at_20_std
value: -3.0740743798103676
- type: nauc_recall_at_3_diff1
value: 16.354018356566712
- type: nauc_recall_at_3_max
value: -2.9812231240997917
- type: nauc_recall_at_3_std
value: -18.27746460743442
- type: nauc_recall_at_5_diff1
value: 16.81486583473587
- type: nauc_recall_at_5_max
value: 2.420128513974744
- type: nauc_recall_at_5_std
value: -14.441820321214108
- type: ndcg_at_1
value: 63.87500000000001
- type: ndcg_at_10
value: 49.884
- type: ndcg_at_100
value: 54.738
- type: ndcg_at_1000
value: 61.635
- type: ndcg_at_20
value: 48.894999999999996
- type: ndcg_at_3
value: 54.287
- type: ndcg_at_5
value: 52.40899999999999
- type: precision_at_1
value: 75.75
- type: precision_at_10
value: 40.9
- type: precision_at_100
value: 13.139999999999999
- type: precision_at_1000
value: 2.533
- type: precision_at_20
value: 30.8
- type: precision_at_3
value: 57.667
- type: precision_at_5
value: 51.05
- type: recall_at_1
value: 9.913
- type: recall_at_10
value: 28.591
- type: recall_at_100
value: 61.017999999999994
- type: recall_at_1000
value: 83.383
- type: recall_at_20
value: 37.834
- type: recall_at_3
value: 17.049
- type: recall_at_5
value: 21.685
task:
type: Retrieval
- dataset:
config: default
name: MTEB EmotionClassification
revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37
split: test
type: mteb/emotion
metrics:
- type: accuracy
value: 78.77499999999999
- type: f1
value: 73.74058240799386
- type: f1_weighted
value: 79.78804377638227
- type: main_score
value: 78.77499999999999
task:
type: Classification
- dataset:
config: default
name: MTEB FEVER
revision: bea83ef9e8fb933d90a2f1d5515737465d613e12
split: test
type: mteb/fever
metrics:
- type: main_score
value: 90.986
- type: map_at_1
value: 81.601
- type: map_at_10
value: 88.242
- type: map_at_100
value: 88.46000000000001
- type: map_at_1000
value: 88.472
- type: map_at_20
value: 88.375
- type: map_at_3
value: 87.237
- type: map_at_5
value: 87.85300000000001
- type: mrr_at_1
value: 87.81878187818782
- type: mrr_at_10
value: 92.20301196786335
- type: mrr_at_100
value: 92.24884236673292
- type: mrr_at_1000
value: 92.2496338899362
- type: mrr_at_20
value: 92.23112073283473
- type: mrr_at_3
value: 91.77417741774165
- type: mrr_at_5
value: 92.03970397039689
- type: nauc_map_at_1000_diff1
value: 56.54670664910505
- type: nauc_map_at_1000_max
value: 33.08375749975477
- type: nauc_map_at_1000_std
value: 2.7491595418252865
- type: nauc_map_at_100_diff1
value: 56.50887688686924
- type: nauc_map_at_100_max
value: 33.075487189958494
- type: nauc_map_at_100_std
value: 2.7675869969253375
- type: nauc_map_at_10_diff1
value: 56.08080806610569
- type: nauc_map_at_10_max
value: 32.776972098819066
- type: nauc_map_at_10_std
value: 2.5904846711290097
- type: nauc_map_at_1_diff1
value: 60.645344065853145
- type: nauc_map_at_1_max
value: 31.232776777514797
- type: nauc_map_at_1_std
value: -1.1946138176109171
- type: nauc_map_at_20_diff1
value: 56.28378454162355
- type: nauc_map_at_20_max
value: 32.98207150385811
- type: nauc_map_at_20_std
value: 2.8469814040214025
- type: nauc_map_at_3_diff1
value: 55.81958007095375
- type: nauc_map_at_3_max
value: 31.602707711038313
- type: nauc_map_at_3_std
value: 0.8117019292273401
- type: nauc_map_at_5_diff1
value: 55.706025752316535
- type: nauc_map_at_5_max
value: 32.16032683604737
- type: nauc_map_at_5_std
value: 1.8853201503498669
- type: nauc_mrr_at_1000_diff1
value: 75.4997173366251
- type: nauc_mrr_at_1000_max
value: 41.49117135484116
- type: nauc_mrr_at_1000_std
value: -2.0636172883680852
- type: nauc_mrr_at_100_diff1
value: 75.50118860648519
- type: nauc_mrr_at_100_max
value: 41.49490161517194
- type: nauc_mrr_at_100_std
value: -2.057024385178682
- type: nauc_mrr_at_10_diff1
value: 75.47295153099428
- type: nauc_mrr_at_10_max
value: 41.55003304042536
- type: nauc_mrr_at_10_std
value: -2.0353663198929253
- type: nauc_mrr_at_1_diff1
value: 76.632058433229
- type: nauc_mrr_at_1_max
value: 39.754483718891656
- type: nauc_mrr_at_1_std
value: -2.962241058101701
- type: nauc_mrr_at_20_diff1
value: 75.47221882396194
- type: nauc_mrr_at_20_max
value: 41.50779280480839
- type: nauc_mrr_at_20_std
value: -1.9620212266426307
- type: nauc_mrr_at_3_diff1
value: 75.5682297897137
- type: nauc_mrr_at_3_max
value: 41.53543801506081
- type: nauc_mrr_at_3_std
value: -3.391681195945978
- type: nauc_mrr_at_5_diff1
value: 75.37562775183947
- type: nauc_mrr_at_5_max
value: 41.42028509006753
- type: nauc_mrr_at_5_std
value: -2.418698675622726
- type: nauc_ndcg_at_1000_diff1
value: 59.364557011624
- type: nauc_ndcg_at_1000_max
value: 35.4112238125149
- type: nauc_ndcg_at_1000_std
value: 3.717516193303376
- type: nauc_ndcg_at_100_diff1
value: 58.55706703023122
- type: nauc_ndcg_at_100_max
value: 35.352285999934594
- type: nauc_ndcg_at_100_std
value: 4.273437944266781
- type: nauc_ndcg_at_10_diff1
value: 56.77422701267037
- type: nauc_ndcg_at_10_max
value: 34.24909893882957
- type: nauc_ndcg_at_10_std
value: 4.178151434006727
- type: nauc_ndcg_at_1_diff1
value: 76.632058433229
- type: nauc_ndcg_at_1_max
value: 39.754483718891656
- type: nauc_ndcg_at_1_std
value: -2.962241058101701
- type: nauc_ndcg_at_20_diff1
value: 57.27343398231262
- type: nauc_ndcg_at_20_max
value: 34.7416626740278
- type: nauc_ndcg_at_20_std
value: 4.955858766014002
- type: nauc_ndcg_at_3_diff1
value: 57.69267803121093
- type: nauc_ndcg_at_3_max
value: 33.13744317023105
- type: nauc_ndcg_at_3_std
value: 0.40380284030057023
- type: nauc_ndcg_at_5_diff1
value: 56.57461019113917
- type: nauc_ndcg_at_5_max
value: 33.244657840804386
- type: nauc_ndcg_at_5_std
value: 2.5121440827702046
- type: nauc_precision_at_1000_diff1
value: -14.54492513449718
- type: nauc_precision_at_1000_max
value: -5.94552147573623
- type: nauc_precision_at_1000_std
value: 1.2446209816057374
- type: nauc_precision_at_100_diff1
value: -15.452676132568344
- type: nauc_precision_at_100_max
value: -3.760241749847617
- type: nauc_precision_at_100_std
value: 4.623534605290865
- type: nauc_precision_at_10_diff1
value: -12.712908026086176
- type: nauc_precision_at_10_max
value: 0.45241316994816805
- type: nauc_precision_at_10_std
value: 7.849478570138391
- type: nauc_precision_at_1_diff1
value: 76.632058433229
- type: nauc_precision_at_1_max
value: 39.754483718891656
- type: nauc_precision_at_1_std
value: -2.962241058101701
- type: nauc_precision_at_20_diff1
value: -14.514618673172041
- type: nauc_precision_at_20_max
value: -1.113635490621818
- type: nauc_precision_at_20_std
value: 8.599811730457576
- type: nauc_precision_at_3_diff1
value: 6.1367799850003815
- type: nauc_precision_at_3_max
value: 8.466271950897857
- type: nauc_precision_at_3_std
value: 1.7458051543195068
- type: nauc_precision_at_5_diff1
value: -5.804548945783379
- type: nauc_precision_at_5_max
value: 3.4060251839074818
- type: nauc_precision_at_5_std
value: 5.583410511782371
- type: nauc_recall_at_1000_diff1
value: 19.329432953574095
- type: nauc_recall_at_1000_max
value: 43.260442595158736
- type: nauc_recall_at_1000_std
value: 53.89644660661804
- type: nauc_recall_at_100_diff1
value: 21.265326296051235
- type: nauc_recall_at_100_max
value: 38.573000195373695
- type: nauc_recall_at_100_std
value: 42.169391082152785
- type: nauc_recall_at_10_diff1
value: 29.785129558987432
- type: nauc_recall_at_10_max
value: 28.379657867558034
- type: nauc_recall_at_10_std
value: 21.132574624091973
- type: nauc_recall_at_1_diff1
value: 60.645344065853145
- type: nauc_recall_at_1_max
value: 31.232776777514797
- type: nauc_recall_at_1_std
value: -1.1946138176109171
- type: nauc_recall_at_20_diff1
value: 25.88845612373954
- type: nauc_recall_at_20_max
value: 30.24785945821152
- type: nauc_recall_at_20_std
value: 31.73911437468067
- type: nauc_recall_at_3_diff1
value: 42.2968464797395
- type: nauc_recall_at_3_max
value: 26.494318009870018
- type: nauc_recall_at_3_std
value: 2.6045977160467544
- type: nauc_recall_at_5_diff1
value: 35.81340094401374
- type: nauc_recall_at_5_max
value: 25.91082947510634
- type: nauc_recall_at_5_std
value: 9.759404930864779
- type: ndcg_at_1
value: 87.819
- type: ndcg_at_10
value: 90.986
- type: ndcg_at_100
value: 91.69
- type: ndcg_at_1000
value: 91.863
- type: ndcg_at_20
value: 91.293
- type: ndcg_at_3
value: 89.621
- type: ndcg_at_5
value: 90.333
- type: precision_at_1
value: 87.819
- type: precision_at_10
value: 10.753
- type: precision_at_100
value: 1.138
- type: precision_at_1000
value: 0.117
- type: precision_at_20
value: 5.4879999999999995
- type: precision_at_3
value: 33.703
- type: precision_at_5
value: 20.831
- type: recall_at_1
value: 81.601
- type: recall_at_10
value: 95.44200000000001
- type: recall_at_100
value: 98.14399999999999
- type: recall_at_1000
value: 99.157
- type: recall_at_20
value: 96.43
- type: recall_at_3
value: 91.729
- type: recall_at_5
value: 93.552
task:
type: Retrieval
- dataset:
config: default
name: MTEB FiQA2018
revision: 27a168819829fe9bcd655c2df245fb19452e8e06
split: test
type: mteb/fiqa
metrics:
- type: main_score
value: 56.056
- type: map_at_1
value: 28.666000000000004
- type: map_at_10
value: 47.437000000000005
- type: map_at_100
value: 49.537
- type: map_at_1000
value: 49.665
- type: map_at_20
value: 48.618
- type: map_at_3
value: 41.355
- type: map_at_5
value: 44.525
- type: mrr_at_1
value: 55.55555555555556
- type: mrr_at_10
value: 63.705173427395614
- type: mrr_at_100
value: 64.25449940779741
- type: mrr_at_1000
value: 64.27635581092147
- type: mrr_at_20
value: 64.03796029079103
- type: mrr_at_3
value: 61.49691358024688
- type: mrr_at_5
value: 62.73148148148143
- type: nauc_map_at_1000_diff1
value: 43.24282910397747
- type: nauc_map_at_1000_max
value: 28.506093180265644
- type: nauc_map_at_1000_std
value: -13.040508386155054
- type: nauc_map_at_100_diff1
value: 43.23650442904607
- type: nauc_map_at_100_max
value: 28.470565635459156
- type: nauc_map_at_100_std
value: -12.988098780714935
- type: nauc_map_at_10_diff1
value: 43.393840733087686
- type: nauc_map_at_10_max
value: 26.637302062720153
- type: nauc_map_at_10_std
value: -14.47500292113762
- type: nauc_map_at_1_diff1
value: 47.705150227211725
- type: nauc_map_at_1_max
value: 15.354189686550129
- type: nauc_map_at_1_std
value: -14.559819859039067
- type: nauc_map_at_20_diff1
value: 43.14121075706104
- type: nauc_map_at_20_max
value: 27.811170590408395
- type: nauc_map_at_20_std
value: -13.459413585283583
- type: nauc_map_at_3_diff1
value: 44.33938667720801
- type: nauc_map_at_3_max
value: 21.785619884549398
- type: nauc_map_at_3_std
value: -15.569980103071593
- type: nauc_map_at_5_diff1
value: 43.39280905665027
- type: nauc_map_at_5_max
value: 25.021492190645017
- type: nauc_map_at_5_std
value: -14.48856622187443
- type: nauc_mrr_at_1000_diff1
value: 52.971563939946286
- type: nauc_mrr_at_1000_max
value: 38.88019486172324
- type: nauc_mrr_at_1000_std
value: -12.412991642381616
- type: nauc_mrr_at_100_diff1
value: 52.978468139876945
- type: nauc_mrr_at_100_max
value: 38.89751787948751
- type: nauc_mrr_at_100_std
value: -12.3677876252269
- type: nauc_mrr_at_10_diff1
value: 52.78507148048174
- type: nauc_mrr_at_10_max
value: 38.55079809310022
- type: nauc_mrr_at_10_std
value: -12.944127025078755
- type: nauc_mrr_at_1_diff1
value: 55.52626805861546
- type: nauc_mrr_at_1_max
value: 40.49306809164979
- type: nauc_mrr_at_1_std
value: -12.886607701317681
- type: nauc_mrr_at_20_diff1
value: 52.9592152665678
- type: nauc_mrr_at_20_max
value: 38.88514014589964
- type: nauc_mrr_at_20_std
value: -12.434464359819444
- type: nauc_mrr_at_3_diff1
value: 52.73696844091174
- type: nauc_mrr_at_3_max
value: 38.61018727252859
- type: nauc_mrr_at_3_std
value: -13.123989867364166
- type: nauc_mrr_at_5_diff1
value: 53.037110010188
- type: nauc_mrr_at_5_max
value: 38.44770729849151
- type: nauc_mrr_at_5_std
value: -13.49318771828972
- type: nauc_ndcg_at_1000_diff1
value: 44.73813840091289
- type: nauc_ndcg_at_1000_max
value: 33.70113904685389
- type: nauc_ndcg_at_1000_std
value: -10.328687058192742
- type: nauc_ndcg_at_100_diff1
value: 44.595174119928835
- type: nauc_ndcg_at_100_max
value: 33.4788285112467
- type: nauc_ndcg_at_100_std
value: -8.695355259716946
- type: nauc_ndcg_at_10_diff1
value: 44.39837225263
- type: nauc_ndcg_at_10_max
value: 29.188289725593393
- type: nauc_ndcg_at_10_std
value: -13.67608323673103
- type: nauc_ndcg_at_1_diff1
value: 55.52626805861546
- type: nauc_ndcg_at_1_max
value: 40.49306809164979
- type: nauc_ndcg_at_1_std
value: -12.886607701317681
- type: nauc_ndcg_at_20_diff1
value: 44.24661739902305
- type: nauc_ndcg_at_20_max
value: 31.667868318249965
- type: nauc_ndcg_at_20_std
value: -10.65470780066342
- type: nauc_ndcg_at_3_diff1
value: 43.39857166975522
- type: nauc_ndcg_at_3_max
value: 31.764668313577495
- type: nauc_ndcg_at_3_std
value: -14.494866954678152
- type: nauc_ndcg_at_5_diff1
value: 43.16976647347281
- type: nauc_ndcg_at_5_max
value: 29.878329062643143
- type: nauc_ndcg_at_5_std
value: -13.987689089179739
- type: nauc_precision_at_1000_diff1
value: -9.807973252625484
- type: nauc_precision_at_1000_max
value: 26.6279603849494
- type: nauc_precision_at_1000_std
value: 7.113187103520632
- type: nauc_precision_at_100_diff1
value: -4.777149603323976
- type: nauc_precision_at_100_max
value: 31.03410463692187
- type: nauc_precision_at_100_std
value: 10.463144150275435
- type: nauc_precision_at_10_diff1
value: 8.691528703215962
- type: nauc_precision_at_10_max
value: 33.329579434123374
- type: nauc_precision_at_10_std
value: -0.8002015226329403
- type: nauc_precision_at_1_diff1
value: 55.52626805861546
- type: nauc_precision_at_1_max
value: 40.49306809164979
- type: nauc_precision_at_1_std
value: -12.886607701317681
- type: nauc_precision_at_20_diff1
value: 3.4564653474184284
- type: nauc_precision_at_20_max
value: 34.401070158471136
- type: nauc_precision_at_20_std
value: 5.813431200164549
- type: nauc_precision_at_3_diff1
value: 22.463219705462187
- type: nauc_precision_at_3_max
value: 34.77413976546924
- type: nauc_precision_at_3_std
value: -7.083890789741479
- type: nauc_precision_at_5_diff1
value: 14.011006004883154
- type: nauc_precision_at_5_max
value: 35.73655466853702
- type: nauc_precision_at_5_std
value: -2.8395172077771598
- type: nauc_recall_at_1000_diff1
value: 16.478046357391555
- type: nauc_recall_at_1000_max
value: 43.231704288282344
- type: nauc_recall_at_1000_std
value: 38.430684937573645
- type: nauc_recall_at_100_diff1
value: 30.764718344602436
- type: nauc_recall_at_100_max
value: 31.769050487166655
- type: nauc_recall_at_100_std
value: 23.48468311677149
- type: nauc_recall_at_10_diff1
value: 34.47339565324045
- type: nauc_recall_at_10_max
value: 19.054212335800454
- type: nauc_recall_at_10_std
value: -11.039734015330437
- type: nauc_recall_at_1_diff1
value: 47.705150227211725
- type: nauc_recall_at_1_max
value: 15.354189686550129
- type: nauc_recall_at_1_std
value: -14.559819859039067
- type: nauc_recall_at_20_diff1
value: 32.1011474016873
- type: nauc_recall_at_20_max
value: 25.546372988304423
- type: nauc_recall_at_20_std
value: -0.007233471152482897
- type: nauc_recall_at_3_diff1
value: 37.5708138019065
- type: nauc_recall_at_3_max
value: 16.66410785756736
- type: nauc_recall_at_3_std
value: -15.404817020108966
- type: nauc_recall_at_5_diff1
value: 35.714519648479595
- type: nauc_recall_at_5_max
value: 19.02075233009296
- type: nauc_recall_at_5_std
value: -13.180963359760725
- type: ndcg_at_1
value: 55.556000000000004
- type: ndcg_at_10
value: 56.056
- type: ndcg_at_100
value: 62.44
- type: ndcg_at_1000
value: 64.263
- type: ndcg_at_20
value: 58.638999999999996
- type: ndcg_at_3
value: 51.722
- type: ndcg_at_5
value: 52.701
- type: precision_at_1
value: 55.556000000000004
- type: precision_at_10
value: 15.679000000000002
- type: precision_at_100
value: 2.252
- type: precision_at_1000
value: 0.257
- type: precision_at_20
value: 9.02
- type: precision_at_3
value: 34.619
- type: precision_at_5
value: 25.093
- type: recall_at_1
value: 28.666000000000004
- type: recall_at_10
value: 63.717999999999996
- type: recall_at_100
value: 86.938
- type: recall_at_1000
value: 97.603
- type: recall_at_20
value: 71.649
- type: recall_at_3
value: 46.663
- type: recall_at_5
value: 53.313
task:
type: Retrieval
- dataset:
config: default
name: MTEB HotpotQA
revision: ab518f4d6fcca38d87c25209f94beba119d02014
split: test
type: mteb/hotpotqa
metrics:
- type: main_score
value: 71.74199999999999
- type: map_at_1
value: 41.729
- type: map_at_10
value: 63.168
- type: map_at_100
value: 64.132
- type: map_at_1000
value: 64.199
- type: map_at_20
value: 63.736000000000004
- type: map_at_3
value: 59.826
- type: map_at_5
value: 61.882000000000005
- type: mrr_at_1
value: 83.45712356515868
- type: mrr_at_10
value: 87.850342432719
- type: mrr_at_100
value: 88.0016320691113
- type: mrr_at_1000
value: 88.00576596968136
- type: mrr_at_20
value: 87.94463253190389
- type: mrr_at_3
value: 87.13706954760278
- type: mrr_at_5
value: 87.59419311276136
- type: nauc_map_at_1000_diff1
value: 13.635446621095054
- type: nauc_map_at_1000_max
value: 18.670632529445633
- type: nauc_map_at_1000_std
value: 10.444842636150575
- type: nauc_map_at_100_diff1
value: 13.599262398010783
- type: nauc_map_at_100_max
value: 18.636389405484806
- type: nauc_map_at_100_std
value: 10.460027483576043
- type: nauc_map_at_10_diff1
value: 13.235053919323942
- type: nauc_map_at_10_max
value: 18.252140477080047
- type: nauc_map_at_10_std
value: 9.9075337042203
- type: nauc_map_at_1_diff1
value: 76.51940497836482
- type: nauc_map_at_1_max
value: 51.251419487235474
- type: nauc_map_at_1_std
value: 0.16714896857146574
- type: nauc_map_at_20_diff1
value: 13.4178245722222
- type: nauc_map_at_20_max
value: 18.40988771210718
- type: nauc_map_at_20_std
value: 10.216685163366282
- type: nauc_map_at_3_diff1
value: 13.38370761663418
- type: nauc_map_at_3_max
value: 17.760962555456537
- type: nauc_map_at_3_std
value: 7.15741965624388
- type: nauc_map_at_5_diff1
value: 13.138133309724855
- type: nauc_map_at_5_max
value: 17.871761295251044
- type: nauc_map_at_5_std
value: 8.475147426940074
- type: nauc_mrr_at_1000_diff1
value: 75.82650818891959
- type: nauc_mrr_at_1000_max
value: 53.6736100668434
- type: nauc_mrr_at_1000_std
value: 1.8025016349213916
- type: nauc_mrr_at_100_diff1
value: 75.82530574210111
- type: nauc_mrr_at_100_max
value: 53.68067545829002
- type: nauc_mrr_at_100_std
value: 1.8147470536495791
- type: nauc_mrr_at_10_diff1
value: 75.8330135686799
- type: nauc_mrr_at_10_max
value: 53.78626885349077
- type: nauc_mrr_at_10_std
value: 1.7975782717226636
- type: nauc_mrr_at_1_diff1
value: 76.51940497836482
- type: nauc_mrr_at_1_max
value: 51.251419487235474
- type: nauc_mrr_at_1_std
value: 0.16714896857146574
- type: nauc_mrr_at_20_diff1
value: 75.82783382464166
- type: nauc_mrr_at_20_max
value: 53.68364567043885
- type: nauc_mrr_at_20_std
value: 1.742037904463963
- type: nauc_mrr_at_3_diff1
value: 75.6944609768663
- type: nauc_mrr_at_3_max
value: 53.803941340341666
- type: nauc_mrr_at_3_std
value: 1.1849945458077804
- type: nauc_mrr_at_5_diff1
value: 75.73006960604903
- type: nauc_mrr_at_5_max
value: 53.62223096420106
- type: nauc_mrr_at_5_std
value: 1.6144067563410909
- type: nauc_ndcg_at_1000_diff1
value: 21.58025241642726
- type: nauc_ndcg_at_1000_max
value: 24.675747527001153
- type: nauc_ndcg_at_1000_std
value: 13.075943547492718
- type: nauc_ndcg_at_100_diff1
value: 20.30260137544846
- type: nauc_ndcg_at_100_max
value: 23.757528813872018
- type: nauc_ndcg_at_100_std
value: 13.648994687574062
- type: nauc_ndcg_at_10_diff1
value: 18.995052360997818
- type: nauc_ndcg_at_10_max
value: 22.254260808196037
- type: nauc_ndcg_at_10_std
value: 11.27212390633054
- type: nauc_ndcg_at_1_diff1
value: 76.51940497836482
- type: nauc_ndcg_at_1_max
value: 51.251419487235474
- type: nauc_ndcg_at_1_std
value: 0.16714896857146574
- type: nauc_ndcg_at_20_diff1
value: 19.333742380695757
- type: nauc_ndcg_at_20_max
value: 22.527779834633364
- type: nauc_ndcg_at_20_std
value: 12.161009000707917
- type: nauc_ndcg_at_3_diff1
value: 20.013329040965534
- type: nauc_ndcg_at_3_max
value: 21.99692460311921
- type: nauc_ndcg_at_3_std
value: 6.8076290638386165
- type: nauc_ndcg_at_5_diff1
value: 19.08226315942471
- type: nauc_ndcg_at_5_max
value: 21.71185964294168
- type: nauc_ndcg_at_5_std
value: 8.671911269518214
- type: nauc_precision_at_1000_diff1
value: 2.4462475489446764
- type: nauc_precision_at_1000_max
value: 29.145662064268578
- type: nauc_precision_at_1000_std
value: 49.20704909525856
- type: nauc_precision_at_100_diff1
value: 0.11271196725540299
- type: nauc_precision_at_100_max
value: 17.37584606388067
- type: nauc_precision_at_100_std
value: 34.66099346244071
- type: nauc_precision_at_10_diff1
value: 2.9923183951227825
- type: nauc_precision_at_10_max
value: 14.261884731124264
- type: nauc_precision_at_10_std
value: 18.084188795498378
- type: nauc_precision_at_1_diff1
value: 76.51940497836482
- type: nauc_precision_at_1_max
value: 51.251419487235474
- type: nauc_precision_at_1_std
value: 0.16714896857146574
- type: nauc_precision_at_20_diff1
value: 1.9180293008303761
- type: nauc_precision_at_20_max
value: 13.832269193468512
- type: nauc_precision_at_20_std
value: 21.65284406055607
- type: nauc_precision_at_3_diff1
value: 7.226609484731811
- type: nauc_precision_at_3_max
value: 15.162908526977272
- type: nauc_precision_at_3_std
value: 8.451859972962776
- type: nauc_precision_at_5_diff1
value: 4.705236845538159
- type: nauc_precision_at_5_max
value: 14.022910843582666
- type: nauc_precision_at_5_std
value: 11.777269322821605
- type: nauc_recall_at_1000_diff1
value: 2.446247548945172
- type: nauc_recall_at_1000_max
value: 29.14566206426889
- type: nauc_recall_at_1000_std
value: 49.20704909525879
- type: nauc_recall_at_100_diff1
value: 0.1127119672553316
- type: nauc_recall_at_100_max
value: 17.37584606388062
- type: nauc_recall_at_100_std
value: 34.660993462440686
- type: nauc_recall_at_10_diff1
value: 2.9923183951227927
- type: nauc_recall_at_10_max
value: 14.261884731124299
- type: nauc_recall_at_10_std
value: 18.08418879549837
- type: nauc_recall_at_1_diff1
value: 76.51940497836482
- type: nauc_recall_at_1_max
value: 51.251419487235474
- type: nauc_recall_at_1_std
value: 0.16714896857146574
- type: nauc_recall_at_20_diff1
value: 1.918029300830432
- type: nauc_recall_at_20_max
value: 13.832269193468566
- type: nauc_recall_at_20_std
value: 21.65284406055605
- type: nauc_recall_at_3_diff1
value: 7.226609484731802
- type: nauc_recall_at_3_max
value: 15.162908526977182
- type: nauc_recall_at_3_std
value: 8.451859972962634
- type: nauc_recall_at_5_diff1
value: 4.705236845538197
- type: nauc_recall_at_5_max
value: 14.02291084358265
- type: nauc_recall_at_5_std
value: 11.777269322821638
- type: ndcg_at_1
value: 83.45700000000001
- type: ndcg_at_10
value: 71.74199999999999
- type: ndcg_at_100
value: 75.008
- type: ndcg_at_1000
value: 76.242
- type: ndcg_at_20
value: 73.114
- type: ndcg_at_3
value: 67.128
- type: ndcg_at_5
value: 69.645
- type: precision_at_1
value: 83.45700000000001
- type: precision_at_10
value: 14.747
- type: precision_at_100
value: 1.73
- type: precision_at_1000
value: 0.189
- type: precision_at_20
value: 7.8149999999999995
- type: precision_at_3
value: 42.323
- type: precision_at_5
value: 27.381
- type: recall_at_1
value: 41.729
- type: recall_at_10
value: 73.734
- type: recall_at_100
value: 86.502
- type: recall_at_1000
value: 94.60499999999999
- type: recall_at_20
value: 78.14999999999999
- type: recall_at_3
value: 63.483999999999995
- type: recall_at_5
value: 68.45400000000001
task:
type: Retrieval
- dataset:
config: default
name: MTEB ImdbClassification
revision: 3d86128a09e091d6018b6d26cad27f2739fc2db7
split: test
type: mteb/imdb
metrics:
- type: accuracy
value: 96.4904
- type: ap
value: 94.85481918794709
- type: ap_weighted
value: 94.85481918794709
- type: f1
value: 96.4898592305707
- type: f1_weighted
value: 96.4898592305707
- type: main_score
value: 96.4904
task:
type: Classification
- dataset:
config: default
name: MTEB MSMARCO
revision: c5a29a104738b98a9e76336939199e264163d4a0
split: dev
type: mteb/msmarco
metrics:
- type: main_score
value: 43.692
- type: map_at_1
value: 23.751
- type: map_at_10
value: 36.553999999999995
- type: map_at_100
value: 37.721
- type: map_at_1000
value: 37.763999999999996
- type: map_at_20
value: 37.289
- type: map_at_3
value: 32.643
- type: map_at_5
value: 34.851
- type: mrr_at_1
value: 24.455587392550143
- type: mrr_at_10
value: 37.18388706963206
- type: mrr_at_100
value: 38.28330737932916
- type: mrr_at_1000
value: 38.32054399710817
- type: mrr_at_20
value: 37.8818001216278
- type: mrr_at_3
value: 33.35721107927405
- type: mrr_at_5
value: 35.52483285577843
- type: nauc_map_at_1000_diff1
value: 36.3576177260684
- type: nauc_map_at_1000_max
value: 7.854511605962703
- type: nauc_map_at_1000_std
value: -17.701121059746878
- type: nauc_map_at_100_diff1
value: 36.356075649230505
- type: nauc_map_at_100_max
value: 7.862168042999533
- type: nauc_map_at_100_std
value: -17.670102459097233
- type: nauc_map_at_10_diff1
value: 36.22122978875574
- type: nauc_map_at_10_max
value: 7.80848606967416
- type: nauc_map_at_10_std
value: -18.3265151386167
- type: nauc_map_at_1_diff1
value: 39.28605466408357
- type: nauc_map_at_1_max
value: 6.20202977590459
- type: nauc_map_at_1_std
value: -15.734334090045026
- type: nauc_map_at_20_diff1
value: 36.33637880909657
- type: nauc_map_at_20_max
value: 7.843437969476022
- type: nauc_map_at_20_std
value: -17.917533363025996
- type: nauc_map_at_3_diff1
value: 36.24864976076741
- type: nauc_map_at_3_max
value: 7.420345251835957
- type: nauc_map_at_3_std
value: -18.71678497722944
- type: nauc_map_at_5_diff1
value: 36.0789619291824
- type: nauc_map_at_5_max
value: 7.7314285669514495
- type: nauc_map_at_5_std
value: -18.748688764538706
- type: nauc_mrr_at_1000_diff1
value: 36.23912675623378
- type: nauc_mrr_at_1000_max
value: 7.690553436255147
- type: nauc_mrr_at_1000_std
value: -17.609526070212304
- type: nauc_mrr_at_100_diff1
value: 36.23782651189002
- type: nauc_mrr_at_100_max
value: 7.70075095171647
- type: nauc_mrr_at_100_std
value: -17.575714144960184
- type: nauc_mrr_at_10_diff1
value: 36.125229472534215
- type: nauc_mrr_at_10_max
value: 7.635472248755658
- type: nauc_mrr_at_10_std
value: -18.208166616511086
- type: nauc_mrr_at_1_diff1
value: 39.20986875554532
- type: nauc_mrr_at_1_max
value: 6.062668487561363
- type: nauc_mrr_at_1_std
value: -16.04130340817602
- type: nauc_mrr_at_20_diff1
value: 36.21207088739667
- type: nauc_mrr_at_20_max
value: 7.699610250145951
- type: nauc_mrr_at_20_std
value: -17.778245221724028
- type: nauc_mrr_at_3_diff1
value: 36.03957583885305
- type: nauc_mrr_at_3_max
value: 7.225515576504581
- type: nauc_mrr_at_3_std
value: -18.74478742943741
- type: nauc_mrr_at_5_diff1
value: 35.969152496648974
- type: nauc_mrr_at_5_max
value: 7.584059789018233
- type: nauc_mrr_at_5_std
value: -18.569374723129332
- type: nauc_ndcg_at_1000_diff1
value: 35.894655529841806
- type: nauc_ndcg_at_1000_max
value: 8.579327424366236
- type: nauc_ndcg_at_1000_std
value: -16.359677367747896
- type: nauc_ndcg_at_100_diff1
value: 35.89861902483983
- type: nauc_ndcg_at_100_max
value: 8.830873623962242
- type: nauc_ndcg_at_100_std
value: -15.173125564722978
- type: nauc_ndcg_at_10_diff1
value: 35.36499811105169
- type: nauc_ndcg_at_10_max
value: 8.449267180956992
- type: nauc_ndcg_at_10_std
value: -18.41978802362402
- type: nauc_ndcg_at_1_diff1
value: 39.15422481210622
- type: nauc_ndcg_at_1_max
value: 6.055515791928331
- type: nauc_ndcg_at_1_std
value: -16.042779610876252
- type: nauc_ndcg_at_20_diff1
value: 35.73402868264468
- type: nauc_ndcg_at_20_max
value: 8.695705518210847
- type: nauc_ndcg_at_20_std
value: -16.7735829470466
- type: nauc_ndcg_at_3_diff1
value: 35.31358242856231
- type: nauc_ndcg_at_3_max
value: 7.645692789058997
- type: nauc_ndcg_at_3_std
value: -19.460003734786874
- type: nauc_ndcg_at_5_diff1
value: 35.05216588927143
- type: nauc_ndcg_at_5_max
value: 8.216690520604715
- type: nauc_ndcg_at_5_std
value: -19.3982054492159
- type: nauc_precision_at_1000_diff1
value: -4.440002625111349
- type: nauc_precision_at_1000_max
value: 7.886988951901723
- type: nauc_precision_at_1000_std
value: 9.88111187048247
- type: nauc_precision_at_100_diff1
value: 15.728286119463325
- type: nauc_precision_at_100_max
value: 13.218650824470654
- type: nauc_precision_at_100_std
value: 16.113245895522553
- type: nauc_precision_at_10_diff1
value: 29.51218489610567
- type: nauc_precision_at_10_max
value: 10.197432401942912
- type: nauc_precision_at_10_std
value: -16.950603431359493
- type: nauc_precision_at_1_diff1
value: 39.15422481210622
- type: nauc_precision_at_1_max
value: 6.055515791928331
- type: nauc_precision_at_1_std
value: -16.042779610876252
- type: nauc_precision_at_20_diff1
value: 27.825993070397338
- type: nauc_precision_at_20_max
value: 11.437632287846007
- type: nauc_precision_at_20_std
value: -7.450353566405601
- type: nauc_precision_at_3_diff1
value: 32.14135556796588
- type: nauc_precision_at_3_max
value: 7.989252443574163
- type: nauc_precision_at_3_std
value: -21.566254595671055
- type: nauc_precision_at_5_diff1
value: 30.68778685307082
- type: nauc_precision_at_5_max
value: 9.332160758499892
- type: nauc_precision_at_5_std
value: -20.928554713448914
- type: nauc_recall_at_1000_diff1
value: 25.00810478716878
- type: nauc_recall_at_1000_max
value: 46.518165765201644
- type: nauc_recall_at_1000_std
value: 61.4734635576085
- type: nauc_recall_at_100_diff1
value: 33.895581318261726
- type: nauc_recall_at_100_max
value: 20.10706035872801
- type: nauc_recall_at_100_std
value: 24.204226584457047
- type: nauc_recall_at_10_diff1
value: 32.363127359576296
- type: nauc_recall_at_10_max
value: 10.729923804989545
- type: nauc_recall_at_10_std
value: -18.1335370184202
- type: nauc_recall_at_1_diff1
value: 39.28605466408357
- type: nauc_recall_at_1_max
value: 6.20202977590459
- type: nauc_recall_at_1_std
value: -15.734334090045026
- type: nauc_recall_at_20_diff1
value: 33.47804003169795
- type: nauc_recall_at_20_max
value: 12.781494765263382
- type: nauc_recall_at_20_std
value: -9.263970132202658
- type: nauc_recall_at_3_diff1
value: 32.71001429428999
- type: nauc_recall_at_3_max
value: 8.353439197382693
- type: nauc_recall_at_3_std
value: -21.235097744366954
- type: nauc_recall_at_5_diff1
value: 31.87451464963415
- type: nauc_recall_at_5_max
value: 9.635051450907305
- type: nauc_recall_at_5_std
value: -21.113235357132794
- type: ndcg_at_1
value: 24.47
- type: ndcg_at_10
value: 43.692
- type: ndcg_at_100
value: 49.211
- type: ndcg_at_1000
value: 50.244
- type: ndcg_at_20
value: 46.278000000000006
- type: ndcg_at_3
value: 35.719
- type: ndcg_at_5
value: 39.652
- type: precision_at_1
value: 24.47
- type: precision_at_10
value: 6.857
- type: precision_at_100
value: 0.9610000000000001
- type: precision_at_1000
value: 0.105
- type: precision_at_20
value: 3.968
- type: precision_at_3
value: 15.181000000000001
- type: precision_at_5
value: 11.117
- type: recall_at_1
value: 23.751
- type: recall_at_10
value: 65.64
- type: recall_at_100
value: 90.967
- type: recall_at_1000
value: 98.738
- type: recall_at_20
value: 75.639
- type: recall_at_3
value: 43.927
- type: recall_at_5
value: 53.366
task:
type: Retrieval
- dataset:
config: en
name: MTEB MTOPDomainClassification (en)
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
split: test
type: mteb/mtop_domain
metrics:
- type: accuracy
value: 98.82580939352485
- type: f1
value: 98.75201754333801
- type: f1_weighted
value: 98.82795205108245
- type: main_score
value: 98.82580939352485
task:
type: Classification
- dataset:
config: en
name: MTEB MTOPIntentClassification (en)
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
split: test
type: mteb/mtop_intent
metrics:
- type: accuracy
value: 92.29822161422709
- type: f1
value: 77.75210224871594
- type: f1_weighted
value: 93.58661422540348
- type: main_score
value: 92.29822161422709
task:
type: Classification
- dataset:
config: en
name: MTEB MassiveIntentClassification (en)
revision: 4672e20407010da34463acc759c162ca9734bca6
split: test
type: mteb/amazon_massive_intent
metrics:
- type: accuracy
value: 85.17484868863484
- type: f1
value: 81.94484244487094
- type: f1_weighted
value: 85.21022593423332
- type: main_score
value: 85.17484868863484
task:
type: Classification
- dataset:
config: en
name: MTEB MassiveScenarioClassification (en)
revision: fad2c6e8459f9e1c45d9315f4953d921437d70f8
split: test
type: mteb/amazon_massive_scenario
metrics:
- type: accuracy
value: 89.61667787491594
- type: f1
value: 89.02701927621264
- type: f1_weighted
value: 89.56306982022801
- type: main_score
value: 89.61667787491594
task:
type: Classification
- dataset:
config: default
name: MTEB MedrxivClusteringP2P
revision: e7a26af6f3ae46b30dde8737f02c07b1505bcc73
split: test
type: mteb/medrxiv-clustering-p2p
metrics:
- type: main_score
value: 46.318282423948574
- type: v_measure
value: 46.318282423948574
- type: v_measure_std
value: 0.9729055662461538
task:
type: Clustering
- dataset:
config: default
name: MTEB MedrxivClusteringS2S
revision: 35191c8c0dca72d8ff3efcd72aa802307d469663
split: test
type: mteb/medrxiv-clustering-s2s
metrics:
- type: main_score
value: 44.29033625273981
- type: v_measure
value: 44.29033625273981
- type: v_measure_std
value: 1.0596383629128594
task:
type: Clustering
- dataset:
config: default
name: MTEB MindSmallReranking
revision: 59042f120c80e8afa9cdbb224f67076cec0fc9a7
split: test
type: mteb/mind_small
metrics:
- type: main_score
value: 33.0526129239962
- type: map
value: 33.0526129239962
- type: mrr
value: 34.29260046890935
- type: nAUC_map_diff1
value: 12.579738077238032
- type: nAUC_map_max
value: -20.936629344962
- type: nAUC_map_std
value: -1.6096805784945216
- type: nAUC_mrr_diff1
value: 11.597584463580807
- type: nAUC_mrr_max
value: -15.723702838537504
- type: nAUC_mrr_std
value: 0.2719172965777737
task:
type: Reranking
- dataset:
config: default
name: MTEB NFCorpus
revision: ec0fa4fe99da2ff19ca1214b7966684033a58814
split: test
type: mteb/nfcorpus
metrics:
- type: main_score
value: 41.486000000000004
- type: map_at_1
value: 6.866
- type: map_at_10
value: 15.895999999999999
- type: map_at_100
value: 21.093
- type: map_at_1000
value: 23.067
- type: map_at_20
value: 18.125
- type: map_at_3
value: 11.421000000000001
- type: map_at_5
value: 13.415
- type: mrr_at_1
value: 52.63157894736842
- type: mrr_at_10
value: 61.486805248415166
- type: mrr_at_100
value: 62.08211009182091
- type: mrr_at_1000
value: 62.10828701365016
- type: mrr_at_20
value: 61.904411187915784
- type: mrr_at_3
value: 59.90712074303407
- type: mrr_at_5
value: 60.91331269349847
- type: nauc_map_at_1000_diff1
value: 25.484625278529403
- type: nauc_map_at_1000_max
value: 31.206600396418853
- type: nauc_map_at_1000_std
value: 15.569448072357156
- type: nauc_map_at_100_diff1
value: 27.636750226316764
- type: nauc_map_at_100_max
value: 29.66992681250722
- type: nauc_map_at_100_std
value: 10.570600484002671
- type: nauc_map_at_10_diff1
value: 32.76642525548697
- type: nauc_map_at_10_max
value: 21.459225397237663
- type: nauc_map_at_10_std
value: -3.546494734209264
- type: nauc_map_at_1_diff1
value: 48.8002894871328
- type: nauc_map_at_1_max
value: 5.7236722609868815
- type: nauc_map_at_1_std
value: -13.283554044471352
- type: nauc_map_at_20_diff1
value: 30.57169701502308
- type: nauc_map_at_20_max
value: 25.79666139518404
- type: nauc_map_at_20_std
value: 1.781732492989651
- type: nauc_map_at_3_diff1
value: 40.076315947201095
- type: nauc_map_at_3_max
value: 12.862524429140054
- type: nauc_map_at_3_std
value: -9.188349777126817
- type: nauc_map_at_5_diff1
value: 36.9918718052938
- type: nauc_map_at_5_max
value: 16.74234374361876
- type: nauc_map_at_5_std
value: -7.818523349307494
- type: nauc_mrr_at_1000_diff1
value: 26.88183002609805
- type: nauc_mrr_at_1000_max
value: 47.10209348428658
- type: nauc_mrr_at_1000_std
value: 32.067825924992924
- type: nauc_mrr_at_100_diff1
value: 26.871482491566745
- type: nauc_mrr_at_100_max
value: 47.11303868498556
- type: nauc_mrr_at_100_std
value: 32.08961428818868
- type: nauc_mrr_at_10_diff1
value: 26.6356914977722
- type: nauc_mrr_at_10_max
value: 47.091624558810366
- type: nauc_mrr_at_10_std
value: 31.942424120660164
- type: nauc_mrr_at_1_diff1
value: 28.19774198483673
- type: nauc_mrr_at_1_max
value: 41.44380927834253
- type: nauc_mrr_at_1_std
value: 25.18222691885917
- type: nauc_mrr_at_20_diff1
value: 26.86487347109452
- type: nauc_mrr_at_20_max
value: 47.1987778214726
- type: nauc_mrr_at_20_std
value: 32.143517921610034
- type: nauc_mrr_at_3_diff1
value: 27.34340373236422
- type: nauc_mrr_at_3_max
value: 46.358726506276646
- type: nauc_mrr_at_3_std
value: 31.74924155572593
- type: nauc_mrr_at_5_diff1
value: 27.209667205060672
- type: nauc_mrr_at_5_max
value: 46.79883369072009
- type: nauc_mrr_at_5_std
value: 31.655605306670758
- type: nauc_ndcg_at_1000_diff1
value: 18.940195769769687
- type: nauc_ndcg_at_1000_max
value: 46.48551313937331
- type: nauc_ndcg_at_1000_std
value: 33.64819502089232
- type: nauc_ndcg_at_100_diff1
value: 19.50885253809146
- type: nauc_ndcg_at_100_max
value: 40.53174462354878
- type: nauc_ndcg_at_100_std
value: 28.516152877751118
- type: nauc_ndcg_at_10_diff1
value: 16.01699218096564
- type: nauc_ndcg_at_10_max
value: 41.17322878314514
- type: nauc_ndcg_at_10_std
value: 29.002233224832196
- type: nauc_ndcg_at_1_diff1
value: 27.443547710102205
- type: nauc_ndcg_at_1_max
value: 40.66529763309582
- type: nauc_ndcg_at_1_std
value: 24.15016766225869
- type: nauc_ndcg_at_20_diff1
value: 17.541197675685062
- type: nauc_ndcg_at_20_max
value: 40.53231266973844
- type: nauc_ndcg_at_20_std
value: 29.54096347876548
- type: nauc_ndcg_at_3_diff1
value: 18.649628357473716
- type: nauc_ndcg_at_3_max
value: 41.18603570171764
- type: nauc_ndcg_at_3_std
value: 27.125524188420396
- type: nauc_ndcg_at_5_diff1
value: 17.519593751448483
- type: nauc_ndcg_at_5_max
value: 42.715997890377345
- type: nauc_ndcg_at_5_std
value: 27.902627839899868
- type: nauc_precision_at_1000_diff1
value: -15.528797630565155
- type: nauc_precision_at_1000_max
value: 13.741640921778671
- type: nauc_precision_at_1000_std
value: 44.50896053788372
- type: nauc_precision_at_100_diff1
value: -14.491464489721887
- type: nauc_precision_at_100_max
value: 23.136434418999457
- type: nauc_precision_at_100_std
value: 49.73145147863128
- type: nauc_precision_at_10_diff1
value: -4.829188942994277
- type: nauc_precision_at_10_max
value: 40.327612559528866
- type: nauc_precision_at_10_std
value: 39.34919529635044
- type: nauc_precision_at_1_diff1
value: 28.19774198483673
- type: nauc_precision_at_1_max
value: 41.44380927834253
- type: nauc_precision_at_1_std
value: 25.18222691885917
- type: nauc_precision_at_20_diff1
value: -7.210726293112847
- type: nauc_precision_at_20_max
value: 37.195679576636984
- type: nauc_precision_at_20_std
value: 45.4597096418357
- type: nauc_precision_at_3_diff1
value: 7.578219537774854
- type: nauc_precision_at_3_max
value: 41.59775233475654
- type: nauc_precision_at_3_std
value: 30.764584790895118
- type: nauc_precision_at_5_diff1
value: 1.655451789039598
- type: nauc_precision_at_5_max
value: 43.435739407610455
- type: nauc_precision_at_5_std
value: 33.42552263325999
- type: nauc_recall_at_1000_diff1
value: 5.030705700690516
- type: nauc_recall_at_1000_max
value: 19.108072570815583
- type: nauc_recall_at_1000_std
value: 14.697734974217308
- type: nauc_recall_at_100_diff1
value: 14.746540318132407
- type: nauc_recall_at_100_max
value: 21.798705033854795
- type: nauc_recall_at_100_std
value: 11.416195108842587
- type: nauc_recall_at_10_diff1
value: 25.548642427860486
- type: nauc_recall_at_10_max
value: 18.711677681987474
- type: nauc_recall_at_10_std
value: -5.988904818971677
- type: nauc_recall_at_1_diff1
value: 48.8002894871328
- type: nauc_recall_at_1_max
value: 5.7236722609868815
- type: nauc_recall_at_1_std
value: -13.283554044471352
- type: nauc_recall_at_20_diff1
value: 23.39140739154809
- type: nauc_recall_at_20_max
value: 19.351150636155474
- type: nauc_recall_at_20_std
value: -2.757280266915132
- type: nauc_recall_at_3_diff1
value: 38.17453576012812
- type: nauc_recall_at_3_max
value: 13.47003839643972
- type: nauc_recall_at_3_std
value: -8.75780163862688
- type: nauc_recall_at_5_diff1
value: 33.02812855226899
- type: nauc_recall_at_5_max
value: 15.477626408978477
- type: nauc_recall_at_5_std
value: -9.072206441070708
- type: ndcg_at_1
value: 50.773999999999994
- type: ndcg_at_10
value: 41.486000000000004
- type: ndcg_at_100
value: 39.051
- type: ndcg_at_1000
value: 48.106
- type: ndcg_at_20
value: 39.432
- type: ndcg_at_3
value: 47.428
- type: ndcg_at_5
value: 45.227000000000004
- type: precision_at_1
value: 52.632
- type: precision_at_10
value: 31.146
- type: precision_at_100
value: 10.328
- type: precision_at_1000
value: 2.432
- type: precision_at_20
value: 23.793
- type: precision_at_3
value: 45.201
- type: precision_at_5
value: 39.876
- type: recall_at_1
value: 6.866
- type: recall_at_10
value: 20.447000000000003
- type: recall_at_100
value: 40.607
- type: recall_at_1000
value: 73.411
- type: recall_at_20
value: 26.082
- type: recall_at_3
value: 12.484
- type: recall_at_5
value: 15.847
task:
type: Retrieval
- dataset:
config: default
name: MTEB NQ
revision: b774495ed302d8c44a3a7ea25c90dbce03968f31
split: test
type: mteb/nq
metrics:
- type: main_score
value: 69.072
- type: map_at_1
value: 45.483000000000004
- type: map_at_10
value: 62.050000000000004
- type: map_at_100
value: 62.693
- type: map_at_1000
value: 62.702999999999996
- type: map_at_20
value: 62.498
- type: map_at_3
value: 58.285
- type: map_at_5
value: 60.711000000000006
- type: mrr_at_1
value: 50.840092699884124
- type: mrr_at_10
value: 64.54635224116673
- type: mrr_at_100
value: 64.9526548702289
- type: mrr_at_1000
value: 64.95908460752281
- type: mrr_at_20
value: 64.82949565799959
- type: mrr_at_3
value: 61.89165701042856
- type: mrr_at_5
value: 63.632676709154026
- type: nauc_map_at_1000_diff1
value: 43.187285304185224
- type: nauc_map_at_1000_max
value: 32.39921659632756
- type: nauc_map_at_1000_std
value: -5.780901333066553
- type: nauc_map_at_100_diff1
value: 43.184487221204456
- type: nauc_map_at_100_max
value: 32.41176116347982
- type: nauc_map_at_100_std
value: -5.76422606662383
- type: nauc_map_at_10_diff1
value: 42.967066814031746
- type: nauc_map_at_10_max
value: 32.489617364418514
- type: nauc_map_at_10_std
value: -6.029045531102664
- type: nauc_map_at_1_diff1
value: 46.16376563218624
- type: nauc_map_at_1_max
value: 26.342624776802232
- type: nauc_map_at_1_std
value: -7.142171388751972
- type: nauc_map_at_20_diff1
value: 43.15894358608328
- type: nauc_map_at_20_max
value: 32.46492198956245
- type: nauc_map_at_20_std
value: -5.788373305449195
- type: nauc_map_at_3_diff1
value: 43.231752344608545
- type: nauc_map_at_3_max
value: 31.68003009949564
- type: nauc_map_at_3_std
value: -8.015235132765458
- type: nauc_map_at_5_diff1
value: 42.86197608819917
- type: nauc_map_at_5_max
value: 32.363857571094485
- type: nauc_map_at_5_std
value: -6.780487416387977
- type: nauc_mrr_at_1000_diff1
value: 43.40542912045782
- type: nauc_mrr_at_1000_max
value: 32.8461770324533
- type: nauc_mrr_at_1000_std
value: -3.6505425530008204
- type: nauc_mrr_at_100_diff1
value: 43.40233508014468
- type: nauc_mrr_at_100_max
value: 32.85598538385942
- type: nauc_mrr_at_100_std
value: -3.637477352635459
- type: nauc_mrr_at_10_diff1
value: 43.260179162806054
- type: nauc_mrr_at_10_max
value: 32.942643527040474
- type: nauc_mrr_at_10_std
value: -3.712052825320437
- type: nauc_mrr_at_1_diff1
value: 46.354919460881206
- type: nauc_mrr_at_1_max
value: 29.1760258591106
- type: nauc_mrr_at_1_std
value: -4.107225031227406
- type: nauc_mrr_at_20_diff1
value: 43.37092385434311
- type: nauc_mrr_at_20_max
value: 32.93390254712846
- type: nauc_mrr_at_20_std
value: -3.5719056112132006
- type: nauc_mrr_at_3_diff1
value: 43.1744474040527
- type: nauc_mrr_at_3_max
value: 32.741290559777994
- type: nauc_mrr_at_3_std
value: -4.72677925120697
- type: nauc_mrr_at_5_diff1
value: 43.108396819975674
- type: nauc_mrr_at_5_max
value: 32.970519514893084
- type: nauc_mrr_at_5_std
value: -4.090906158975974
- type: nauc_ndcg_at_1000_diff1
value: 42.786664193638714
- type: nauc_ndcg_at_1000_max
value: 33.65554095609296
- type: nauc_ndcg_at_1000_std
value: -4.024030130584482
- type: nauc_ndcg_at_100_diff1
value: 42.691246775210814
- type: nauc_ndcg_at_100_max
value: 34.063232335110875
- type: nauc_ndcg_at_100_std
value: -3.477813807415248
- type: nauc_ndcg_at_10_diff1
value: 41.90988990571757
- type: nauc_ndcg_at_10_max
value: 34.58934812881633
- type: nauc_ndcg_at_10_std
value: -4.3295110195497655
- type: nauc_ndcg_at_1_diff1
value: 46.354919460881206
- type: nauc_ndcg_at_1_max
value: 29.1760258591106
- type: nauc_ndcg_at_1_std
value: -4.107225031227406
- type: nauc_ndcg_at_20_diff1
value: 42.493206675867114
- type: nauc_ndcg_at_20_max
value: 34.562441307459544
- type: nauc_ndcg_at_20_std
value: -3.4456116866749107
- type: nauc_ndcg_at_3_diff1
value: 42.24180336502808
- type: nauc_ndcg_at_3_max
value: 33.064267018100594
- type: nauc_ndcg_at_3_std
value: -7.786248093572142
- type: nauc_ndcg_at_5_diff1
value: 41.692714787779565
- type: nauc_ndcg_at_5_max
value: 34.20502498949156
- type: nauc_ndcg_at_5_std
value: -5.979557859282785
- type: nauc_precision_at_1000_diff1
value: -13.779832506640702
- type: nauc_precision_at_1000_max
value: 1.243001688631421
- type: nauc_precision_at_1000_std
value: 17.351623398622323
- type: nauc_precision_at_100_diff1
value: -11.310526816290297
- type: nauc_precision_at_100_max
value: 5.771669506192959
- type: nauc_precision_at_100_std
value: 19.917795079540113
- type: nauc_precision_at_10_diff1
value: 2.163699384635286
- type: nauc_precision_at_10_max
value: 19.66440698458386
- type: nauc_precision_at_10_std
value: 13.689876348315726
- type: nauc_precision_at_1_diff1
value: 46.354919460881206
- type: nauc_precision_at_1_max
value: 29.1760258591106
- type: nauc_precision_at_1_std
value: -4.107225031227406
- type: nauc_precision_at_20_diff1
value: -3.038735879584471
- type: nauc_precision_at_20_max
value: 14.132968299701695
- type: nauc_precision_at_20_std
value: 17.78069734664346
- type: nauc_precision_at_3_diff1
value: 21.783760758070095
- type: nauc_precision_at_3_max
value: 30.244127986404497
- type: nauc_precision_at_3_std
value: -0.12411163467738723
- type: nauc_precision_at_5_diff1
value: 10.980635723302418
- type: nauc_precision_at_5_max
value: 25.302293738975575
- type: nauc_precision_at_5_std
value: 6.4740817488722024
- type: nauc_recall_at_1000_diff1
value: 34.10343772356593
- type: nauc_recall_at_1000_max
value: 80.72497340357538
- type: nauc_recall_at_1000_std
value: 69.54564103264093
- type: nauc_recall_at_100_diff1
value: 33.427719956774126
- type: nauc_recall_at_100_max
value: 71.54086768335449
- type: nauc_recall_at_100_std
value: 49.66157377654885
- type: nauc_recall_at_10_diff1
value: 33.70139560054039
- type: nauc_recall_at_10_max
value: 45.47878072860151
- type: nauc_recall_at_10_std
value: 1.4188516615716378
- type: nauc_recall_at_1_diff1
value: 46.16376563218624
- type: nauc_recall_at_1_max
value: 26.342624776802232
- type: nauc_recall_at_1_std
value: -7.142171388751972
- type: nauc_recall_at_20_diff1
value: 35.805379874970086
- type: nauc_recall_at_20_max
value: 51.80479822253392
- type: nauc_recall_at_20_std
value: 13.531467576460143
- type: nauc_recall_at_3_diff1
value: 37.288500141631616
- type: nauc_recall_at_3_max
value: 35.07078243516728
- type: nauc_recall_at_3_std
value: -10.452926441410405
- type: nauc_recall_at_5_diff1
value: 34.83186104526897
- type: nauc_recall_at_5_max
value: 39.58488976496973
- type: nauc_recall_at_5_std
value: -6.3049292065708835
- type: ndcg_at_1
value: 50.839999999999996
- type: ndcg_at_10
value: 69.072
- type: ndcg_at_100
value: 71.538
- type: ndcg_at_1000
value: 71.77799999999999
- type: ndcg_at_20
value: 70.41
- type: ndcg_at_3
value: 62.544999999999995
- type: ndcg_at_5
value: 66.33099999999999
- type: precision_at_1
value: 50.839999999999996
- type: precision_at_10
value: 10.495000000000001
- type: precision_at_100
value: 1.1900000000000002
- type: precision_at_1000
value: 0.121
- type: precision_at_20
value: 5.5809999999999995
- type: precision_at_3
value: 27.636
- type: precision_at_5
value: 18.864
- type: recall_at_1
value: 45.483000000000004
- type: recall_at_10
value: 87.483
- type: recall_at_100
value: 97.844
- type: recall_at_1000
value: 99.66199999999999
- type: recall_at_20
value: 92.294
- type: recall_at_3
value: 71.2
- type: recall_at_5
value: 79.753
task:
type: Retrieval
- dataset:
config: default
name: MTEB QuoraRetrieval
revision: e4e08e0b7dbe3c8700f0daef558ff32256715259
split: test
type: mteb/quora
metrics:
- type: main_score
value: 89.58
- type: map_at_1
value: 71.819
- type: map_at_10
value: 86.04899999999999
- type: map_at_100
value: 86.648
- type: map_at_1000
value: 86.66199999999999
- type: map_at_20
value: 86.441
- type: map_at_3
value: 83.114
- type: map_at_5
value: 84.981
- type: mrr_at_1
value: 82.62
- type: mrr_at_10
value: 88.62899999999979
- type: mrr_at_100
value: 88.70918591324215
- type: mrr_at_1000
value: 88.70973091492397
- type: mrr_at_20
value: 88.68914765317221
- type: mrr_at_3
value: 87.74999999999979
- type: mrr_at_5
value: 88.36799999999974
- type: nauc_map_at_1000_diff1
value: 77.89207709760448
- type: nauc_map_at_1000_max
value: 29.63371361495422
- type: nauc_map_at_1000_std
value: -48.628180385874344
- type: nauc_map_at_100_diff1
value: 77.89592179104915
- type: nauc_map_at_100_max
value: 29.617171506130756
- type: nauc_map_at_100_std
value: -48.66057170774648
- type: nauc_map_at_10_diff1
value: 78.0618161228185
- type: nauc_map_at_10_max
value: 29.178490609366737
- type: nauc_map_at_10_std
value: -50.74755004592002
- type: nauc_map_at_1_diff1
value: 81.64335579973574
- type: nauc_map_at_1_max
value: 21.813832226652174
- type: nauc_map_at_1_std
value: -42.57570978190876
- type: nauc_map_at_20_diff1
value: 77.9299081005938
- type: nauc_map_at_20_max
value: 29.458718470003888
- type: nauc_map_at_20_std
value: -49.63337236763102
- type: nauc_map_at_3_diff1
value: 78.72941448509229
- type: nauc_map_at_3_max
value: 26.600997896960056
- type: nauc_map_at_3_std
value: -51.889002227479885
- type: nauc_map_at_5_diff1
value: 78.31466610917171
- type: nauc_map_at_5_max
value: 28.09863984582896
- type: nauc_map_at_5_std
value: -52.14058096096497
- type: nauc_mrr_at_1000_diff1
value: 78.42667263739992
- type: nauc_mrr_at_1000_max
value: 31.98996235127974
- type: nauc_mrr_at_1000_std
value: -44.380439148429296
- type: nauc_mrr_at_100_diff1
value: 78.42661032698115
- type: nauc_mrr_at_100_max
value: 31.991652631740102
- type: nauc_mrr_at_100_std
value: -44.37854108460535
- type: nauc_mrr_at_10_diff1
value: 78.39126022544136
- type: nauc_mrr_at_10_max
value: 32.02023484451197
- type: nauc_mrr_at_10_std
value: -44.561252349176954
- type: nauc_mrr_at_1_diff1
value: 79.21630894647448
- type: nauc_mrr_at_1_max
value: 31.526303156060177
- type: nauc_mrr_at_1_std
value: -41.887504422443136
- type: nauc_mrr_at_20_diff1
value: 78.42548039170424
- type: nauc_mrr_at_20_max
value: 31.99588275070137
- type: nauc_mrr_at_20_std
value: -44.44957722627042
- type: nauc_mrr_at_3_diff1
value: 78.26165151833735
- type: nauc_mrr_at_3_max
value: 32.18028826126801
- type: nauc_mrr_at_3_std
value: -44.6998237213182
- type: nauc_mrr_at_5_diff1
value: 78.34786430903962
- type: nauc_mrr_at_5_max
value: 32.168476272879566
- type: nauc_mrr_at_5_std
value: -44.7915919956712
- type: nauc_ndcg_at_1000_diff1
value: 77.79198355957816
- type: nauc_ndcg_at_1000_max
value: 31.14363511518406
- type: nauc_ndcg_at_1000_std
value: -46.69335151274275
- type: nauc_ndcg_at_100_diff1
value: 77.79898090286419
- type: nauc_ndcg_at_100_max
value: 31.115103811629215
- type: nauc_ndcg_at_100_std
value: -46.73078913421965
- type: nauc_ndcg_at_10_diff1
value: 77.74856635461343
- type: nauc_ndcg_at_10_max
value: 30.279584686212747
- type: nauc_ndcg_at_10_std
value: -50.23514662356807
- type: nauc_ndcg_at_1_diff1
value: 79.17833000040999
- type: nauc_ndcg_at_1_max
value: 31.703788144510746
- type: nauc_ndcg_at_1_std
value: -41.854817402870715
- type: nauc_ndcg_at_20_diff1
value: 77.7380353804671
- type: nauc_ndcg_at_20_max
value: 30.622294129001553
- type: nauc_ndcg_at_20_std
value: -49.035794761065254
- type: nauc_ndcg_at_3_diff1
value: 77.41476880573593
- type: nauc_ndcg_at_3_max
value: 29.015949978243032
- type: nauc_ndcg_at_3_std
value: -49.78627087622648
- type: nauc_ndcg_at_5_diff1
value: 77.64439137502896
- type: nauc_ndcg_at_5_max
value: 29.444684897492206
- type: nauc_ndcg_at_5_std
value: -51.21908400252501
- type: nauc_precision_at_1000_diff1
value: -44.92396459446822
- type: nauc_precision_at_1000_max
value: -3.674153720989045
- type: nauc_precision_at_1000_std
value: 39.56552468277785
- type: nauc_precision_at_100_diff1
value: -44.75143023259094
- type: nauc_precision_at_100_max
value: -3.705280025140011
- type: nauc_precision_at_100_std
value: 39.433619999113326
- type: nauc_precision_at_10_diff1
value: -41.0651074726579
- type: nauc_precision_at_10_max
value: -0.21097985601783667
- type: nauc_precision_at_10_std
value: 26.24652824589493
- type: nauc_precision_at_1_diff1
value: 79.17833000040999
- type: nauc_precision_at_1_max
value: 31.703788144510746
- type: nauc_precision_at_1_std
value: -41.854817402870715
- type: nauc_precision_at_20_diff1
value: -43.368001340920294
- type: nauc_precision_at_20_max
value: -2.036990010399129
- type: nauc_precision_at_20_std
value: 32.37747041406297
- type: nauc_precision_at_3_diff1
value: -22.089307548346877
- type: nauc_precision_at_3_max
value: 6.2280973175296
- type: nauc_precision_at_3_std
value: 5.323992514036145
- type: nauc_precision_at_5_diff1
value: -34.07115055244003
- type: nauc_precision_at_5_max
value: 2.5955315789198834
- type: nauc_precision_at_5_std
value: 16.26096689407332
- type: nauc_recall_at_1000_diff1
value: 58.27703860947467
- type: nauc_recall_at_1000_max
value: 68.59835835315768
- type: nauc_recall_at_1000_std
value: 77.96687006056064
- type: nauc_recall_at_100_diff1
value: 73.24371223081737
- type: nauc_recall_at_100_max
value: 39.55925344664591
- type: nauc_recall_at_100_std
value: -32.25605030215798
- type: nauc_recall_at_10_diff1
value: 73.41261201339202
- type: nauc_recall_at_10_max
value: 26.822979434062926
- type: nauc_recall_at_10_std
value: -74.2909332592806
- type: nauc_recall_at_1_diff1
value: 81.64335579973574
- type: nauc_recall_at_1_max
value: 21.813832226652174
- type: nauc_recall_at_1_std
value: -42.57570978190876
- type: nauc_recall_at_20_diff1
value: 72.7621297920656
- type: nauc_recall_at_20_max
value: 26.02492304096079
- type: nauc_recall_at_20_std
value: -77.8724532438279
- type: nauc_recall_at_3_diff1
value: 75.25149312810714
- type: nauc_recall_at_3_max
value: 23.20545662481487
- type: nauc_recall_at_3_std
value: -59.69689982140521
- type: nauc_recall_at_5_diff1
value: 73.69807273001406
- type: nauc_recall_at_5_max
value: 24.073666798066057
- type: nauc_recall_at_5_std
value: -67.91121268130719
- type: ndcg_at_1
value: 82.64
- type: ndcg_at_10
value: 89.58
- type: ndcg_at_100
value: 90.606
- type: ndcg_at_1000
value: 90.676
- type: ndcg_at_20
value: 90.132
- type: ndcg_at_3
value: 86.88
- type: ndcg_at_5
value: 88.40299999999999
- type: precision_at_1
value: 82.64
- type: precision_at_10
value: 13.604
- type: precision_at_100
value: 1.539
- type: precision_at_1000
value: 0.157
- type: precision_at_20
value: 7.188
- type: precision_at_3
value: 38.083
- type: precision_at_5
value: 25.018
- type: recall_at_1
value: 71.819
- type: recall_at_10
value: 96.34700000000001
- type: recall_at_100
value: 99.715
- type: recall_at_1000
value: 99.995
- type: recall_at_20
value: 98.073
- type: recall_at_3
value: 88.57300000000001
- type: recall_at_5
value: 92.908
task:
type: Retrieval
- dataset:
config: default
name: MTEB RedditClustering
revision: 24640382cdbf8abc73003fb0fa6d111a705499eb
split: test
type: mteb/reddit-clustering
metrics:
- type: main_score
value: 71.18966762070158
- type: v_measure
value: 71.18966762070158
- type: v_measure_std
value: 2.7498969054457048
task:
type: Clustering
- dataset:
config: default
name: MTEB RedditClusteringP2P
revision: 385e3cb46b4cfa89021f56c4380204149d0efe33
split: test
type: mteb/reddit-clustering-p2p
metrics:
- type: main_score
value: 74.42014716862516
- type: v_measure
value: 74.42014716862516
- type: v_measure_std
value: 9.909739891410648
task:
type: Clustering
- dataset:
config: default
name: MTEB SCIDOCS
revision: f8c2fcf00f625baaa80f62ec5bd9e1fff3b8ae88
split: test
type: mteb/scidocs
metrics:
- type: main_score
value: 25.041999999999998
- type: map_at_1
value: 5.893000000000001
- type: map_at_10
value: 15.260000000000002
- type: map_at_100
value: 18.084
- type: map_at_1000
value: 18.467
- type: map_at_20
value: 16.675
- type: map_at_3
value: 10.526
- type: map_at_5
value: 12.775
- type: mrr_at_1
value: 28.999999999999996
- type: mrr_at_10
value: 41.03575396825395
- type: mrr_at_100
value: 42.136771862785835
- type: mrr_at_1000
value: 42.16698555415099
- type: mrr_at_20
value: 41.707493696104315
- type: mrr_at_3
value: 37.34999999999998
- type: mrr_at_5
value: 39.59999999999995
- type: nauc_map_at_1000_diff1
value: 12.080002654911883
- type: nauc_map_at_1000_max
value: 29.813563682286276
- type: nauc_map_at_1000_std
value: 20.36659817908673
- type: nauc_map_at_100_diff1
value: 12.108735517749706
- type: nauc_map_at_100_max
value: 29.76830671710955
- type: nauc_map_at_100_std
value: 20.3433621032846
- type: nauc_map_at_10_diff1
value: 12.91575031185637
- type: nauc_map_at_10_max
value: 29.427600958386318
- type: nauc_map_at_10_std
value: 16.89867275177153
- type: nauc_map_at_1_diff1
value: 19.353069488987916
- type: nauc_map_at_1_max
value: 17.093914951159693
- type: nauc_map_at_1_std
value: 8.19886078055046
- type: nauc_map_at_20_diff1
value: 11.977233457943113
- type: nauc_map_at_20_max
value: 29.171812822948805
- type: nauc_map_at_20_std
value: 18.780517506173965
- type: nauc_map_at_3_diff1
value: 14.453129464176092
- type: nauc_map_at_3_max
value: 25.801958649112077
- type: nauc_map_at_3_std
value: 11.572823684429643
- type: nauc_map_at_5_diff1
value: 13.167155808104997
- type: nauc_map_at_5_max
value: 27.355626948365792
- type: nauc_map_at_5_std
value: 14.414151839192183
- type: nauc_mrr_at_1000_diff1
value: 17.262104643988636
- type: nauc_mrr_at_1000_max
value: 23.991373837217058
- type: nauc_mrr_at_1000_std
value: 12.44755488671623
- type: nauc_mrr_at_100_diff1
value: 17.267280132318703
- type: nauc_mrr_at_100_max
value: 24.022189287889294
- type: nauc_mrr_at_100_std
value: 12.480695500214788
- type: nauc_mrr_at_10_diff1
value: 17.012383998246268
- type: nauc_mrr_at_10_max
value: 24.192637911171722
- type: nauc_mrr_at_10_std
value: 12.524608847408917
- type: nauc_mrr_at_1_diff1
value: 19.43518811038007
- type: nauc_mrr_at_1_max
value: 17.747482933395602
- type: nauc_mrr_at_1_std
value: 8.410779775558684
- type: nauc_mrr_at_20_diff1
value: 17.202663281407446
- type: nauc_mrr_at_20_max
value: 24.091991130543118
- type: nauc_mrr_at_20_std
value: 12.503814263019908
- type: nauc_mrr_at_3_diff1
value: 17.52733013432995
- type: nauc_mrr_at_3_max
value: 23.569459518780214
- type: nauc_mrr_at_3_std
value: 11.770846827520726
- type: nauc_mrr_at_5_diff1
value: 17.10817561975543
- type: nauc_mrr_at_5_max
value: 23.945141435234678
- type: nauc_mrr_at_5_std
value: 12.034468615317719
- type: nauc_ndcg_at_1000_diff1
value: 12.317811393346936
- type: nauc_ndcg_at_1000_max
value: 30.809991350156103
- type: nauc_ndcg_at_1000_std
value: 24.517501065205067
- type: nauc_ndcg_at_100_diff1
value: 12.824804203182936
- type: nauc_ndcg_at_100_max
value: 30.895499817010748
- type: nauc_ndcg_at_100_std
value: 25.424376279745402
- type: nauc_ndcg_at_10_diff1
value: 13.32724552457439
- type: nauc_ndcg_at_10_max
value: 30.409088666807456
- type: nauc_ndcg_at_10_std
value: 18.216330475714113
- type: nauc_ndcg_at_1_diff1
value: 19.43518811038007
- type: nauc_ndcg_at_1_max
value: 17.747482933395602
- type: nauc_ndcg_at_1_std
value: 8.410779775558684
- type: nauc_ndcg_at_20_diff1
value: 12.224399111852902
- type: nauc_ndcg_at_20_max
value: 29.86352330445272
- type: nauc_ndcg_at_20_std
value: 21.196937851331807
- type: nauc_ndcg_at_3_diff1
value: 15.367489533734027
- type: nauc_ndcg_at_3_max
value: 26.76486390741532
- type: nauc_ndcg_at_3_std
value: 12.606077508789923
- type: nauc_ndcg_at_5_diff1
value: 13.831157482390935
- type: nauc_ndcg_at_5_max
value: 28.070226983968904
- type: nauc_ndcg_at_5_std
value: 15.236787943125435
- type: nauc_precision_at_1000_diff1
value: 0.016122957101357048
- type: nauc_precision_at_1000_max
value: 24.380929903557334
- type: nauc_precision_at_1000_std
value: 34.54045112720052
- type: nauc_precision_at_100_diff1
value: 7.255224788507301
- type: nauc_precision_at_100_max
value: 27.98453788447542
- type: nauc_precision_at_100_std
value: 35.38999555441665
- type: nauc_precision_at_10_diff1
value: 9.69185099834181
- type: nauc_precision_at_10_max
value: 32.532315522580454
- type: nauc_precision_at_10_std
value: 21.48948348473612
- type: nauc_precision_at_1_diff1
value: 19.43518811038007
- type: nauc_precision_at_1_max
value: 17.747482933395602
- type: nauc_precision_at_1_std
value: 8.410779775558684
- type: nauc_precision_at_20_diff1
value: 6.964076536695672
- type: nauc_precision_at_20_max
value: 29.30087236410044
- type: nauc_precision_at_20_std
value: 26.413625895571986
- type: nauc_precision_at_3_diff1
value: 14.145134359925155
- type: nauc_precision_at_3_max
value: 29.915650960808303
- type: nauc_precision_at_3_std
value: 14.095370019867797
- type: nauc_precision_at_5_diff1
value: 11.043933558522692
- type: nauc_precision_at_5_max
value: 30.93016505807111
- type: nauc_precision_at_5_std
value: 17.749256196062603
- type: nauc_recall_at_1000_diff1
value: -0.7776817772090345
- type: nauc_recall_at_1000_max
value: 23.094717340324518
- type: nauc_recall_at_1000_std
value: 37.189908681396425
- type: nauc_recall_at_100_diff1
value: 6.887748742013364
- type: nauc_recall_at_100_max
value: 27.00798435230277
- type: nauc_recall_at_100_std
value: 35.908147807345344
- type: nauc_recall_at_10_diff1
value: 9.605632017480751
- type: nauc_recall_at_10_max
value: 31.845202901168655
- type: nauc_recall_at_10_std
value: 21.497414586634683
- type: nauc_recall_at_1_diff1
value: 19.353069488987916
- type: nauc_recall_at_1_max
value: 17.093914951159693
- type: nauc_recall_at_1_std
value: 8.19886078055046
- type: nauc_recall_at_20_diff1
value: 6.927503731844782
- type: nauc_recall_at_20_max
value: 28.611698183338202
- type: nauc_recall_at_20_std
value: 26.69018660149911
- type: nauc_recall_at_3_diff1
value: 14.043724087062268
- type: nauc_recall_at_3_max
value: 29.269835821380465
- type: nauc_recall_at_3_std
value: 14.104419605998094
- type: nauc_recall_at_5_diff1
value: 11.017319452873336
- type: nauc_recall_at_5_max
value: 30.295720628306228
- type: nauc_recall_at_5_std
value: 17.758048545573825
- type: ndcg_at_1
value: 28.999999999999996
- type: ndcg_at_10
value: 25.041999999999998
- type: ndcg_at_100
value: 35.045
- type: ndcg_at_1000
value: 40.803
- type: ndcg_at_20
value: 28.584
- type: ndcg_at_3
value: 23.249
- type: ndcg_at_5
value: 20.533
- type: precision_at_1
value: 28.999999999999996
- type: precision_at_10
value: 13.120000000000001
- type: precision_at_100
value: 2.7470000000000003
- type: precision_at_1000
value: 0.41200000000000003
- type: precision_at_20
value: 8.584999999999999
- type: precision_at_3
value: 21.633
- type: precision_at_5
value: 18.099999999999998
- type: recall_at_1
value: 5.893000000000001
- type: recall_at_10
value: 26.567
- type: recall_at_100
value: 55.800000000000004
- type: recall_at_1000
value: 83.608
- type: recall_at_20
value: 34.86
- type: recall_at_3
value: 13.153
- type: recall_at_5
value: 18.323
task:
type: Retrieval
- dataset:
config: default
name: MTEB SICK-R
revision: 20a6d6f312dd54037fe07a32d58e5e168867909d
split: test
type: mteb/sickr-sts
metrics:
- type: cosine_pearson
value: 86.57284584320382
- type: cosine_spearman
value: 82.20531642680812
- type: euclidean_pearson
value: 83.94261758556554
- type: euclidean_spearman
value: 82.20721497738559
- type: main_score
value: 82.20531642680812
- type: manhattan_pearson
value: 84.15902154703083
- type: manhattan_spearman
value: 82.19506027155957
- type: pearson
value: 86.57284584320382
- type: spearman
value: 82.20531642680812
task:
type: STS
- dataset:
config: default
name: MTEB STS12
revision: a0d554a64d88156834ff5ae9920b964011b16384
split: test
type: mteb/sts12-sts
metrics:
- type: cosine_pearson
value: 86.28047602146931
- type: cosine_spearman
value: 79.51504881448884
- type: euclidean_pearson
value: 83.10545189967856
- type: euclidean_spearman
value: 79.50586960492797
- type: main_score
value: 79.51504881448884
- type: manhattan_pearson
value: 83.44244457500889
- type: manhattan_spearman
value: 79.730303339846
- type: pearson
value: 86.28047602146931
- type: spearman
value: 79.51504881448884
task:
type: STS
- dataset:
config: default
name: MTEB STS13
revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca
split: test
type: mteb/sts13-sts
metrics:
- type: cosine_pearson
value: 88.74723553048702
- type: cosine_spearman
value: 89.18936052329725
- type: euclidean_pearson
value: 88.90400878928668
- type: euclidean_spearman
value: 89.19174821431281
- type: main_score
value: 89.18936052329725
- type: manhattan_pearson
value: 88.81504628424054
- type: manhattan_spearman
value: 89.18063294142597
- type: pearson
value: 88.74723553048702
- type: spearman
value: 89.18936052329725
task:
type: STS
- dataset:
config: default
name: MTEB STS14
revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375
split: test
type: mteb/sts14-sts
metrics:
- type: cosine_pearson
value: 86.45403437836023
- type: cosine_spearman
value: 85.14654611519086
- type: euclidean_pearson
value: 85.87509624462743
- type: euclidean_spearman
value: 85.1391108856681
- type: main_score
value: 85.14654611519086
- type: manhattan_pearson
value: 85.96635794953866
- type: manhattan_spearman
value: 85.3271371527667
- type: pearson
value: 86.45403437836023
- type: spearman
value: 85.14654611519086
task:
type: STS
- dataset:
config: default
name: MTEB STS15
revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3
split: test
type: mteb/sts15-sts
metrics:
- type: cosine_pearson
value: 87.84742260009705
- type: cosine_spearman
value: 89.10215217191254
- type: euclidean_pearson
value: 88.97393286325477
- type: euclidean_spearman
value: 89.1014105509662
- type: main_score
value: 89.10215217191254
- type: manhattan_pearson
value: 89.31698781090151
- type: manhattan_spearman
value: 89.53000001764433
- type: pearson
value: 87.84742260009705
- type: spearman
value: 89.10215217191254
task:
type: STS
- dataset:
config: default
name: MTEB STS16
revision: 4d8694f8f0e0100860b497b999b3dbed754a0513
split: test
type: mteb/sts16-sts
metrics:
- type: cosine_pearson
value: 85.22397535461835
- type: cosine_spearman
value: 87.14066355879785
- type: euclidean_pearson
value: 86.31393364087295
- type: euclidean_spearman
value: 87.14018892702765
- type: main_score
value: 87.14066355879785
- type: manhattan_pearson
value: 86.36366855248434
- type: manhattan_spearman
value: 87.20858630423012
- type: pearson
value: 85.22397535461835
- type: spearman
value: 87.14066355879785
task:
type: STS
- dataset:
config: en-en
name: MTEB STS17 (en-en)
revision: faeb762787bd10488a50c8b5be4a3b82e411949c
split: test
type: mteb/sts17-crosslingual-sts
metrics:
- type: cosine_pearson
value: 90.66131612061355
- type: cosine_spearman
value: 90.97082650129164
- type: euclidean_pearson
value: 90.98181906744969
- type: euclidean_spearman
value: 90.99008476850047
- type: main_score
value: 90.97082650129164
- type: manhattan_pearson
value: 90.75245040709021
- type: manhattan_spearman
value: 90.6199877691265
- type: pearson
value: 90.66131612061355
- type: spearman
value: 90.97082650129164
task:
type: STS
- dataset:
config: en
name: MTEB STS22 (en)
revision: de9d86b3b84231dc21f76c7b7af1f28e2f57f6e3
split: test
type: mteb/sts22-crosslingual-sts
metrics:
- type: cosine_pearson
value: 67.270656447085
- type: cosine_spearman
value: 67.82870469746828
- type: euclidean_pearson
value: 69.03857775285664
- type: euclidean_spearman
value: 67.74455108773341
- type: main_score
value: 67.82870469746828
- type: manhattan_pearson
value: 69.25304172245812
- type: manhattan_spearman
value: 68.00987097916055
- type: pearson
value: 67.270656447085
- type: spearman
value: 67.82870469746828
task:
type: STS
- dataset:
config: default
name: MTEB STSBenchmark
revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831
split: test
type: mteb/stsbenchmark-sts
metrics:
- type: cosine_pearson
value: 87.17245205384889
- type: cosine_spearman
value: 87.7360146030987
- type: euclidean_pearson
value: 87.48919412794656
- type: euclidean_spearman
value: 87.7312047878383
- type: main_score
value: 87.7360146030987
- type: manhattan_pearson
value: 87.61476224354806
- type: manhattan_spearman
value: 87.95220889254693
- type: pearson
value: 87.17245205384889
- type: spearman
value: 87.7360146030987
task:
type: STS
- dataset:
config: default
name: MTEB SciDocsRR
revision: d3c5e1fc0b855ab6097bf1cda04dd73947d7caab
split: test
type: mteb/scidocs-reranking
metrics:
- type: main_score
value: 88.43547871921146
- type: map
value: 88.43547871921146
- type: mrr
value: 96.5564473652709
- type: nAUC_map_diff1
value: -13.66029392579231
- type: nAUC_map_max
value: 50.325613574053506
- type: nAUC_map_std
value: 60.02986231275796
- type: nAUC_mrr_diff1
value: 23.83821476411125
- type: nAUC_mrr_max
value: 86.72643311769906
- type: nAUC_mrr_std
value: 72.12741063469213
task:
type: Reranking
- dataset:
config: default
name: MTEB SciFact
revision: 0228b52cf27578f30900b9e5271d331663a030d7
split: test
type: mteb/scifact
metrics:
- type: main_score
value: 78.233
- type: map_at_1
value: 61.49400000000001
- type: map_at_10
value: 73.30600000000001
- type: map_at_100
value: 73.719
- type: map_at_1000
value: 73.724
- type: map_at_20
value: 73.611
- type: map_at_3
value: 70.626
- type: map_at_5
value: 72.417
- type: mrr_at_1
value: 64.66666666666666
- type: mrr_at_10
value: 74.30357142857143
- type: mrr_at_100
value: 74.56950898079988
- type: mrr_at_1000
value: 74.57295833098681
- type: mrr_at_20
value: 74.46165223665226
- type: mrr_at_3
value: 72.3888888888889
- type: mrr_at_5
value: 73.60555555555557
- type: nauc_map_at_1000_diff1
value: 76.51524604780636
- type: nauc_map_at_1000_max
value: 53.48521938401881
- type: nauc_map_at_1000_std
value: -7.347799382158861
- type: nauc_map_at_100_diff1
value: 76.5122888096236
- type: nauc_map_at_100_max
value: 53.49221847471618
- type: nauc_map_at_100_std
value: -7.329683735681086
- type: nauc_map_at_10_diff1
value: 76.30928630674504
- type: nauc_map_at_10_max
value: 53.00102977185941
- type: nauc_map_at_10_std
value: -7.7467740085108705
- type: nauc_map_at_1_diff1
value: 79.54189281784247
- type: nauc_map_at_1_max
value: 46.630071622109526
- type: nauc_map_at_1_std
value: -14.395943134644112
- type: nauc_map_at_20_diff1
value: 76.41604361947962
- type: nauc_map_at_20_max
value: 53.578883876146875
- type: nauc_map_at_20_std
value: -7.403103451288041
- type: nauc_map_at_3_diff1
value: 76.25911617571941
- type: nauc_map_at_3_max
value: 49.140287380513605
- type: nauc_map_at_3_std
value: -11.35992449218983
- type: nauc_map_at_5_diff1
value: 76.35122077770336
- type: nauc_map_at_5_max
value: 52.1744367901208
- type: nauc_map_at_5_std
value: -7.85753955055384
- type: nauc_mrr_at_1000_diff1
value: 76.97223309515867
- type: nauc_mrr_at_1000_max
value: 57.263787498613326
- type: nauc_mrr_at_1000_std
value: -4.884090708840035
- type: nauc_mrr_at_100_diff1
value: 76.97312970894603
- type: nauc_mrr_at_100_max
value: 57.26850730446478
- type: nauc_mrr_at_100_std
value: -4.875200894216617
- type: nauc_mrr_at_10_diff1
value: 76.65927674223613
- type: nauc_mrr_at_10_max
value: 57.30979763941454
- type: nauc_mrr_at_10_std
value: -4.863331094022142
- type: nauc_mrr_at_1_diff1
value: 80.0454932568644
- type: nauc_mrr_at_1_max
value: 56.76038421319305
- type: nauc_mrr_at_1_std
value: -4.101939392632653
- type: nauc_mrr_at_20_diff1
value: 76.87237970440503
- type: nauc_mrr_at_20_max
value: 57.33843605225869
- type: nauc_mrr_at_20_std
value: -4.96248984417978
- type: nauc_mrr_at_3_diff1
value: 76.74130186666727
- type: nauc_mrr_at_3_max
value: 56.19313244846155
- type: nauc_mrr_at_3_std
value: -5.684365934009136
- type: nauc_mrr_at_5_diff1
value: 76.66406918799962
- type: nauc_mrr_at_5_max
value: 57.56110093228628
- type: nauc_mrr_at_5_std
value: -3.7464413085588073
- type: nauc_ndcg_at_1000_diff1
value: 76.19194173971773
- type: nauc_ndcg_at_1000_max
value: 55.57464600170693
- type: nauc_ndcg_at_1000_std
value: -6.0761689532372625
- type: nauc_ndcg_at_100_diff1
value: 76.14631273843654
- type: nauc_ndcg_at_100_max
value: 55.72246565373382
- type: nauc_ndcg_at_100_std
value: -5.595160698860595
- type: nauc_ndcg_at_10_diff1
value: 75.0108223611192
- type: nauc_ndcg_at_10_max
value: 55.27894212877493
- type: nauc_ndcg_at_10_std
value: -6.968331740214591
- type: nauc_ndcg_at_1_diff1
value: 80.0454932568644
- type: nauc_ndcg_at_1_max
value: 56.76038421319305
- type: nauc_ndcg_at_1_std
value: -4.101939392632653
- type: nauc_ndcg_at_20_diff1
value: 75.54887755702472
- type: nauc_ndcg_at_20_max
value: 56.406879417251496
- type: nauc_ndcg_at_20_std
value: -6.495231061329629
- type: nauc_ndcg_at_3_diff1
value: 75.03620356688509
- type: nauc_ndcg_at_3_max
value: 52.147381077773424
- type: nauc_ndcg_at_3_std
value: -8.448005688956199
- type: nauc_ndcg_at_5_diff1
value: 75.1195898074229
- type: nauc_ndcg_at_5_max
value: 54.2321033861173
- type: nauc_ndcg_at_5_std
value: -5.882690780895338
- type: nauc_precision_at_1000_diff1
value: -28.081979732100532
- type: nauc_precision_at_1000_max
value: 35.055348014832916
- type: nauc_precision_at_1000_std
value: 59.61280468927384
- type: nauc_precision_at_100_diff1
value: -25.112740730587458
- type: nauc_precision_at_100_max
value: 38.26331300116496
- type: nauc_precision_at_100_std
value: 62.46316222328831
- type: nauc_precision_at_10_diff1
value: -2.6766206473658833
- type: nauc_precision_at_10_max
value: 45.95321867204845
- type: nauc_precision_at_10_std
value: 45.07212468670564
- type: nauc_precision_at_1_diff1
value: 80.0454932568644
- type: nauc_precision_at_1_max
value: 56.76038421319305
- type: nauc_precision_at_1_std
value: -4.101939392632653
- type: nauc_precision_at_20_diff1
value: -10.698911116738385
- type: nauc_precision_at_20_max
value: 43.467275950182994
- type: nauc_precision_at_20_std
value: 48.00467321991766
- type: nauc_precision_at_3_diff1
value: 33.6344708541193
- type: nauc_precision_at_3_max
value: 49.309242331670504
- type: nauc_precision_at_3_std
value: 21.02940391379915
- type: nauc_precision_at_5_diff1
value: 13.560415600596318
- type: nauc_precision_at_5_max
value: 48.918726500100085
- type: nauc_precision_at_5_std
value: 39.940930429172184
- type: nauc_recall_at_1000_diff1
value: .nan
- type: nauc_recall_at_1000_max
value: .nan
- type: nauc_recall_at_1000_std
value: .nan
- type: nauc_recall_at_100_diff1
value: 70.82166199813196
- type: nauc_recall_at_100_max
value: 76.6106442577042
- type: nauc_recall_at_100_std
value: 66.47992530345513
- type: nauc_recall_at_10_diff1
value: 62.68908885556092
- type: nauc_recall_at_10_max
value: 58.14262437741839
- type: nauc_recall_at_10_std
value: -12.946717875063369
- type: nauc_recall_at_1_diff1
value: 79.54189281784247
- type: nauc_recall_at_1_max
value: 46.630071622109526
- type: nauc_recall_at_1_std
value: -14.395943134644112
- type: nauc_recall_at_20_diff1
value: 65.79470497876567
- type: nauc_recall_at_20_max
value: 71.68308183488456
- type: nauc_recall_at_20_std
value: -12.556850697268453
- type: nauc_recall_at_3_diff1
value: 68.3240211318129
- type: nauc_recall_at_3_max
value: 45.05998217275036
- type: nauc_recall_at_3_std
value: -14.23179772593869
- type: nauc_recall_at_5_diff1
value: 67.53366869904056
- type: nauc_recall_at_5_max
value: 53.57935627081027
- type: nauc_recall_at_5_std
value: -3.3271112904853393
- type: ndcg_at_1
value: 64.667
- type: ndcg_at_10
value: 78.233
- type: ndcg_at_100
value: 79.806
- type: ndcg_at_1000
value: 79.92099999999999
- type: ndcg_at_20
value: 79.006
- type: ndcg_at_3
value: 74.018
- type: ndcg_at_5
value: 76.334
- type: precision_at_1
value: 64.667
- type: precision_at_10
value: 10.4
- type: precision_at_100
value: 1.1199999999999999
- type: precision_at_1000
value: 0.11299999999999999
- type: precision_at_20
value: 5.383
- type: precision_at_3
value: 29.444
- type: precision_at_5
value: 19.467000000000002
- type: recall_at_1
value: 61.49400000000001
- type: recall_at_10
value: 92.156
- type: recall_at_100
value: 99.167
- type: recall_at_1000
value: 100.0
- type: recall_at_20
value: 94.833
- type: recall_at_3
value: 80.833
- type: recall_at_5
value: 86.6
task:
type: Retrieval
- dataset:
config: default
name: MTEB SprintDuplicateQuestions
revision: d66bd1f72af766a5cc4b0ca5e00c162f89e8cc46
split: test
type: mteb/sprintduplicatequestions-pairclassification
metrics:
- type: cosine_accuracy
value: 99.8039603960396
- type: cosine_accuracy_threshold
value: 84.54211950302124
- type: cosine_ap
value: 95.59056372734358
- type: cosine_f1
value: 90.1394422310757
- type: cosine_f1_threshold
value: 84.54211950302124
- type: cosine_precision
value: 89.78174603174604
- type: cosine_recall
value: 90.5
- type: dot_accuracy
value: 99.80594059405941
- type: dot_accuracy_threshold
value: 85.57180166244507
- type: dot_ap
value: 95.53453431914399
- type: dot_f1
value: 90.10442565887618
- type: dot_f1_threshold
value: 84.59715843200684
- type: dot_precision
value: 89.61424332344214
- type: dot_recall
value: 90.60000000000001
- type: euclidean_accuracy
value: 99.8039603960396
- type: euclidean_accuracy_threshold
value: 53.253382444381714
- type: euclidean_ap
value: 95.5850992402159
- type: euclidean_f1
value: 90.09457441513192
- type: euclidean_f1_threshold
value: 55.725520849227905
- type: euclidean_precision
value: 89.69276511397423
- type: euclidean_recall
value: 90.5
- type: main_score
value: 95.7485189884476
- type: manhattan_accuracy
value: 99.81485148514851
- type: manhattan_accuracy_threshold
value: 3491.29638671875
- type: manhattan_ap
value: 95.7485189884476
- type: manhattan_f1
value: 90.464048954615
- type: manhattan_f1_threshold
value: 3491.29638671875
- type: manhattan_precision
value: 92.2996878251821
- type: manhattan_recall
value: 88.7
- type: max_ap
value: 95.7485189884476
- type: max_f1
value: 90.464048954615
- type: max_precision
value: 92.2996878251821
- type: max_recall
value: 90.60000000000001
- type: similarity_accuracy
value: 99.8039603960396
- type: similarity_accuracy_threshold
value: 84.54211950302124
- type: similarity_ap
value: 95.59056372734358
- type: similarity_f1
value: 90.1394422310757
- type: similarity_f1_threshold
value: 84.54211950302124
- type: similarity_precision
value: 89.78174603174604
- type: similarity_recall
value: 90.5
task:
type: PairClassification
- dataset:
config: default
name: MTEB StackExchangeClustering
revision: 6cbc1f7b2bc0622f2e39d2c77fa502909748c259
split: test
type: mteb/stackexchange-clustering
metrics:
- type: main_score
value: 78.49205191950675
- type: v_measure
value: 78.49205191950675
- type: v_measure_std
value: 2.84869550699959
task:
type: Clustering
- dataset:
config: default
name: MTEB StackExchangeClusteringP2P
revision: 815ca46b2622cec33ccafc3735d572c266efdb44
split: test
type: mteb/stackexchange-clustering-p2p
metrics:
- type: main_score
value: 48.90421736513028
- type: v_measure
value: 48.90421736513028
- type: v_measure_std
value: 1.6875865714471023
task:
type: Clustering
- dataset:
config: default
name: MTEB StackOverflowDupQuestions
revision: e185fbe320c72810689fc5848eb6114e1ef5ec69
split: test
type: mteb/stackoverflowdupquestions-reranking
metrics:
- type: main_score
value: 52.9874730481696
- type: map
value: 52.9874730481696
- type: mrr
value: 53.85867604617604
- type: nAUC_map_diff1
value: 39.633429293407616
- type: nAUC_map_max
value: 10.236807988858546
- type: nAUC_map_std
value: 10.276522217929674
- type: nAUC_mrr_diff1
value: 40.0543079218377
- type: nAUC_mrr_max
value: 10.96209807382042
- type: nAUC_mrr_std
value: 10.524400196109918
task:
type: Reranking
- dataset:
config: default
name: MTEB SummEval
revision: cda12ad7615edc362dbf25a00fdd61d3b1eaf93c
split: test
type: mteb/summeval
metrics:
- type: cosine_pearson
value: 30.727801109114232
- type: cosine_spearman
value: 31.66058223980157
- type: dot_pearson
value: 30.78818248622866
- type: dot_spearman
value: 31.525158776890265
- type: main_score
value: 31.66058223980157
- type: pearson
value: 30.727801109114232
- type: spearman
value: 31.66058223980157
task:
type: Summarization
- dataset:
config: default
name: MTEB TRECCOVID
revision: bb9466bac8153a0349341eb1b22e06409e78ef4e
split: test
type: mteb/trec-covid
metrics:
- type: main_score
value: 85.206
- type: map_at_1
value: 0.246
- type: map_at_10
value: 2.1950000000000003
- type: map_at_100
value: 14.179
- type: map_at_1000
value: 35.037
- type: map_at_20
value: 4.143
- type: map_at_3
value: 0.7100000000000001
- type: map_at_5
value: 1.135
- type: mrr_at_1
value: 94.0
- type: mrr_at_10
value: 96.66666666666666
- type: mrr_at_100
value: 96.66666666666666
- type: mrr_at_1000
value: 96.66666666666666
- type: mrr_at_20
value: 96.66666666666666
- type: mrr_at_3
value: 96.66666666666666
- type: mrr_at_5
value: 96.66666666666666
- type: nauc_map_at_1000_diff1
value: -4.6264497624527525
- type: nauc_map_at_1000_max
value: 44.594457564749355
- type: nauc_map_at_1000_std
value: 73.17642341400133
- type: nauc_map_at_100_diff1
value: 23.451335157405726
- type: nauc_map_at_100_max
value: 25.426398857299525
- type: nauc_map_at_100_std
value: 64.07416694472633
- type: nauc_map_at_10_diff1
value: 46.57568738568346
- type: nauc_map_at_10_max
value: 9.693233249079238
- type: nauc_map_at_10_std
value: 28.549530265164357
- type: nauc_map_at_1_diff1
value: 53.48238396620123
- type: nauc_map_at_1_max
value: 0.33476619393733076
- type: nauc_map_at_1_std
value: 8.906362219128463
- type: nauc_map_at_20_diff1
value: 39.40719602207749
- type: nauc_map_at_20_max
value: 9.635915072074045
- type: nauc_map_at_20_std
value: 35.15634791346394
- type: nauc_map_at_3_diff1
value: 53.11784737840137
- type: nauc_map_at_3_max
value: 3.059682761072153
- type: nauc_map_at_3_std
value: 21.310633086556617
- type: nauc_map_at_5_diff1
value: 49.91570701185436
- type: nauc_map_at_5_max
value: 8.045082896244576
- type: nauc_map_at_5_std
value: 20.597686235051647
- type: nauc_mrr_at_1000_diff1
value: 41.98412698412726
- type: nauc_mrr_at_1000_max
value: 78.24463118580779
- type: nauc_mrr_at_1000_std
value: 0.30812324930028195
- type: nauc_mrr_at_100_diff1
value: 41.98412698412726
- type: nauc_mrr_at_100_max
value: 78.24463118580779
- type: nauc_mrr_at_100_std
value: 0.30812324930028195
- type: nauc_mrr_at_10_diff1
value: 41.98412698412726
- type: nauc_mrr_at_10_max
value: 78.24463118580779
- type: nauc_mrr_at_10_std
value: 0.30812324930028195
- type: nauc_mrr_at_1_diff1
value: 38.62433862433873
- type: nauc_mrr_at_1_max
value: 80.78120136943666
- type: nauc_mrr_at_1_std
value: -10.768751945222197
- type: nauc_mrr_at_20_diff1
value: 41.98412698412726
- type: nauc_mrr_at_20_max
value: 78.24463118580779
- type: nauc_mrr_at_20_std
value: 0.30812324930028195
- type: nauc_mrr_at_3_diff1
value: 41.98412698412726
- type: nauc_mrr_at_3_max
value: 78.24463118580779
- type: nauc_mrr_at_3_std
value: 0.30812324930028195
- type: nauc_mrr_at_5_diff1
value: 41.98412698412726
- type: nauc_mrr_at_5_max
value: 78.24463118580779
- type: nauc_mrr_at_5_std
value: 0.30812324930028195
- type: nauc_ndcg_at_1000_diff1
value: 0.5174948602880207
- type: nauc_ndcg_at_1000_max
value: 48.60686602077053
- type: nauc_ndcg_at_1000_std
value: 75.72456343175277
- type: nauc_ndcg_at_100_diff1
value: -20.747252137999254
- type: nauc_ndcg_at_100_max
value: 49.985132618254994
- type: nauc_ndcg_at_100_std
value: 61.096383293836574
- type: nauc_ndcg_at_10_diff1
value: 6.791377920463332
- type: nauc_ndcg_at_10_max
value: 57.50019332833286
- type: nauc_ndcg_at_10_std
value: 49.201028841219426
- type: nauc_ndcg_at_1_diff1
value: 54.92683440362145
- type: nauc_ndcg_at_1_max
value: 83.8667228129276
- type: nauc_ndcg_at_1_std
value: 1.6738604063586122
- type: nauc_ndcg_at_20_diff1
value: -5.1948699196314925
- type: nauc_ndcg_at_20_max
value: 54.483087684806556
- type: nauc_ndcg_at_20_std
value: 50.54823818118781
- type: nauc_ndcg_at_3_diff1
value: 26.267246500164372
- type: nauc_ndcg_at_3_max
value: 63.0173212926611
- type: nauc_ndcg_at_3_std
value: 41.025597406368256
- type: nauc_ndcg_at_5_diff1
value: 16.910185454343036
- type: nauc_ndcg_at_5_max
value: 60.9328683868778
- type: nauc_ndcg_at_5_std
value: 36.70169905857712
- type: nauc_precision_at_1000_diff1
value: -46.374447765983525
- type: nauc_precision_at_1000_max
value: 35.36052337813863
- type: nauc_precision_at_1000_std
value: 14.219220668161018
- type: nauc_precision_at_100_diff1
value: -29.7838083657744
- type: nauc_precision_at_100_max
value: 43.93589400385112
- type: nauc_precision_at_100_std
value: 55.425045718579945
- type: nauc_precision_at_10_diff1
value: -12.016613405227687
- type: nauc_precision_at_10_max
value: 57.79924427743131
- type: nauc_precision_at_10_std
value: 49.022036703550675
- type: nauc_precision_at_1_diff1
value: 38.62433862433873
- type: nauc_precision_at_1_max
value: 80.78120136943666
- type: nauc_precision_at_1_std
value: -10.768751945222197
- type: nauc_precision_at_20_diff1
value: -23.95633847880195
- type: nauc_precision_at_20_max
value: 48.34715917258276
- type: nauc_precision_at_20_std
value: 48.82198285255887
- type: nauc_precision_at_3_diff1
value: 6.871296905858807
- type: nauc_precision_at_3_max
value: 70.54805793285054
- type: nauc_precision_at_3_std
value: 44.65108624094803
- type: nauc_precision_at_5_diff1
value: -9.074932448759695
- type: nauc_precision_at_5_max
value: 67.41284242437573
- type: nauc_precision_at_5_std
value: 23.876891983919577
- type: nauc_recall_at_1000_diff1
value: 8.142288830293255
- type: nauc_recall_at_1000_max
value: 38.85182826835104
- type: nauc_recall_at_1000_std
value: 68.60783819217335
- type: nauc_recall_at_100_diff1
value: 34.262914076287466
- type: nauc_recall_at_100_max
value: 12.87009658528838
- type: nauc_recall_at_100_std
value: 56.21330603762995
- type: nauc_recall_at_10_diff1
value: 49.33830945338758
- type: nauc_recall_at_10_max
value: 0.3539875530671406
- type: nauc_recall_at_10_std
value: 26.85864465557644
- type: nauc_recall_at_1_diff1
value: 53.48238396620123
- type: nauc_recall_at_1_max
value: 0.33476619393733076
- type: nauc_recall_at_1_std
value: 8.906362219128463
- type: nauc_recall_at_20_diff1
value: 44.21928181266254
- type: nauc_recall_at_20_max
value: -0.9198356057088594
- type: nauc_recall_at_20_std
value: 31.484376992896784
- type: nauc_recall_at_3_diff1
value: 53.038093080990876
- type: nauc_recall_at_3_max
value: -1.4170895916973003
- type: nauc_recall_at_3_std
value: 21.890202855574497
- type: nauc_recall_at_5_diff1
value: 49.39742214825278
- type: nauc_recall_at_5_max
value: 2.8412267611894517
- type: nauc_recall_at_5_std
value: 18.01598921859512
- type: ndcg_at_1
value: 91.0
- type: ndcg_at_10
value: 85.206
- type: ndcg_at_100
value: 67.29
- type: ndcg_at_1000
value: 60.584
- type: ndcg_at_20
value: 82.321
- type: ndcg_at_3
value: 88.642
- type: ndcg_at_5
value: 87.063
- type: precision_at_1
value: 94.0
- type: precision_at_10
value: 89.8
- type: precision_at_100
value: 69.78
- type: precision_at_1000
value: 26.738
- type: precision_at_20
value: 87.2
- type: precision_at_3
value: 92.0
- type: precision_at_5
value: 90.8
- type: recall_at_1
value: 0.246
- type: recall_at_10
value: 2.344
- type: recall_at_100
value: 16.962
- type: recall_at_1000
value: 57.325
- type: recall_at_20
value: 4.517
- type: recall_at_3
value: 0.731
- type: recall_at_5
value: 1.1780000000000002
task:
type: Retrieval
- dataset:
config: default
name: MTEB Touche2020
revision: a34f9a33db75fa0cbb21bb5cfc3dae8dc8bec93f
split: test
type: mteb/touche2020
metrics:
- type: main_score
value: 31.455
- type: map_at_1
value: 2.9739999999999998
- type: map_at_10
value: 12.183
- type: map_at_100
value: 18.772
- type: map_at_1000
value: 20.415
- type: map_at_20
value: 14.451
- type: map_at_3
value: 6.507000000000001
- type: map_at_5
value: 8.66
- type: mrr_at_1
value: 40.816326530612244
- type: mrr_at_10
value: 57.70975056689341
- type: mrr_at_100
value: 58.18379126542391
- type: mrr_at_1000
value: 58.18379126542391
- type: mrr_at_20
value: 57.85552316164561
- type: mrr_at_3
value: 54.08163265306123
- type: mrr_at_5
value: 56.42857142857143
- type: nauc_map_at_1000_diff1
value: 3.1567471051481437
- type: nauc_map_at_1000_max
value: -1.5882060729791523
- type: nauc_map_at_1000_std
value: 18.69622198722074
- type: nauc_map_at_100_diff1
value: 3.3449677678147536
- type: nauc_map_at_100_max
value: -2.8928606866168405
- type: nauc_map_at_100_std
value: 15.789984947653412
- type: nauc_map_at_10_diff1
value: 2.9696743570444264
- type: nauc_map_at_10_max
value: -9.096749212011876
- type: nauc_map_at_10_std
value: -5.38545817258353
- type: nauc_map_at_1_diff1
value: 20.680780404542546
- type: nauc_map_at_1_max
value: -7.04722927447817
- type: nauc_map_at_1_std
value: -7.062494733973898
- type: nauc_map_at_20_diff1
value: 4.070437790119271
- type: nauc_map_at_20_max
value: -4.84491434686032
- type: nauc_map_at_20_std
value: 0.5846341109021014
- type: nauc_map_at_3_diff1
value: 11.9634978045925
- type: nauc_map_at_3_max
value: -8.27834591046608
- type: nauc_map_at_3_std
value: -8.687615453381065
- type: nauc_map_at_5_diff1
value: 0.9195191526009436
- type: nauc_map_at_5_max
value: -1.673813362719489
- type: nauc_map_at_5_std
value: -6.67549753473631
- type: nauc_mrr_at_1000_diff1
value: 19.877993208719573
- type: nauc_mrr_at_1000_max
value: -10.37776706406218
- type: nauc_mrr_at_1000_std
value: 7.132169578056367
- type: nauc_mrr_at_100_diff1
value: 19.877993208719573
- type: nauc_mrr_at_100_max
value: -10.37776706406218
- type: nauc_mrr_at_100_std
value: 7.132169578056367
- type: nauc_mrr_at_10_diff1
value: 20.414285568401457
- type: nauc_mrr_at_10_max
value: -9.677800295687861
- type: nauc_mrr_at_10_std
value: 8.001103690180859
- type: nauc_mrr_at_1_diff1
value: 22.393284073955723
- type: nauc_mrr_at_1_max
value: -5.889370191243167
- type: nauc_mrr_at_1_std
value: -1.5183536173658247
- type: nauc_mrr_at_20_diff1
value: 20.455564720604055
- type: nauc_mrr_at_20_max
value: -10.230642830103074
- type: nauc_mrr_at_20_std
value: 7.863582453266621
- type: nauc_mrr_at_3_diff1
value: 17.554895390732618
- type: nauc_mrr_at_3_max
value: -15.618463505555052
- type: nauc_mrr_at_3_std
value: 5.913231577966864
- type: nauc_mrr_at_5_diff1
value: 18.393678507779914
- type: nauc_mrr_at_5_max
value: -11.903593353147762
- type: nauc_mrr_at_5_std
value: 7.580745996262831
- type: nauc_ndcg_at_1000_diff1
value: 13.746937095530473
- type: nauc_ndcg_at_1000_max
value: -0.9319249687895838
- type: nauc_ndcg_at_1000_std
value: 38.56328031451904
- type: nauc_ndcg_at_100_diff1
value: 13.854865944415895
- type: nauc_ndcg_at_100_max
value: -7.142142012591404
- type: nauc_ndcg_at_100_std
value: 35.61341954818848
- type: nauc_ndcg_at_10_diff1
value: 9.010144273248759
- type: nauc_ndcg_at_10_max
value: -15.320014897424574
- type: nauc_ndcg_at_10_std
value: 2.84883880489144
- type: nauc_ndcg_at_1_diff1
value: 20.939533945592967
- type: nauc_ndcg_at_1_max
value: -6.387319972188946
- type: nauc_ndcg_at_1_std
value: -0.5258673122126726
- type: nauc_ndcg_at_20_diff1
value: 14.660827309009496
- type: nauc_ndcg_at_20_max
value: -13.476196120145994
- type: nauc_ndcg_at_20_std
value: 8.22391881710838
- type: nauc_ndcg_at_3_diff1
value: 13.429985227235935
- type: nauc_ndcg_at_3_max
value: -14.904544592570247
- type: nauc_ndcg_at_3_std
value: 1.599779998183342
- type: nauc_ndcg_at_5_diff1
value: 8.085466231900622
- type: nauc_ndcg_at_5_max
value: -9.09591969526831
- type: nauc_ndcg_at_5_std
value: 3.5794092637248505
- type: nauc_precision_at_1000_diff1
value: -9.31941215946743
- type: nauc_precision_at_1000_max
value: 31.52913520470716
- type: nauc_precision_at_1000_std
value: 22.720784312185856
- type: nauc_precision_at_100_diff1
value: 8.958548406995279
- type: nauc_precision_at_100_max
value: 15.100597910674104
- type: nauc_precision_at_100_std
value: 71.04548238175113
- type: nauc_precision_at_10_diff1
value: 12.4698194690008
- type: nauc_precision_at_10_max
value: -15.84870544871496
- type: nauc_precision_at_10_std
value: 7.575297622501928
- type: nauc_precision_at_1_diff1
value: 22.393284073955723
- type: nauc_precision_at_1_max
value: -5.889370191243167
- type: nauc_precision_at_1_std
value: -1.5183536173658247
- type: nauc_precision_at_20_diff1
value: 15.393505718138758
- type: nauc_precision_at_20_max
value: -3.70684298539384
- type: nauc_precision_at_20_std
value: 29.426137824970304
- type: nauc_precision_at_3_diff1
value: 9.997768085465394
- type: nauc_precision_at_3_max
value: -17.12224314347674
- type: nauc_precision_at_3_std
value: -1.343018166772313
- type: nauc_precision_at_5_diff1
value: 3.8936997437913554
- type: nauc_precision_at_5_max
value: -5.689104289687632
- type: nauc_precision_at_5_std
value: 3.181098051304285
- type: nauc_recall_at_1000_diff1
value: 9.908303508158387
- type: nauc_recall_at_1000_max
value: 6.174506592699848
- type: nauc_recall_at_1000_std
value: 77.41931114780012
- type: nauc_recall_at_100_diff1
value: 10.286839241876192
- type: nauc_recall_at_100_max
value: -6.6138697026666815
- type: nauc_recall_at_100_std
value: 49.608313692633224
- type: nauc_recall_at_10_diff1
value: 2.215545846659851
- type: nauc_recall_at_10_max
value: -17.83025802478445
- type: nauc_recall_at_10_std
value: -3.3784768673705465
- type: nauc_recall_at_1_diff1
value: 20.680780404542546
- type: nauc_recall_at_1_max
value: -7.04722927447817
- type: nauc_recall_at_1_std
value: -7.062494733973898
- type: nauc_recall_at_20_diff1
value: 6.974410239251615
- type: nauc_recall_at_20_max
value: -14.161147924731646
- type: nauc_recall_at_20_std
value: 9.328412057721454
- type: nauc_recall_at_3_diff1
value: 7.904589805754212
- type: nauc_recall_at_3_max
value: -12.1912388648593
- type: nauc_recall_at_3_std
value: -9.221542013385555
- type: nauc_recall_at_5_diff1
value: -3.2604132752706914
- type: nauc_recall_at_5_max
value: -6.886351441658915
- type: nauc_recall_at_5_std
value: -7.014252851712789
- type: ndcg_at_1
value: 39.796
- type: ndcg_at_10
value: 31.455
- type: ndcg_at_100
value: 42.388999999999996
- type: ndcg_at_1000
value: 53.556000000000004
- type: ndcg_at_20
value: 30.808000000000003
- type: ndcg_at_3
value: 35.831
- type: ndcg_at_5
value: 32.845
- type: precision_at_1
value: 40.816
- type: precision_at_10
value: 27.143
- type: precision_at_100
value: 8.449
- type: precision_at_1000
value: 1.6179999999999999
- type: precision_at_20
value: 19.387999999999998
- type: precision_at_3
value: 35.374
- type: precision_at_5
value: 31.019999999999996
- type: recall_at_1
value: 2.9739999999999998
- type: recall_at_10
value: 19.39
- type: recall_at_100
value: 51.636
- type: recall_at_1000
value: 86.99900000000001
- type: recall_at_20
value: 26.478
- type: recall_at_3
value: 7.703
- type: recall_at_5
value: 11.42
task:
type: Retrieval
- dataset:
config: default
name: MTEB ToxicConversationsClassification
revision: edfaf9da55d3dd50d43143d90c1ac476895ae6de
split: test
type: mteb/toxic_conversations_50k
metrics:
- type: accuracy
value: 86.9384765625
- type: ap
value: 31.737513704141552
- type: ap_weighted
value: 31.737513704141552
- type: f1
value: 71.5490757306975
- type: f1_weighted
value: 89.14632533489856
- type: main_score
value: 86.9384765625
task:
type: Classification
- dataset:
config: default
name: MTEB TweetSentimentExtractionClassification
revision: d604517c81ca91fe16a244d1248fc021f9ecee7a
split: test
type: mteb/tweet_sentiment_extraction
metrics:
- type: accuracy
value: 73.57668364459535
- type: f1
value: 73.90467103648074
- type: f1_weighted
value: 73.42158415034704
- type: main_score
value: 73.57668364459535
task:
type: Classification
- dataset:
config: default
name: MTEB TwentyNewsgroupsClustering
revision: 6125ec4e24fa026cec8a478383ee943acfbd5449
split: test
type: mteb/twentynewsgroups-clustering
metrics:
- type: main_score
value: 58.574148097494685
- type: v_measure
value: 58.574148097494685
- type: v_measure_std
value: 0.9443161637490822
task:
type: Clustering
- dataset:
config: default
name: MTEB TwitterSemEval2015
revision: 70970daeab8776df92f5ea462b6173c0b46fd2d1
split: test
type: mteb/twittersemeval2015-pairclassification
metrics:
- type: cosine_accuracy
value: 88.1385229778864
- type: cosine_accuracy_threshold
value: 83.86307954788208
- type: cosine_ap
value: 80.17965893449055
- type: cosine_f1
value: 73.0614300100705
- type: cosine_f1_threshold
value: 80.7942807674408
- type: cosine_precision
value: 69.8603755416466
- type: cosine_recall
value: 76.56992084432717
- type: dot_accuracy
value: 88.2100494724921
- type: dot_accuracy_threshold
value: 83.84793996810913
- type: dot_ap
value: 80.18603932881858
- type: dot_f1
value: 73.07643714466204
- type: dot_f1_threshold
value: 80.87586164474487
- type: dot_precision
value: 70.10909090909091
- type: dot_recall
value: 76.3060686015831
- type: euclidean_accuracy
value: 88.1385229778864
- type: euclidean_accuracy_threshold
value: 56.77661895751953
- type: euclidean_ap
value: 80.1784070881624
- type: euclidean_f1
value: 73.04830369529574
- type: euclidean_f1_threshold
value: 61.91838979721069
- type: euclidean_precision
value: 69.96859144720948
- type: euclidean_recall
value: 76.41160949868075
- type: main_score
value: 80.18603932881858
- type: manhattan_accuracy
value: 88.0431543184121
- type: manhattan_accuracy_threshold
value: 3755.6137084960938
- type: manhattan_ap
value: 79.98270453664578
- type: manhattan_f1
value: 72.68242015061023
- type: manhattan_f1_threshold
value: 3892.494583129883
- type: manhattan_precision
value: 71.54907975460122
- type: manhattan_recall
value: 73.85224274406332
- type: max_ap
value: 80.18603932881858
- type: max_f1
value: 73.07643714466204
- type: max_precision
value: 71.54907975460122
- type: max_recall
value: 76.56992084432717
- type: similarity_accuracy
value: 88.1385229778864
- type: similarity_accuracy_threshold
value: 83.86307954788208
- type: similarity_ap
value: 80.17965893449055
- type: similarity_f1
value: 73.0614300100705
- type: similarity_f1_threshold
value: 80.7942807674408
- type: similarity_precision
value: 69.8603755416466
- type: similarity_recall
value: 76.56992084432717
task:
type: PairClassification
- dataset:
config: default
name: MTEB TwitterURLCorpus
revision: 8b6510b0b1fa4e4c4f879467980e9be563ec1cdf
split: test
type: mteb/twitterurlcorpus-pairclassification
metrics:
- type: cosine_accuracy
value: 89.7892653393876
- type: cosine_accuracy_threshold
value: 79.69566583633423
- type: cosine_ap
value: 87.4579867302024
- type: cosine_f1
value: 79.91620843152658
- type: cosine_f1_threshold
value: 78.53609323501587
- type: cosine_precision
value: 77.7155329210622
- type: cosine_recall
value: 82.24514936864799
- type: dot_accuracy
value: 89.78732487289945
- type: dot_accuracy_threshold
value: 80.05315661430359
- type: dot_ap
value: 87.44916182456272
- type: dot_f1
value: 79.90419878751591
- type: dot_f1_threshold
value: 78.57890725135803
- type: dot_precision
value: 77.73409057812728
- type: dot_recall
value: 82.19895287958116
- type: euclidean_accuracy
value: 89.78538440641131
- type: euclidean_accuracy_threshold
value: 62.29925751686096
- type: euclidean_ap
value: 87.45904868911386
- type: euclidean_f1
value: 79.93127404474657
- type: euclidean_f1_threshold
value: 65.61101078987122
- type: euclidean_precision
value: 77.62060210373595
- type: euclidean_recall
value: 82.38373883584848
- type: main_score
value: 87.46554314325058
- type: manhattan_accuracy
value: 89.76597974152986
- type: manhattan_accuracy_threshold
value: 3988.5299682617188
- type: manhattan_ap
value: 87.46554314325058
- type: manhattan_f1
value: 79.97181740645973
- type: manhattan_f1_threshold
value: 4235.905838012695
- type: manhattan_precision
value: 77.13713427283783
- type: manhattan_recall
value: 83.02279026793964
- type: max_ap
value: 87.46554314325058
- type: max_f1
value: 79.97181740645973
- type: max_precision
value: 77.73409057812728
- type: max_recall
value: 83.02279026793964
- type: similarity_accuracy
value: 89.7892653393876
- type: similarity_accuracy_threshold
value: 79.69566583633423
- type: similarity_ap
value: 87.4579867302024
- type: similarity_f1
value: 79.91620843152658
- type: similarity_f1_threshold
value: 78.53609323501587
- type: similarity_precision
value: 77.7155329210622
- type: similarity_recall
value: 82.24514936864799
task:
type: PairClassification
tags:
- mteb
- sentence-transformers
- transformers
- sentence-similarity
license: mit
---
# Updates
New open-source models and ToDoList will be listed on https://github.com/DunZhang/Stella/blob/main/news_and_todo.md.
You can also find these models on my [homepage](https://huggingface.co/infgrad).
# Introduction
The models are trained based on `Alibaba-NLP/gte-large-en-v1.5` and `Alibaba-NLP/gte-Qwen2-1.5B-instruct`. Thanks for
their contributions!
**We simplify usage of prompts, providing two prompts for most general tasks, one is for s2p, another one is for s2s.**
Prompt of s2p task(e.g. retrieve task):
```text
Instruct: Given a web search query, retrieve relevant passages that answer the query.\nQuery: {query}
```
Prompt of s2s task(e.g. semantic textual similarity task):
```text
Instruct: Retrieve semantically similar text.\nQuery: {query}
```
The models are finally trained by [MRL](https://arxiv.org/abs/2205.13147), so they have multiple dimensions: 512, 768,
1024, 2048, 4096, 6144 and 8192.
The higher the dimension, the better the performance.
**Generally speaking, 1024d is good enough.** The MTEB score of 1024d is only 0.001 lower than 8192d.
# Model directory structure
The model directory structure is very simple, it is a standard SentenceTransformer directory **with a series
of `2_Dense_{dims}`
folders**, where `dims` represents the final vector dimension.
For example, the `2_Dense_256` folder stores Linear weights that convert vector dimensions to 256 dimensions.
Please refer to the following chapters for specific instructions on how to use them.
# Usage
You can use `SentenceTransformers` or `transformers` library to encode text.
## Sentence Transformers
```python
from sentence_transformers import SentenceTransformer
# This model supports two prompts: "s2p_query" and "s2s_query" for sentence-to-passage and sentence-to-sentence tasks, respectively.
# They are defined in `config_sentence_transformers.json`
query_prompt_name = "s2p_query"
queries = [
"What are some ways to reduce stress?",
"What are the benefits of drinking green tea?",
]
# docs do not need any prompts
docs = [
"There are many effective ways to reduce stress. Some common techniques include deep breathing, meditation, and physical activity. Engaging in hobbies, spending time in nature, and connecting with loved ones can also help alleviate stress. Additionally, setting boundaries, practicing self-care, and learning to say no can prevent stress from building up.",
"Green tea has been consumed for centuries and is known for its potential health benefits. It contains antioxidants that may help protect the body against damage caused by free radicals. Regular consumption of green tea has been associated with improved heart health, enhanced cognitive function, and a reduced risk of certain types of cancer. The polyphenols in green tea may also have anti-inflammatory and weight loss properties.",
]
# ！The default dimension is 1024, if you need other dimensions, please clone the model and modify `modules.json` to replace `2_Dense_1024` with another dimension, e.g. `2_Dense_256` or `2_Dense_8192` !
# on gpu
model = SentenceTransformer("dunzhang/stella_en_400M_v5", trust_remote_code=True).cuda()
# you can also use this model without the features of `use_memory_efficient_attention` and `unpad_inputs`. It can be worked in CPU.
# model = SentenceTransformer(
# "dunzhang/stella_en_400M_v5",
# trust_remote_code=True,
# device="cpu",
# config_kwargs={"use_memory_efficient_attention": False, "unpad_inputs": False}
# )
query_embeddings = model.encode(queries, prompt_name=query_prompt_name)
doc_embeddings = model.encode(docs)
print(query_embeddings.shape, doc_embeddings.shape)
# (2, 1024) (2, 1024)
similarities = model.similarity(query_embeddings, doc_embeddings)
print(similarities)
# tensor([[0.8398, 0.2990],
# [0.3282, 0.8095]])
```
## Transformers
```python
import os
import torch
from transformers import AutoModel, AutoTokenizer
from sklearn.preprocessing import normalize
query_prompt = "Instruct: Given a web search query, retrieve relevant passages that answer the query.\nQuery: "
queries = [
"What are some ways to reduce stress?",
"What are the benefits of drinking green tea?",
]
queries = [query_prompt + query for query in queries]
# docs do not need any prompts
docs = [
"There are many effective ways to reduce stress. Some common techniques include deep breathing, meditation, and physical activity. Engaging in hobbies, spending time in nature, and connecting with loved ones can also help alleviate stress. Additionally, setting boundaries, practicing self-care, and learning to say no can prevent stress from building up.",
"Green tea has been consumed for centuries and is known for its potential health benefits. It contains antioxidants that may help protect the body against damage caused by free radicals. Regular consumption of green tea has been associated with improved heart health, enhanced cognitive function, and a reduced risk of certain types of cancer. The polyphenols in green tea may also have anti-inflammatory and weight loss properties.",
]
# The path of your model after cloning it
model_dir = "{Your MODEL_PATH}"
vector_dim = 1024
vector_linear_directory = f"2_Dense_{vector_dim}"
model = AutoModel.from_pretrained(model_dir, trust_remote_code=True).cuda().eval()
# you can also use this model without the features of `use_memory_efficient_attention` and `unpad_inputs`. It can be worked in CPU.
# model = AutoModel.from_pretrained(model_dir, trust_remote_code=True,use_memory_efficient_attention=False,unpad_inputs=False).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained(model_dir, trust_remote_code=True)
vector_linear = torch.nn.Linear(in_features=model.config.hidden_size, out_features=vector_dim)
vector_linear_dict = {
k.replace("linear.", ""): v for k, v in
torch.load(os.path.join(model_dir, f"{vector_linear_directory}/pytorch_model.bin")).items()
}
vector_linear.load_state_dict(vector_linear_dict)
vector_linear.cuda()
# Embed the queries
with torch.no_grad():
input_data = tokenizer(queries, padding="longest", truncation=True, max_length=512, return_tensors="pt")
input_data = {k: v.cuda() for k, v in input_data.items()}
attention_mask = input_data["attention_mask"]
last_hidden_state = model(**input_data)[0]
last_hidden = last_hidden_state.masked_fill(~attention_mask[..., None].bool(), 0.0)
query_vectors = last_hidden.sum(dim=1) / attention_mask.sum(dim=1)[..., None]
query_vectors = normalize(vector_linear(query_vectors).cpu().numpy())
# Embed the documents
with torch.no_grad():
input_data = tokenizer(docs, padding="longest", truncation=True, max_length=512, return_tensors="pt")
input_data = {k: v.cuda() for k, v in input_data.items()}
attention_mask = input_data["attention_mask"]
last_hidden_state = model(**input_data)[0]
last_hidden = last_hidden_state.masked_fill(~attention_mask[..., None].bool(), 0.0)
docs_vectors = last_hidden.sum(dim=1) / attention_mask.sum(dim=1)[..., None]
docs_vectors = normalize(vector_linear(docs_vectors).cpu().numpy())
print(query_vectors.shape, docs_vectors.shape)
# (2, 1024) (2, 1024)
similarities = query_vectors @ docs_vectors.T
print(similarities)
# [[0.8397531 0.29900077]
# [0.32818374 0.80954516]]
```
### infinity_emb
Usage via [infinity, MIT Licensed](https://github.com/michaelfeil/infinity).
```bash
docker run \
--gpus all -p "7997":"7997" \
michaelf34/infinity:0.0.69 \
v2 --model-id dunzhang/stella_en_400M_v5 --revision "refs/pr/24" --dtype bfloat16 --batch-size 16 --device cuda --engine torch --port 7997 --no-bettertransformer
```
# FAQ
Q: The details of training?
A: The training method and datasets will be released in the future. (specific time unknown, may be provided in a paper)
Q: How to choose a suitable prompt for my own task?
A: In most cases, please use the s2p and s2s prompts. These two prompts account for the vast majority of the training
data.
Q: How to reproduce MTEB results?
A: Please use evaluation scripts in `Alibaba-NLP/gte-Qwen2-1.5B-instruct` or `intfloat/e5-mistral-7b-instruct`
Q: Why each dimension has a linear weight?
A: MRL has multiple training methods, we choose this method which has the best performance.
Q: What is the sequence length of models?
A: 512 is recommended, in our experiments, almost all models perform poorly on specialized long text retrieval datasets. Besides, the
model is trained on datasets of 512 length. This may be an optimization term.
If you have any questions, please start a discussion on community.
|
learnifyhealth/biobert-v1-1-pubmedqa-finetuned
|
learnifyhealth
| 2025-03-05T10:46:49Z | 0 | 1 |
transformers
|
[
"transformers",
"safetensors",
"bert",
"text-classification",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2025-03-03T05:57:43Z |
---
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]
|
kira/pxl-tokenizer
|
kira
| 2025-03-05T10:45:59Z | 0 | 0 |
transformers
|
[
"transformers",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-03-05T10:43:57Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
MrRobotoAI/C1-L
|
MrRobotoAI
| 2025-03-05T10:44:42Z | 105 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"mergekit",
"merge",
"conversational",
"arxiv:2403.19522",
"base_model:MrRobotoAI/A1-L-R",
"base_model:merge:MrRobotoAI/A1-L-R",
"base_model:MrRobotoAI/A6-L",
"base_model:merge:MrRobotoAI/A6-L",
"base_model:MrRobotoAI/B6-L",
"base_model:merge:MrRobotoAI/B6-L",
"base_model:MrRobotoAI/B7-L",
"base_model:merge:MrRobotoAI/B7-L",
"base_model:MrRobotoAI/Hel-v4-8b-DARK-FICTION-128K",
"base_model:merge:MrRobotoAI/Hel-v4-8b-DARK-FICTION-128K",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-03-04T20:35:53Z |
---
base_model:
- MrRobotoAI/B7
- MrRobotoAI/A1-L-R
- MrRobotoAI/A6-L
- MrRobotoAI/B6
- MrRobotoAI/Hel-v4-8b-DARK-FICTION-128K
library_name: transformers
tags:
- mergekit
- merge
---
# merge 13,632 LINES
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [MrRobotoAI/Hel-v4-8b-DARK-FICTION-128K](https://huggingface.co/MrRobotoAI/Hel-v4-8b-DARK-FICTION-128K) as a base.
### Models Merged
The following models were included in the merge:
* [MrRobotoAI/B7](https://huggingface.co/MrRobotoAI/B7)
* [MrRobotoAI/A1-L-R](https://huggingface.co/MrRobotoAI/A1-L-R)
* [MrRobotoAI/A6-L](https://huggingface.co/MrRobotoAI/A6-L)
* [MrRobotoAI/B6](https://huggingface.co/MrRobotoAI/B6)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: MrRobotoAI/B7
- model: MrRobotoAI/A6-L
- model: MrRobotoAI/B6
- model: MrRobotoAI/A1-L-R
merge_method: model_stock
base_model: MrRobotoAI/Hel-v4-8b-DARK-FICTION-128K
normalize: true
dtype: float16
```
|
palaio/code-search-net-tokenizer
|
palaio
| 2025-03-05T10:44:14Z | 0 | 0 |
transformers
|
[
"transformers",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-03-05T10:44:08Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
smartrichard/xr1-lora-6
|
smartrichard
| 2025-03-05T10:42:39Z | 0 | 0 |
peft
|
[
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:Qwen/Qwen2.5-0.5B",
"base_model:adapter:Qwen/Qwen2.5-0.5B",
"region:us"
] | null | 2025-03-05T10:41:54Z |
---
base_model: Qwen/Qwen2.5-0.5B
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 0.14.0
|
miguelfodaocom/Pentest
|
miguelfodaocom
| 2025-03-05T10:41:39Z | 0 | 0 | null |
[
"license:apache-2.0",
"region:us"
] | null | 2025-03-05T10:41:37Z |
---
license: apache-2.0
---
|
OumaymaELBIACH/Results_Llama3_SMM4H
|
OumaymaELBIACH
| 2025-03-05T10:40:18Z | 0 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"generated_from_trainer",
"trl",
"sft",
"base_model:meta-llama/Llama-3.2-1B",
"base_model:finetune:meta-llama/Llama-3.2-1B",
"endpoints_compatible",
"region:us"
] | null | 2025-01-04T10:33:31Z |
---
base_model: meta-llama/Llama-3.2-1B
library_name: transformers
model_name: Results_llama3_SMM4H
tags:
- generated_from_trainer
- trl
- sft
licence: license
---
# Model Card for Results_llama3_SMM4H
This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B).
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="OumaymaELBIACH/Results_llama3_SMM4H", 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 SFT.
### Framework versions
- TRL: 0.15.2
- Transformers: 4.48.3
- Pytorch: 2.5.1+cu124
- Datasets: 3.3.2
- Tokenizers: 0.21.0
## Citations
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}}
}
```
|
jingxie23/Mistral-7B-Instruct-v0.3-Q4_K_M-GGUF
|
jingxie23
| 2025-03-05T10:39:51Z | 0 | 0 | null |
[
"gguf",
"llama-cpp",
"gguf-my-repo",
"base_model:mistralai/Mistral-7B-Instruct-v0.3",
"base_model:quantized:mistralai/Mistral-7B-Instruct-v0.3",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-03-05T10:39:30Z |
---
license: apache-2.0
base_model: mistralai/Mistral-7B-Instruct-v0.3
extra_gated_description: If you want to learn more about how we process your personal
data, please read our <a href="https://mistral.ai/terms/">Privacy Policy</a>.
tags:
- llama-cpp
- gguf-my-repo
---
# jingxie23/Mistral-7B-Instruct-v0.3-Q4_K_M-GGUF
This model was converted to GGUF format from [`mistralai/Mistral-7B-Instruct-v0.3`](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) 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/mistralai/Mistral-7B-Instruct-v0.3) 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 jingxie23/Mistral-7B-Instruct-v0.3-Q4_K_M-GGUF --hf-file mistral-7b-instruct-v0.3-q4_k_m.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo jingxie23/Mistral-7B-Instruct-v0.3-Q4_K_M-GGUF --hf-file mistral-7b-instruct-v0.3-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 jingxie23/Mistral-7B-Instruct-v0.3-Q4_K_M-GGUF --hf-file mistral-7b-instruct-v0.3-q4_k_m.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo jingxie23/Mistral-7B-Instruct-v0.3-Q4_K_M-GGUF --hf-file mistral-7b-instruct-v0.3-q4_k_m.gguf -c 2048
```
|
Felix-Zhenghao/Libero-FAST
|
Felix-Zhenghao
| 2025-03-05T10:38:54Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-03-05T07:46:12Z |
This uses physical-intelligence's FAST action tokenizer but is only trained on LIBERO dataset. Action horizon = 10 (1 second).
|
Grogros/dmWM-llama-3.2-1B-Instruct-OWTWM-Al4WM-DistillationWM-Al4-wmToken-d4-APP
|
Grogros
| 2025-03-05T10:34:06Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"generated_from_trainer",
"conversational",
"base_model:meta-llama/Llama-3.2-1B-Instruct",
"base_model:finetune:meta-llama/Llama-3.2-1B-Instruct",
"license:llama3.2",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-03-05T08:00:44Z |
---
library_name: transformers
license: llama3.2
base_model: meta-llama/Llama-3.2-1B-Instruct
tags:
- generated_from_trainer
model-index:
- name: dmWM-llama-3.2-1B-Instruct-OWTWM-Al4WM-DistillationWM-Al4-wmToken-d4-APP
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. -->
# dmWM-llama-3.2-1B-Instruct-OWTWM-Al4WM-DistillationWM-Al4-wmToken-d4-APP
This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) 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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- optimizer: Use OptimizerNames.ADAFACTOR and the args are:
No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 2500
### Training results
### Framework versions
- Transformers 4.46.3
- Pytorch 2.5.1.post303
- Datasets 3.2.0
- Tokenizers 0.20.3
|
mradermacher/UnFimbulvetr-20B-V2-GGUF
|
mradermacher
| 2025-03-05T10:32:23Z | 240 | 2 |
transformers
|
[
"transformers",
"gguf",
"mergekit",
"merge",
"en",
"base_model:KaraKaraWarehouse/UnFimbulvetr-20B-V2",
"base_model:quantized:KaraKaraWarehouse/UnFimbulvetr-20B-V2",
"endpoints_compatible",
"region:us"
] | null | 2024-05-15T18:54:10Z |
---
base_model: KaraKaraWarehouse/UnFimbulvetr-20B-V2
language:
- en
library_name: transformers
quantized_by: mradermacher
tags:
- mergekit
- merge
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/KaraKaraWarehouse/UnFimbulvetr-20B-V2
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/UnFimbulvetr-20B-V2-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/UnFimbulvetr-20B-V2-GGUF/resolve/main/UnFimbulvetr-20B-V2.Q2_K.gguf) | Q2_K | 7.8 | |
| [GGUF](https://huggingface.co/mradermacher/UnFimbulvetr-20B-V2-GGUF/resolve/main/UnFimbulvetr-20B-V2.IQ3_XS.gguf) | IQ3_XS | 8.6 | |
| [GGUF](https://huggingface.co/mradermacher/UnFimbulvetr-20B-V2-GGUF/resolve/main/UnFimbulvetr-20B-V2.Q3_K_S.gguf) | Q3_K_S | 9.1 | |
| [GGUF](https://huggingface.co/mradermacher/UnFimbulvetr-20B-V2-GGUF/resolve/main/UnFimbulvetr-20B-V2.IQ3_S.gguf) | IQ3_S | 9.1 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/UnFimbulvetr-20B-V2-GGUF/resolve/main/UnFimbulvetr-20B-V2.IQ3_M.gguf) | IQ3_M | 9.4 | |
| [GGUF](https://huggingface.co/mradermacher/UnFimbulvetr-20B-V2-GGUF/resolve/main/UnFimbulvetr-20B-V2.Q3_K_M.gguf) | Q3_K_M | 10.1 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/UnFimbulvetr-20B-V2-GGUF/resolve/main/UnFimbulvetr-20B-V2.Q3_K_L.gguf) | Q3_K_L | 11.0 | |
| [GGUF](https://huggingface.co/mradermacher/UnFimbulvetr-20B-V2-GGUF/resolve/main/UnFimbulvetr-20B-V2.IQ4_XS.gguf) | IQ4_XS | 11.3 | |
| [GGUF](https://huggingface.co/mradermacher/UnFimbulvetr-20B-V2-GGUF/resolve/main/UnFimbulvetr-20B-V2.Q4_K_S.gguf) | Q4_K_S | 11.9 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/UnFimbulvetr-20B-V2-GGUF/resolve/main/UnFimbulvetr-20B-V2.Q4_K_M.gguf) | Q4_K_M | 12.6 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/UnFimbulvetr-20B-V2-GGUF/resolve/main/UnFimbulvetr-20B-V2.Q5_K_S.gguf) | Q5_K_S | 14.4 | |
| [GGUF](https://huggingface.co/mradermacher/UnFimbulvetr-20B-V2-GGUF/resolve/main/UnFimbulvetr-20B-V2.Q5_K_M.gguf) | Q5_K_M | 14.8 | |
| [GGUF](https://huggingface.co/mradermacher/UnFimbulvetr-20B-V2-GGUF/resolve/main/UnFimbulvetr-20B-V2.Q6_K.gguf) | Q6_K | 17.1 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/UnFimbulvetr-20B-V2-GGUF/resolve/main/UnFimbulvetr-20B-V2.Q8_0.gguf) | Q8_0 | 22.2 | fast, best quality |
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 -->
|
LA1512/whisper-tiny-add-noise
|
LA1512
| 2025-03-05T10:32:15Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"whisper",
"automatic-speech-recognition",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2025-03-05T10:30:36Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
ShihamFM/House_Price_Prediction
|
ShihamFM
| 2025-03-05T10:30:41Z | 0 | 0 | null |
[
"license:apache-2.0",
"region:us"
] | null | 2025-03-05T10:30:41Z |
---
license: apache-2.0
---
|
Anasft9/model-1-test
|
Anasft9
| 2025-03-05T10:30:35Z | 0 | 0 | null |
[
"license:apache-2.0",
"region:us"
] | null | 2025-03-05T10:30:35Z |
---
license: apache-2.0
---
|
voxreality/voxreality-arta-lego-llama2-7b-chat
|
voxreality
| 2025-03-05T10:29:28Z | 15 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"en",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-12-19T14:03:17Z |
---
license: apache-2.0
task_categories:
- text-generation
language:
- en
extra_gated_fields:
Organization type:
type: select
options:
- Industry
- Academia
- Government
- Non-Profit
- label: Other
value: other
Role type:
type: select
options:
- Researcher
- Engineer
- Student
- label: Other
value: other
Country: country
I agree to use this model for non-commercial use ONLY: checkbox
---
# 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. -->
voxreality-arta-lego-llama2-7b-chat is a Large Language Model (LLM) that is a fine-tuned version of Llama-2-7b-chat-hf using LEGO assembly dataset. This model aims to act as a training assistant for assembly task in an extended reality application.
### How to use the Model
```python
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("voxreality/voxreality-arta-lego-llama2-7b-chat", device_map="auto", trust_remote_code=True, token=True)
model = AutoModelForCausalLM.from_pretrained("voxreality/voxreality-arta-lego-llama2-7b-chat", device_map="auto", trust_remote_code=True, token=True, quantization_config=bnb_config)
```
### More details
- **Paper:** Autonomous Workflow for Multimodal Fine-Grained Training Assistants Towards Mixed Reality, ACL 2024
|
Sileshi/Lora_Finetuned_for_Arrhthmia
|
Sileshi
| 2025-03-05T10:28:17Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llava_llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-03-04T23:04:24Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
labula123/deepseek_afterpretrain_tining
|
labula123
| 2025-03-05T10:26:56Z | 0 | 0 | null |
[
"safetensors",
"llama",
"license:apache-2.0",
"region:us"
] | null | 2025-03-05T08:34:49Z |
---
license: apache-2.0
---
|
AImused/cold37
|
AImused
| 2025-03-05T10:26:36Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"phi3",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-03-05T09:49:54Z |
---
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]
|
voxreality/mistral-7B-navigation-new-instructions
|
voxreality
| 2025-03-05T10:25:49Z | 31 | 0 | null |
[
"safetensors",
"mistral",
"en",
"dataset:voxreality/navigation_intructions_v2",
"base_model:mistralai/Mistral-7B-Instruct-v0.2",
"base_model:finetune:mistralai/Mistral-7B-Instruct-v0.2",
"license:apache-2.0",
"region:us"
] | null | 2024-09-25T09:58:44Z |
---
license: apache-2.0
datasets:
- voxreality/navigation_intructions_v2
language:
- en
base_model:
- mistralai/Mistral-7B-Instruct-v0.2
extra_gated_fields:
Organization type:
type: select
options:
- Industry
- Academia
- Government
- Non-Profit
- label: Other
value: other
Role type:
type: select
options:
- Researcher
- Engineer
- Student
- label: Other
value: other
Country: country
I agree to use this model for non-commercial use ONLY: checkbox
---
**Model Description**
**llama2-navigation** is a Larage Language Model (LLM) that is a fine-tuned version of **mistralai/Mistral-7B-Instruct-v0.2**. This model aims to provide navigation instructions given knowledge.
The model was fine-tuned with Lora and custom training data(voxreality/navigation_intructions_v2). For more details about the model's use case, you can find the code at the following link:
- **Repository**: [https://gitlab.com/horizon-europe-voxreality/dialogue-system/conference_agent](https://gitlab.com/horizon-europe-voxreality/dialogue-system/conference_agent)
**How to Get Started with the Model**
Below you can find an example of model usage:
```python
import torch, textwrap
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig, pipeline
from langchain import HuggingFacePipeline, PromptTemplate
from langchain.chains import LLMChain
model_name = "voxreality/mistral-7B-navigation-new-instructions"
user_msg = "I need to go to the social area."
knowledge = "start, turn left, crossing yellow sphere left, arrive wall opening, turn left, turn right, pass corridor, crossing magenta sphere left, arrive conference room, finish"
tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=True)
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, trust_remote_code=True, device_map="auto")
generation_config = GenerationConfig.from_pretrained(model_name)
generation_config.max_new_tokens = 1024
generation_config.temperature = 0.0001
generation_config.top_p = 0.95
generation_config.do_sample = True
generation_config.repetition_penalty = 1.15
text_pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer, generation_config=generation_config)
llm = HuggingFacePipeline(pipeline=text_pipeline, model_kwargs={"temperature": 0})
text_pipeline = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
generation_config=generation_config)
model = HuggingFacePipeline(pipeline=text_pipeline, model_kwargs={"temperature": 0})
prompt = textwrap.dedent("""
[INST] <>
You are a navigation assistant at a conference venue. Your task is to guide users to specific locations within the venue, including "booth 1", "booth 2", "booth 3", "booth 4", "social area", "exit", "business room", and "conference room".
- For clear directions, respond with numbered steps using the details provided in the 'knowledge' field.
- Ensure to translate the directions from the 'knowledge' field into a user-friendly format with clear, numbered steps."
"" \n\n
<>
### input: {input}
### knowledge: {knowledge}
[/INST]
""")
prompt = PromptTemplate(input_variables=["input", "knowledge"], template= prompt)
chain = LLMChain(llm=model, prompt=prompt)
print(chain.run(input=user_msg, knowledge=knowledge))
```
|
zisisbatzos/3SFTs_synthetic_emobench_llama3.2-3B
|
zisisbatzos
| 2025-03-05T10:21:33Z | 0 | 0 | null |
[
"safetensors",
"llama",
"region:us"
] | null | 2025-03-05T08:09:51Z |
training_arguments = SFTConfig(
output_dir=output_dir,
per_device_train_batch_size=16,
gradient_accumulation_steps=1,
optim="adamw_torch",
save_steps=100,
logging_steps=1,
learning_rate=1e-4,
bf16=True,
# max_grad_norm=0.3,
num_train_epochs=3,
save_strategy="epoch",
warmup_ratio=0.05,
group_by_length=True,
# lr_scheduler_type="cosine",
gradient_checkpointing=True,
gradient_checkpointing_kwargs = {"use_reentrant": True},
dataset_text_field="text",
max_seq_length=1024,
packing=False
# report_to="wandb",
)
baseline_model = 'zisisbatzos/2SFTs_llama3.2-3B'
Metrics:
emotion_accuracy = 0.36554621848739494
correct_format = 0.7058823529411765
|
KPSTIJ/T-lite-WS
|
KPSTIJ
| 2025-03-05T10:21:24Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"qwen2",
"trl",
"en",
"base_model:t-tech/T-lite-it-1.0",
"base_model:finetune:t-tech/T-lite-it-1.0",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-03-05T10:21:06Z |
---
base_model: t-tech/T-lite-it-1.0
tags:
- text-generation-inference
- transformers
- unsloth
- qwen2
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** KPSTIJ
- **License:** apache-2.0
- **Finetuned from model :** t-tech/T-lite-it-1.0
This qwen2 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)
|
Krazeder/Reinforce-CartPole-v1
|
Krazeder
| 2025-03-05T10:21:15Z | 0 | 0 | null |
[
"CartPole-v1",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] |
reinforcement-learning
| 2025-03-05T10:21:05Z |
---
tags:
- CartPole-v1
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-CartPole-v1
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: CartPole-v1
type: CartPole-v1
metrics:
- type: mean_reward
value: 500.00 +/- 0.00
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **CartPole-v1**
This is a trained model of a **Reinforce** agent playing **CartPole-v1** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
NoMoreCopyrightOrg/flux-test
|
NoMoreCopyrightOrg
| 2025-03-05T10:20:55Z | 0 | 0 | null |
[
"en",
"license:other",
"endpoints_compatible",
"region:us"
] | null | 2025-03-04T14:05:28Z |
---
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.
language:
- en
inference: true
---
|
NoMoreCopyrightOrg/flux-dev-8step
|
NoMoreCopyrightOrg
| 2025-03-05T10:20:45Z | 0 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"en",
"license:other",
"endpoints_compatible",
"diffusers:FluxPipeline",
"region:us"
] |
text-to-image
| 2025-03-05T07:42:01Z |
---
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.
language:
- en
inference: true
---
|
ann04ka/Qwen_2_5_3B_test
|
ann04ka
| 2025-03-05T10:19:52Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"generated_from_trainer",
"trl",
"sft",
"base_model:Qwen/Qwen2.5-VL-3B-Instruct",
"base_model:finetune:Qwen/Qwen2.5-VL-3B-Instruct",
"endpoints_compatible",
"region:us"
] | null | 2025-02-20T13:07:27Z |
---
base_model: Qwen/Qwen2.5-VL-3B-Instruct
library_name: transformers
model_name: Qwen_2_5_3B_test
tags:
- generated_from_trainer
- trl
- sft
licence: license
---
# Model Card for Qwen_2_5_3B_test
This model is a fine-tuned version of [Qwen/Qwen2.5-VL-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-3B-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="ann04ka/Qwen_2_5_3B_test", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/annbeze57-itmo/Qwen_2_5_3B_try/runs/zetronm3)
This model was trained with SFT.
### Framework versions
- TRL: 0.16.0.dev0
- Transformers: 4.49.0
- Pytorch: 2.4.1+cu121
- Datasets: 3.3.2
- Tokenizers: 0.21.0
## Citations
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}}
}
```
|
UMCU/CardioLM_encoder_base
|
UMCU
| 2025-03-05T10:19:09Z | 9 | 0 |
transformers
|
[
"transformers",
"safetensors",
"roberta",
"fill-mask",
"medical",
"healthcare",
"nl",
"base_model:CLTL/MedRoBERTa.nl",
"base_model:finetune:CLTL/MedRoBERTa.nl",
"license:gpl-3.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2025-03-04T14:55:04Z |
---
license: gpl-3.0
language:
- nl
base_model:
- CLTL/MedRoBERTa.nl
tags:
- medical
- healthcare
metrics:
- perplexity
library_name: transformers
---
Continued, off-premise, pre-training of [MedRoBERTa.nl](https://huggingface.co/CLTL/MedRoBERTa.nl) using about 50GB of open Dutch and translated
English corpora.
# Data statistics
Sources:
* Dutch: medical guidelines (FMS, NHG)
* Dutch: [NtvG](https://www.ntvg.nl/) papers
* English: Pubmed abstracts
* English: PMC abstracts translated using DeepL
* English: Apollo guidelines, papers and books
* English: Meditron guidelines
* English: MIMIC3
* English: MIMIC CXR
* English: MIMIC4
All translated (if not with DeepL) with performed with a combination of GeminiFlash 1.5/GPT4o mini, MariaNMT, NLLB200.
* Number of tokens: 15B
* Number of documents: 27M
# Training
* Effective batch size: 5120
* Learning rate: 2e-4
* Weight decay: 1e-3
* Learning schedule: linear, with 5_000 warmup steps
* Num epochs: ~3
Train perplexity: 3.0
Validation perplexity: 3.0
# Acknowledgement
We were happy to be able to use the [Google TPU research cloud](https://sites.research.google/trc/about/) for training the model.
|
gghsgn/model_inacbg_llama
|
gghsgn
| 2025-03-05T10:18:46Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-03-05T10:18:09Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
deqing/llama-3.2-350M-fourier_multiplication_dataset
|
deqing
| 2025-03-05T10:18:14Z | 3 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"generated_from_trainer",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-03-04T13:20:52Z |
---
library_name: transformers
base_model: llama_small_config.json
tags:
- generated_from_trainer
model-index:
- name: llama-3.2-350M-fourier_multiplication_dataset
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. -->
# llama-3.2-350M-fourier_multiplication_dataset
This model is a fine-tuned version of [llama_small_config.json](https://huggingface.co/llama_small_config.json) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.7836
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- 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_steps: 1000
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 2.6476 | 0.1415 | 1000 | 2.5967 |
| 2.0109 | 0.2831 | 2000 | 2.0067 |
| 2.1092 | 0.4246 | 3000 | 2.1034 |
| 1.9086 | 0.5661 | 4000 | 1.9051 |
| 1.8537 | 0.7076 | 5000 | 1.8473 |
| 1.7953 | 0.8492 | 6000 | 1.7943 |
| 1.7858 | 0.9907 | 7000 | 1.7836 |
### Framework versions
- Transformers 4.48.2
- Pytorch 2.3.1+cu118
- Datasets 3.2.0
- Tokenizers 0.21.0
|
baby-dev/1676b2e3-14d1-4122-91a8-5b42a90a77de
|
baby-dev
| 2025-03-05T10:18:10Z | 0 | 0 |
peft
|
[
"peft",
"generated_from_trainer",
"base_model:fxmarty/tiny-random-GemmaForCausalLM",
"base_model:adapter:fxmarty/tiny-random-GemmaForCausalLM",
"region:us"
] | null | 2025-03-05T10:18:03Z |
---
library_name: peft
tags:
- generated_from_trainer
base_model: fxmarty/tiny-random-GemmaForCausalLM
model-index:
- name: baby-dev/1676b2e3-14d1-4122-91a8-5b42a90a77de
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. -->
# baby-dev/1676b2e3-14d1-4122-91a8-5b42a90a77de
This model was trained from scratch on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 12.3670
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
### Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1
|
rohinm/model_top_p_works
|
rohinm
| 2025-03-05T10:14:11Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen2",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-03-05T10:11:50Z |
---
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]
|
baby-dev/61b4c3f7-554b-4797-9f31-b2752335b627
|
baby-dev
| 2025-03-05T10:12:39Z | 0 | 0 |
peft
|
[
"peft",
"generated_from_trainer",
"base_model:unsloth/Phi-3-medium-4k-instruct",
"base_model:adapter:unsloth/Phi-3-medium-4k-instruct",
"region:us"
] | null | 2025-03-05T10:12:16Z |
---
library_name: peft
tags:
- generated_from_trainer
base_model: unsloth/Phi-3-medium-4k-instruct
model-index:
- name: baby-dev/61b4c3f7-554b-4797-9f31-b2752335b627
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. -->
# baby-dev/61b4c3f7-554b-4797-9f31-b2752335b627
This model was trained from scratch on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1190
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
### Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1
|
emirhanboge/sst2_mnli_qqp_llama1b_modified
|
emirhanboge
| 2025-03-05T10:12:36Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-03-05T10:12:18Z |
# Multi-Task Dataset: SST-2 + MNLI + QQP (Modified for LLaMA 1B)
This dataset is a combination of **SST-2, MNLI, and QQP** for multi-task learning.
## **Modifications:**
- Each example includes a task prefix:
- **SST-2:** `"Task: SST2 | Sentence: ..."`
- **MNLI:** `"Task: MNLI | Premise: ... Hypothesis: ..."`
- **QQP:** `"Task: QQP | Q1: ... Q2: ..."`
- Labels are standardized to integer format.
- Tokenized using the **LLaMA-1B tokenizer**.
- Maximum sequence length is **128 tokens**.
## **Dataset Usage:**
```python
from datasets import load_dataset
dataset = load_dataset("emirhanboge/sst2_mnli_qqp_llama1b_modified")
|
csm9493/43_five_dataset_shuffle_10000_cot_lora_all_r64_alpha128_lr_1e-05_decay_1e2_cosine_epoch_3_mbs_16
|
csm9493
| 2025-03-05T10:11:38Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"mistral",
"text-generation",
"trl",
"sft",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
] |
text-generation
| 2025-03-05T10:05:37Z |
---
library_name: transformers
tags:
- trl
- sft
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
emirhanboge/sst2_llama1b_modified
|
emirhanboge
| 2025-03-05T10:11:04Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-03-05T10:10:59Z |
# SST-2 (Modified for LLaMA 1B)
This dataset is a modified version of the **Stanford Sentiment Treebank 2 (SST-2)**, a binary classification dataset for sentiment analysis.
## **Modifications:**
- Labels were originally `"negative"` and `"positive"`, now converted to integers (`0` for negative, `1` for positive).
- Each example includes a task prefix: `Task: SST2 | Sentence: ...`
- The dataset has been **tokenized using the LLaMA-1B tokenizer**.
- Maximum sequence length is **128 tokens**.
## **Dataset Usage:**
```python
from datasets import load_dataset
dataset = load_dataset("emirhanboge/sst2_llama1b_modified")
|
Illumicorp/Psytrance
|
Illumicorp
| 2025-03-05T10:10:47Z | 0 | 0 | null |
[
"license:bigscience-openrail-m",
"region:us"
] | null | 2025-03-05T10:10:47Z |
---
license: bigscience-openrail-m
---
|
alibidaran/SMOLL_image_captioner
|
alibidaran
| 2025-03-05T10:09:40Z | 37 | 0 | null |
[
"safetensors",
"llama",
"en",
"base_model:HuggingFaceTB/SmolLM2-360M",
"base_model:finetune:HuggingFaceTB/SmolLM2-360M",
"license:apache-2.0",
"region:us"
] | null | 2025-02-13T13:03:34Z |
---
license: apache-2.0
language:
- en
base_model:
- HuggingFaceTB/SmolLM2-360M
---
# SMOLLM_VISON_Image_Captioner
## Overview
This project implements an image captioning model using OpenAI's CLIP model and a causal language model (LLM). The model extracts image features using CLIP and generates captions using a fine-tuned LLM. It is trained with the Flickr-8k dataset.
## Requirements
Before running the code, ensure you have installed the necessary dependencies:
```bash
pip install transformers==4.47.0 torch opencv-python matplotlib pillow requests
```
## Model and Token Configuration
The code utilizes the following models:
- CLIP: `openai/clip-vit-large-patch14`
- LLM: `alibidaran/SMOLL_image_captioner`
- Tokenizer: `HuggingFaceTB/SmolLM2-360M`
## Installation and Setup
### Load Necessary Libraries
```python
from PIL import Image
import requests
from transformers import CLIPProcessor, CLIPModel
import cv2
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
import matplotlib.pyplot as plt
```
### Load CLIP Model
```python
clip_model = CLIPModel.from_pretrained("openai/clip-vit-large-patch14").to('cuda:0')
clip_processor = CLIPProcessor.from_pretrained("openai/clip-vit-large-patch14")
print(torch.cuda.is_available())
```
### Load Tokenizer and LLM Model
```python
device = 'cuda' if torch.cuda.is_available() else 'cpu'
tokenizer = AutoTokenizer.from_pretrained("HuggingFaceTB/SmolLM2-360M")
llm_model = AutoModelForCausalLM.from_pretrained("alibidaran/SMOLL_image_captioner").to('cuda')
```
### Download Pretrained Model Weights
```bash
wget https://huggingface.co/alibidaran/SMOLL_image_captioner/resolve/main/content/SMOLL_image_captioner.pt
```
## Image Captioning Model
### Load Model Weights
```python
from SMOLLM_VisionModel import SMOLLm_VISION_ImageCaptioning,SmoLLM_processor
image_captioning_model = SMOLLm_VISION_ImageCaptioning(llm_model=llm_model, hidden_dim=4096).to('cuda')
model = image_captioning_model
processor=SmoLLM_processor(image_model=clip_model,image_processor=clip_processor)
saved_model = torch.load('/content/SMOLL_image_captioner.pt', map_location=torch.device('cuda'))
```
## Image Caption Generation
### Load Image and Extract Features
```python
import cv2
import matplotlib.pyplot as plt
image_url = '/content/54322546688_71515f8335_w.jpg'
image_features = processor.get_features(image_url, device='cuda')
```
### Generate Caption
```python
tokenizer.pad_token = tokenizer.eos_token
prompt = """
##User <image> Write a caption
##Assitant:"""
# Tokenize input
tokenized = tokenizer(prompt, return_tensors='pt')
label = tokenized['input_ids'].to('cuda')
att = tokenized['attention_mask'].to('cuda')
# Generate caption
with torch.no_grad():
_, embeds = model(image_features.unsqueeze(0).to('cuda'), label, att)
generate_kwargs = {
"input_ids": None,
"inputs_embeds": embeds,
"max_new_tokens": 50,
}
output = saved_model.llm_model.generate(**generate_kwargs, do_sample=True, temperature=0.8, top_p=0.99, top_k=10)
# Decode and display result
print(tokenizer.decode(output[0]))
plt.imshow(image)
```
|
TFOCUS/memevis-father_20
|
TFOCUS
| 2025-03-05T10:07:27Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-03-05T10:02:56Z |
---
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]
|
texanrangee/83824331-34ff-46de-915c-43e3a79871c7
|
texanrangee
| 2025-03-05T10:04:27Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"unsloth",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-03-05T07:47:55Z |
---
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]
|
HueyWoo/Llama-3.2-3B-en
|
HueyWoo
| 2025-03-05T10:04:13Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"unsloth",
"trl",
"sft",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-03-05T09:51:40Z |
---
library_name: transformers
tags:
- unsloth
- trl
- sft
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
omlab/VLM-R1-Math-0305
|
omlab
| 2025-03-05T10:03:11Z | 0 | 0 | null |
[
"safetensors",
"qwen2_5_vl",
"license:apache-2.0",
"region:us"
] | null | 2025-03-05T08:42:39Z |
---
license: apache-2.0
---
|
auxyus/673a17a4-a592-4f00-a685-09ecc2ee6132
|
auxyus
| 2025-03-05T10:02:56Z | 0 | 0 |
peft
|
[
"peft",
"safetensors",
"llama",
"axolotl",
"generated_from_trainer",
"base_model:The-matt/llama2_ko-7b_distinctive-snowflake-182_1060",
"base_model:adapter:The-matt/llama2_ko-7b_distinctive-snowflake-182_1060",
"region:us"
] | null | 2025-03-05T05:50:08Z |
---
library_name: peft
base_model: The-matt/llama2_ko-7b_distinctive-snowflake-182_1060
tags:
- axolotl
- generated_from_trainer
model-index:
- name: 673a17a4-a592-4f00-a685-09ecc2ee6132
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: The-matt/llama2_ko-7b_distinctive-snowflake-182_1060
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
- 34274ad5cb19828a_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/34274ad5cb19828a_train_data.json
type:
field_instruction: prompt
field_output: prompt_orig
format: '{instruction}'
no_input_format: '{instruction}'
system_format: '{system}'
system_prompt: ''
ddp_timeout: 1800
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: 4
eval_batch_size: 4
eval_max_new_tokens: 128
eval_steps: 150
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: true
hub_model_id: auxyus/673a17a4-a592-4f00-a685-09ecc2ee6132
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: 0
logging_steps: 10
lora_alpha: 32
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lr_scheduler: cosine
max_memory:
0: 75GB
max_steps: 9000
micro_batch_size: 8
mlflow_experiment_name: /tmp/34274ad5cb19828a_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 10
optim_args:
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
relora_prune_ratio: 0.9
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 150
saves_per_epoch: null
sequence_len: 512
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: acopia-grant
wandb_mode: online
wandb_name: 59de877e-10a9-4c24-8555-05cbc12fb911
wandb_project: Gradients-On-165
wandb_run: your_name
wandb_runid: 59de877e-10a9-4c24-8555-05cbc12fb911
warmup_steps: 50
weight_decay: 0.01
xformers_attention: null
```
</details><br>
# 673a17a4-a592-4f00-a685-09ecc2ee6132
This model is a fine-tuned version of [The-matt/llama2_ko-7b_distinctive-snowflake-182_1060](https://huggingface.co/The-matt/llama2_ko-7b_distinctive-snowflake-182_1060) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4719
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 8
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.999,adam_epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 50
- training_steps: 9000
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| No log | 0.0008 | 1 | 1.3931 |
| 0.753 | 0.1188 | 150 | 0.5800 |
| 0.6043 | 0.2375 | 300 | 0.5314 |
| 0.635 | 0.3563 | 450 | 0.5138 |
| 0.6008 | 0.4751 | 600 | 0.4898 |
| 0.5637 | 0.5938 | 750 | 0.4781 |
| 0.6343 | 0.7126 | 900 | 0.4674 |
| 0.5859 | 0.8314 | 1050 | 0.4624 |
| 0.5929 | 0.9501 | 1200 | 0.4528 |
| 0.2427 | 1.0689 | 1350 | 0.4518 |
| 0.2182 | 1.1876 | 1500 | 0.4516 |
| 0.2365 | 1.3064 | 1650 | 0.4498 |
| 0.2401 | 1.4252 | 1800 | 0.4463 |
| 0.256 | 1.5439 | 1950 | 0.4444 |
| 0.245 | 1.6627 | 2100 | 0.4417 |
| 0.234 | 1.7815 | 2250 | 0.4405 |
| 0.2867 | 1.9002 | 2400 | 0.4355 |
| 0.2399 | 2.0190 | 2550 | 0.4518 |
| 0.2022 | 2.1378 | 2700 | 0.4691 |
| 0.1905 | 2.2565 | 2850 | 0.4572 |
| 0.2419 | 2.3753 | 3000 | 0.4719 |
### Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1
|
chaowenguo/lcm-lora-sdxl
|
chaowenguo
| 2025-03-05T10:02:54Z | 0 | 0 |
diffusers
|
[
"diffusers",
"lora",
"text-to-image",
"arxiv:2311.05556",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0",
"license:openrail++",
"region:us"
] |
text-to-image
| 2025-03-05T09:56:56Z |
---
library_name: diffusers
base_model: stabilityai/stable-diffusion-xl-base-1.0
tags:
- lora
- text-to-image
license: openrail++
inference: false
---
# Latent Consistency Model (LCM) LoRA: SDXL
Latent Consistency Model (LCM) LoRA was proposed in [LCM-LoRA: A universal Stable-Diffusion Acceleration Module](https://arxiv.org/abs/2311.05556)
by *Simian Luo, Yiqin Tan, Suraj Patil, Daniel Gu et al.*
It is a distilled consistency adapter for [`stable-diffusion-xl-base-1.0`](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) that allows
to reduce the number of inference steps to only between **2 - 8 steps**.
| Model | Params / M |
|----------------------------------------------------------------------------|------------|
| [lcm-lora-sdv1-5](https://huggingface.co/latent-consistency/lcm-lora-sdv1-5) | 67.5 |
| [lcm-lora-ssd-1b](https://huggingface.co/latent-consistency/lcm-lora-ssd-1b) | 105 |
| [**lcm-lora-sdxl**](https://huggingface.co/latent-consistency/lcm-lora-sdxl) | **197M** |
## Usage
LCM-LoRA is supported in 🤗 Hugging Face Diffusers library from version v0.23.0 onwards. To run the model, first
install the latest version of the Diffusers library as well as `peft`, `accelerate` and `transformers`.
audio dataset from the Hugging Face Hub:
```bash
pip install --upgrade pip
pip install --upgrade diffusers transformers accelerate peft
```
***Note: For detailed usage examples we recommend you to check out our official [LCM-LoRA docs](https://huggingface.co/docs/diffusers/main/en/using-diffusers/inference_with_lcm_lora)***
### Text-to-Image
The adapter can be loaded with it's base model `stabilityai/stable-diffusion-xl-base-1.0`. Next, the scheduler needs to be changed to [`LCMScheduler`](https://huggingface.co/docs/diffusers/v0.22.3/en/api/schedulers/lcm#diffusers.LCMScheduler) and we can reduce the number of inference steps to just 2 to 8 steps.
Please make sure to either disable `guidance_scale` or use values between 1.0 and 2.0.
```python
import torch
from diffusers import LCMScheduler, AutoPipelineForText2Image
model_id = "stabilityai/stable-diffusion-xl-base-1.0"
adapter_id = "latent-consistency/lcm-lora-sdxl"
pipe = AutoPipelineForText2Image.from_pretrained(model_id, torch_dtype=torch.float16, variant="fp16")
pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
pipe.to("cuda")
# load and fuse lcm lora
pipe.load_lora_weights(adapter_id)
pipe.fuse_lora()
prompt = "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k"
# disable guidance_scale by passing 0
image = pipe(prompt=prompt, num_inference_steps=4, guidance_scale=0).images[0]
```
### Inpainting
LCM-LoRA can be used for inpainting as well.
```python
import torch
from diffusers import AutoPipelineForInpainting, LCMScheduler
from diffusers.utils import load_image, make_image_grid
pipe = AutoPipelineForInpainting.from_pretrained(
"diffusers/stable-diffusion-xl-1.0-inpainting-0.1",
torch_dtype=torch.float16,
variant="fp16",
).to("cuda")
# set scheduler
pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
# load LCM-LoRA
pipe.load_lora_weights("latent-consistency/lcm-lora-sdxl")
pipe.fuse_lora()
# load base and mask image
init_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/inpaint.png").resize((1024, 1024))
mask_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/inpaint_mask.png").resize((1024, 1024))
prompt = "a castle on top of a mountain, highly detailed, 8k"
generator = torch.manual_seed(42)
image = pipe(
prompt=prompt,
image=init_image,
mask_image=mask_image,
generator=generator,
num_inference_steps=5,
guidance_scale=4,
).images[0]
make_image_grid([init_image, mask_image, image], rows=1, cols=3)
```
## Combine with styled LoRAs
LCM-LoRA can be combined with other LoRAs to generate styled-images in very few steps (4-8). In the following example, we'll use the LCM-LoRA with the [papercut LoRA](TheLastBen/Papercut_SDXL).
To learn more about how to combine LoRAs, refer to [this guide](https://huggingface.co/docs/diffusers/tutorials/using_peft_for_inference#combine-multiple-adapters).
```python
import torch
from diffusers import DiffusionPipeline, LCMScheduler
pipe = DiffusionPipeline.from_pretrained(
"stabilityai/stable-diffusion-xl-base-1.0",
variant="fp16",
torch_dtype=torch.float16
).to("cuda")
# set scheduler
pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
# load LoRAs
pipe.load_lora_weights("latent-consistency/lcm-lora-sdxl", adapter_name="lcm")
pipe.load_lora_weights("TheLastBen/Papercut_SDXL", weight_name="papercut.safetensors", adapter_name="papercut")
# Combine LoRAs
pipe.set_adapters(["lcm", "papercut"], adapter_weights=[1.0, 0.8])
prompt = "papercut, a cute fox"
generator = torch.manual_seed(0)
image = pipe(prompt, num_inference_steps=4, guidance_scale=1, generator=generator).images[0]
image
```
### ControlNet
```python
import torch
import cv2
import numpy as np
from PIL import Image
from diffusers import StableDiffusionXLControlNetPipeline, ControlNetModel, LCMScheduler
from diffusers.utils import load_image
image = load_image(
"https://hf.co/datasets/huggingface/documentation-images/resolve/main/diffusers/input_image_vermeer.png"
).resize((1024, 1024))
image = np.array(image)
low_threshold = 100
high_threshold = 200
image = cv2.Canny(image, low_threshold, high_threshold)
image = image[:, :, None]
image = np.concatenate([image, image, image], axis=2)
canny_image = Image.fromarray(image)
controlnet = ControlNetModel.from_pretrained("diffusers/controlnet-canny-sdxl-1.0-small", torch_dtype=torch.float16, variant="fp16")
pipe = StableDiffusionXLControlNetPipeline.from_pretrained(
"stabilityai/stable-diffusion-xl-base-1.0",
controlnet=controlnet,
torch_dtype=torch.float16,
safety_checker=None,
variant="fp16"
).to("cuda")
# set scheduler
pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
# load LCM-LoRA
pipe.load_lora_weights("latent-consistency/lcm-lora-sdxl")
pipe.fuse_lora()
generator = torch.manual_seed(0)
image = pipe(
"picture of the mona lisa",
image=canny_image,
num_inference_steps=5,
guidance_scale=1.5,
controlnet_conditioning_scale=0.5,
cross_attention_kwargs={"scale": 1},
generator=generator,
).images[0]
make_image_grid([canny_image, image], rows=1, cols=2)
```
<Tip>
The inference parameters in this example might not work for all examples, so we recommend you to try different values for `num_inference_steps`, `guidance_scale`, `controlnet_conditioning_scale` and `cross_attention_kwargs` parameters and choose the best one.
</Tip>
### T2I Adapter
This example shows how to use the LCM-LoRA with the [Canny T2I-Adapter](TencentARC/t2i-adapter-canny-sdxl-1.0) and SDXL.
```python
import torch
import cv2
import numpy as np
from PIL import Image
from diffusers import StableDiffusionXLAdapterPipeline, T2IAdapter, LCMScheduler
from diffusers.utils import load_image, make_image_grid
# Prepare image
# Detect the canny map in low resolution to avoid high-frequency details
image = load_image(
"https://huggingface.co/Adapter/t2iadapter/resolve/main/figs_SDXLV1.0/org_canny.jpg"
).resize((384, 384))
image = np.array(image)
low_threshold = 100
high_threshold = 200
image = cv2.Canny(image, low_threshold, high_threshold)
image = image[:, :, None]
image = np.concatenate([image, image, image], axis=2)
canny_image = Image.fromarray(image).resize((1024, 1024))
# load adapter
adapter = T2IAdapter.from_pretrained("TencentARC/t2i-adapter-canny-sdxl-1.0", torch_dtype=torch.float16, varient="fp16").to("cuda")
pipe = StableDiffusionXLAdapterPipeline.from_pretrained(
"stabilityai/stable-diffusion-xl-base-1.0",
adapter=adapter,
torch_dtype=torch.float16,
variant="fp16",
).to("cuda")
# set scheduler
pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
# load LCM-LoRA
pipe.load_lora_weights("latent-consistency/lcm-lora-sdxl")
prompt = "Mystical fairy in real, magic, 4k picture, high quality"
negative_prompt = "extra digit, fewer digits, cropped, worst quality, low quality, glitch, deformed, mutated, ugly, disfigured"
generator = torch.manual_seed(0)
image = pipe(
prompt=prompt,
negative_prompt=negative_prompt,
image=canny_image,
num_inference_steps=4,
guidance_scale=1.5,
adapter_conditioning_scale=0.8,
adapter_conditioning_factor=1,
generator=generator,
).images[0]
make_image_grid([canny_image, image], rows=1, cols=2)
```
## Speed Benchmark
TODO
## Training
TODO
|
coffeepowered/arctic-l-enhanced
|
coffeepowered
| 2025-03-05T10:02:32Z | 0 | 0 |
sentence-transformers
|
[
"sentence-transformers",
"safetensors",
"xlm-roberta",
"sentence-similarity",
"feature-extraction",
"generated_from_trainer",
"loss:CosineSimilarityLoss",
"arxiv:1908.10084",
"base_model:Snowflake/snowflake-arctic-embed-l-v2.0",
"base_model:finetune:Snowflake/snowflake-arctic-embed-l-v2.0",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] |
sentence-similarity
| 2025-03-05T10:01:12Z |
---
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- loss:CosineSimilarityLoss
base_model: Snowflake/snowflake-arctic-embed-l-v2.0
pipeline_tag: sentence-similarity
library_name: sentence-transformers
---
# SentenceTransformer based on Snowflake/snowflake-arctic-embed-l-v2.0
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Snowflake/snowflake-arctic-embed-l-v2.0](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) on the json dataset. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
## Model Details
### Model Description
- **Model Type:** Sentence Transformer
- **Base model:** [Snowflake/snowflake-arctic-embed-l-v2.0](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) <!-- at revision 7f311bb640ad3babc0a4e3a8873240dcba44c9d2 -->
- **Maximum Sequence Length:** 8192 tokens
- **Output Dimensionality:** 1024 dimensions
- **Similarity Function:** Cosine Similarity
- **Training Dataset:**
- json
<!-- - **Language:** Unknown -->
<!-- - **License:** Unknown -->
### Model Sources
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
### Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 8192, 'do_lower_case': False}) with Transformer model: XLMRobertaModel
(1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
(2): Normalize()
)
```
## Usage
### Direct Usage (Sentence Transformers)
First install the Sentence Transformers library:
```bash
pip install -U sentence-transformers
```
Then you can load this model and run inference.
```python
from sentence_transformers import SentenceTransformer
# Download from the 🤗 Hub
model = SentenceTransformer("coffeepowered/arctic-l-enhanced")
# Run inference
sentences = [
'The weather is lovely today.',
"It's so sunny outside!",
'He drove to the stadium.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]
# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]
```
<!--
### Direct Usage (Transformers)
<details><summary>Click to see the direct usage in Transformers</summary>
</details>
-->
<!--
### Downstream Usage (Sentence Transformers)
You can finetune this model on your own dataset.
<details><summary>Click to expand</summary>
</details>
-->
<!--
### Out-of-Scope Use
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
-->
<!--
## Bias, Risks and Limitations
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
-->
<!--
### Recommendations
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
-->
## Training Details
### Training Dataset
#### json
* Dataset: json
* Columns: <code>sentence1</code>, <code>sentence2</code>, <code>score</code>, and <code>split</code>
* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
```json
{
"loss_fct": "torch.nn.modules.loss.MSELoss"
}
```
### Evaluation Dataset
#### json
* Dataset: json
* Columns: <code>sentence1</code>, <code>sentence2</code>, <code>score</code>, and <code>split</code>
* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
```json
{
"loss_fct": "torch.nn.modules.loss.MSELoss"
}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `eval_strategy`: steps
- `learning_rate`: 4.000000000000001e-06
- `max_steps`: 13938
- `warmup_ratio`: 0.1
- `fp16`: True
- `load_best_model_at_end`: True
#### All Hyperparameters
<details><summary>Click to expand</summary>
- `overwrite_output_dir`: False
- `do_predict`: False
- `eval_strategy`: steps
- `prediction_loss_only`: True
- `per_device_train_batch_size`: 8
- `per_device_eval_batch_size`: 8
- `per_gpu_train_batch_size`: None
- `per_gpu_eval_batch_size`: None
- `gradient_accumulation_steps`: 1
- `eval_accumulation_steps`: None
- `torch_empty_cache_steps`: None
- `learning_rate`: 4.000000000000001e-06
- `weight_decay`: 0.0
- `adam_beta1`: 0.9
- `adam_beta2`: 0.999
- `adam_epsilon`: 1e-08
- `max_grad_norm`: 1.0
- `num_train_epochs`: 3
- `max_steps`: 13938
- `lr_scheduler_type`: linear
- `lr_scheduler_kwargs`: {}
- `warmup_ratio`: 0.1
- `warmup_steps`: 0
- `log_level`: passive
- `log_level_replica`: warning
- `log_on_each_node`: True
- `logging_nan_inf_filter`: True
- `save_safetensors`: True
- `save_on_each_node`: False
- `save_only_model`: False
- `restore_callback_states_from_checkpoint`: False
- `no_cuda`: False
- `use_cpu`: False
- `use_mps_device`: False
- `seed`: 42
- `data_seed`: None
- `jit_mode_eval`: False
- `use_ipex`: False
- `bf16`: False
- `fp16`: True
- `fp16_opt_level`: O1
- `half_precision_backend`: auto
- `bf16_full_eval`: False
- `fp16_full_eval`: False
- `tf32`: None
- `local_rank`: 0
- `ddp_backend`: None
- `tpu_num_cores`: None
- `tpu_metrics_debug`: False
- `debug`: []
- `dataloader_drop_last`: False
- `dataloader_num_workers`: 0
- `dataloader_prefetch_factor`: None
- `past_index`: -1
- `disable_tqdm`: False
- `remove_unused_columns`: True
- `label_names`: None
- `load_best_model_at_end`: True
- `ignore_data_skip`: False
- `fsdp`: []
- `fsdp_min_num_params`: 0
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
- `fsdp_transformer_layer_cls_to_wrap`: None
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
- `deepspeed`: None
- `label_smoothing_factor`: 0.0
- `optim`: adamw_torch
- `optim_args`: None
- `adafactor`: False
- `group_by_length`: False
- `length_column_name`: length
- `ddp_find_unused_parameters`: None
- `ddp_bucket_cap_mb`: None
- `ddp_broadcast_buffers`: False
- `dataloader_pin_memory`: True
- `dataloader_persistent_workers`: False
- `skip_memory_metrics`: True
- `use_legacy_prediction_loop`: False
- `push_to_hub`: False
- `resume_from_checkpoint`: None
- `hub_model_id`: None
- `hub_strategy`: every_save
- `hub_private_repo`: None
- `hub_always_push`: False
- `gradient_checkpointing`: False
- `gradient_checkpointing_kwargs`: None
- `include_inputs_for_metrics`: False
- `include_for_metrics`: []
- `eval_do_concat_batches`: True
- `fp16_backend`: auto
- `push_to_hub_model_id`: None
- `push_to_hub_organization`: None
- `mp_parameters`:
- `auto_find_batch_size`: False
- `full_determinism`: False
- `torchdynamo`: None
- `ray_scope`: last
- `ddp_timeout`: 1800
- `torch_compile`: False
- `torch_compile_backend`: None
- `torch_compile_mode`: None
- `dispatch_batches`: None
- `split_batches`: None
- `include_tokens_per_second`: False
- `include_num_input_tokens_seen`: False
- `neftune_noise_alpha`: None
- `optim_target_modules`: None
- `batch_eval_metrics`: False
- `eval_on_start`: False
- `use_liger_kernel`: False
- `eval_use_gather_object`: False
- `average_tokens_across_devices`: False
- `prompts`: None
- `batch_sampler`: batch_sampler
- `multi_dataset_batch_sampler`: proportional
</details>
### Training Logs
<details><summary>Click to expand</summary>
| Epoch | Step | Training Loss | Validation Loss |
|:----------:|:--------:|:-------------:|:---------------:|
| 0.0007 | 10 | 0.1359 | - |
| 0.0014 | 20 | 0.1202 | - |
| 0.0022 | 30 | 0.1314 | - |
| 0.0029 | 40 | 0.1302 | - |
| 0.0036 | 50 | 0.1158 | - |
| 0.0043 | 60 | 0.1158 | - |
| 0.0050 | 70 | 0.1114 | - |
| 0.0057 | 80 | 0.1316 | - |
| 0.0065 | 90 | 0.133 | - |
| 0.0072 | 100 | 0.0958 | - |
| 0.0079 | 110 | 0.0973 | - |
| 0.0086 | 120 | 0.0949 | - |
| 0.0093 | 130 | 0.0892 | - |
| 0.0100 | 140 | 0.0867 | - |
| 0.0108 | 150 | 0.0717 | 0.0712 |
| 0.0115 | 160 | 0.0762 | - |
| 0.0122 | 170 | 0.0828 | - |
| 0.0129 | 180 | 0.0775 | - |
| 0.0136 | 190 | 0.0614 | - |
| 0.0143 | 200 | 0.0748 | - |
| 0.0151 | 210 | 0.0545 | - |
| 0.0158 | 220 | 0.0725 | - |
| 0.0165 | 230 | 0.0627 | - |
| 0.0172 | 240 | 0.0612 | - |
| 0.0179 | 250 | 0.0508 | - |
| 0.0187 | 260 | 0.0592 | - |
| 0.0194 | 270 | 0.0489 | - |
| 0.0201 | 280 | 0.0545 | - |
| 0.0208 | 290 | 0.0598 | - |
| 0.0215 | 300 | 0.0641 | 0.0566 |
| 0.0222 | 310 | 0.0554 | - |
| 0.0230 | 320 | 0.0523 | - |
| 0.0237 | 330 | 0.0568 | - |
| 0.0244 | 340 | 0.0594 | - |
| 0.0251 | 350 | 0.0488 | - |
| 0.0258 | 360 | 0.06 | - |
| 0.0265 | 370 | 0.0737 | - |
| 0.0273 | 380 | 0.0565 | - |
| 0.0280 | 390 | 0.0456 | - |
| 0.0287 | 400 | 0.0489 | - |
| 0.0294 | 410 | 0.0478 | - |
| 0.0301 | 420 | 0.0481 | - |
| 0.0309 | 430 | 0.0541 | - |
| 0.0316 | 440 | 0.0581 | - |
| 0.0323 | 450 | 0.0549 | 0.0578 |
| 0.0330 | 460 | 0.042 | - |
| 0.0337 | 470 | 0.0451 | - |
| 0.0344 | 480 | 0.0537 | - |
| 0.0352 | 490 | 0.0487 | - |
| 0.0359 | 500 | 0.0444 | - |
| 0.0366 | 510 | 0.0443 | - |
| 0.0373 | 520 | 0.0418 | - |
| 0.0380 | 530 | 0.0447 | - |
| 0.0387 | 540 | 0.0453 | - |
| 0.0395 | 550 | 0.0465 | - |
| 0.0402 | 560 | 0.0623 | - |
| 0.0409 | 570 | 0.0507 | - |
| 0.0416 | 580 | 0.0428 | - |
| 0.0423 | 590 | 0.0494 | - |
| 0.0430 | 600 | 0.0407 | 0.0519 |
| 0.0438 | 610 | 0.0452 | - |
| 0.0445 | 620 | 0.0439 | - |
| 0.0452 | 630 | 0.0534 | - |
| 0.0459 | 640 | 0.0422 | - |
| 0.0466 | 650 | 0.0514 | - |
| 0.0474 | 660 | 0.0406 | - |
| 0.0481 | 670 | 0.0428 | - |
| 0.0488 | 680 | 0.0346 | - |
| 0.0495 | 690 | 0.0485 | - |
| 0.0502 | 700 | 0.0549 | - |
| 0.0509 | 710 | 0.0399 | - |
| 0.0517 | 720 | 0.0362 | - |
| 0.0524 | 730 | 0.0507 | - |
| 0.0531 | 740 | 0.0434 | - |
| 0.0538 | 750 | 0.0363 | 0.0553 |
| 0.0545 | 760 | 0.0426 | - |
| 0.0552 | 770 | 0.0375 | - |
| 0.0560 | 780 | 0.0501 | - |
| 0.0567 | 790 | 0.043 | - |
| 0.0574 | 800 | 0.0476 | - |
| 0.0581 | 810 | 0.037 | - |
| 0.0588 | 820 | 0.0317 | - |
| 0.0595 | 830 | 0.0387 | - |
| 0.0603 | 840 | 0.0348 | - |
| 0.0610 | 850 | 0.0379 | - |
| 0.0617 | 860 | 0.0506 | - |
| 0.0624 | 870 | 0.0419 | - |
| 0.0631 | 880 | 0.0431 | - |
| 0.0639 | 890 | 0.0478 | - |
| 0.0646 | 900 | 0.0394 | 0.0571 |
| 0.0653 | 910 | 0.0334 | - |
| 0.0660 | 920 | 0.0384 | - |
| 0.0667 | 930 | 0.0381 | - |
| 0.0674 | 940 | 0.0343 | - |
| 0.0682 | 950 | 0.0355 | - |
| 0.0689 | 960 | 0.0384 | - |
| 0.0696 | 970 | 0.0352 | - |
| 0.0703 | 980 | 0.0479 | - |
| 0.0710 | 990 | 0.0362 | - |
| 0.0717 | 1000 | 0.0357 | - |
| 0.0725 | 1010 | 0.0414 | - |
| 0.0732 | 1020 | 0.0346 | - |
| 0.0739 | 1030 | 0.039 | - |
| 0.0746 | 1040 | 0.0317 | - |
| 0.0753 | 1050 | 0.0502 | 0.0523 |
| 0.0761 | 1060 | 0.0407 | - |
| 0.0768 | 1070 | 0.0377 | - |
| 0.0775 | 1080 | 0.0404 | - |
| 0.0782 | 1090 | 0.0297 | - |
| 0.0789 | 1100 | 0.0344 | - |
| 0.0796 | 1110 | 0.0277 | - |
| 0.0804 | 1120 | 0.0453 | - |
| 0.0811 | 1130 | 0.0469 | - |
| 0.0818 | 1140 | 0.044 | - |
| 0.0825 | 1150 | 0.0339 | - |
| 0.0832 | 1160 | 0.0331 | - |
| 0.0839 | 1170 | 0.0327 | - |
| 0.0847 | 1180 | 0.0445 | - |
| 0.0854 | 1190 | 0.0392 | - |
| 0.0861 | 1200 | 0.048 | 0.0531 |
| 0.0868 | 1210 | 0.0375 | - |
| 0.0875 | 1220 | 0.0311 | - |
| 0.0882 | 1230 | 0.037 | - |
| 0.0890 | 1240 | 0.0369 | - |
| 0.0897 | 1250 | 0.0398 | - |
| 0.0904 | 1260 | 0.0363 | - |
| 0.0911 | 1270 | 0.0425 | - |
| 0.0918 | 1280 | 0.0355 | - |
| 0.0926 | 1290 | 0.0362 | - |
| 0.0933 | 1300 | 0.0354 | - |
| 0.0940 | 1310 | 0.0252 | - |
| 0.0947 | 1320 | 0.03 | - |
| 0.0954 | 1330 | 0.03 | - |
| 0.0961 | 1340 | 0.0218 | - |
| 0.0969 | 1350 | 0.0248 | 0.0448 |
| 0.0976 | 1360 | 0.0287 | - |
| 0.0983 | 1370 | 0.0322 | - |
| 0.0990 | 1380 | 0.0359 | - |
| 0.0997 | 1390 | 0.0287 | - |
| 0.1004 | 1400 | 0.034 | - |
| 0.1012 | 1410 | 0.0305 | - |
| 0.1019 | 1420 | 0.0241 | - |
| 0.1026 | 1430 | 0.0227 | - |
| 0.1033 | 1440 | 0.0279 | - |
| 0.1040 | 1450 | 0.0298 | - |
| 0.1047 | 1460 | 0.0382 | - |
| 0.1055 | 1470 | 0.0269 | - |
| 0.1062 | 1480 | 0.0243 | - |
| 0.1069 | 1490 | 0.0266 | - |
| 0.1076 | 1500 | 0.016 | 0.0456 |
| 0.1083 | 1510 | 0.0233 | - |
| 0.1091 | 1520 | 0.0247 | - |
| 0.1098 | 1530 | 0.0233 | - |
| 0.1105 | 1540 | 0.0214 | - |
| 0.1112 | 1550 | 0.0229 | - |
| 0.1119 | 1560 | 0.0145 | - |
| 0.1126 | 1570 | 0.0187 | - |
| 0.1134 | 1580 | 0.0231 | - |
| 0.1141 | 1590 | 0.0268 | - |
| 0.1148 | 1600 | 0.027 | - |
| 0.1155 | 1610 | 0.0354 | - |
| 0.1162 | 1620 | 0.0398 | - |
| 0.1169 | 1630 | 0.0431 | - |
| 0.1177 | 1640 | 0.0391 | - |
| 0.1184 | 1650 | 0.056 | 0.0422 |
| 0.1191 | 1660 | 0.0394 | - |
| 0.1198 | 1670 | 0.0338 | - |
| 0.1205 | 1680 | 0.0417 | - |
| 0.1213 | 1690 | 0.0479 | - |
| 0.1220 | 1700 | 0.0348 | - |
| 0.1227 | 1710 | 0.0366 | - |
| 0.1234 | 1720 | 0.0335 | - |
| 0.1241 | 1730 | 0.0367 | - |
| 0.1248 | 1740 | 0.0355 | - |
| 0.1256 | 1750 | 0.0319 | - |
| 0.1263 | 1760 | 0.0324 | - |
| 0.1270 | 1770 | 0.0345 | - |
| 0.1277 | 1780 | 0.0352 | - |
| 0.1284 | 1790 | 0.0362 | - |
| 0.1291 | 1800 | 0.0319 | 0.0388 |
| 0.1299 | 1810 | 0.0381 | - |
| 0.1306 | 1820 | 0.0368 | - |
| 0.1313 | 1830 | 0.0318 | - |
| 0.1320 | 1840 | 0.0296 | - |
| 0.1327 | 1850 | 0.0331 | - |
| 0.1334 | 1860 | 0.0381 | - |
| 0.1342 | 1870 | 0.0237 | - |
| 0.1349 | 1880 | 0.0284 | - |
| 0.1356 | 1890 | 0.0353 | - |
| 0.1363 | 1900 | 0.0408 | - |
| 0.1370 | 1910 | 0.0277 | - |
| 0.1378 | 1920 | 0.0268 | - |
| 0.1385 | 1930 | 0.0348 | - |
| 0.1392 | 1940 | 0.0348 | - |
| 0.1399 | 1950 | 0.0269 | 0.0351 |
| 0.1406 | 1960 | 0.0317 | - |
| 0.1413 | 1970 | 0.0375 | - |
| 0.1421 | 1980 | 0.0321 | - |
| 0.1428 | 1990 | 0.0302 | - |
| 0.1435 | 2000 | 0.0411 | - |
| 0.1442 | 2010 | 0.0329 | - |
| 0.1449 | 2020 | 0.0246 | - |
| 0.1456 | 2030 | 0.0288 | - |
| 0.1464 | 2040 | 0.0297 | - |
| 0.1471 | 2050 | 0.0285 | - |
| 0.1478 | 2060 | 0.0326 | - |
| 0.1485 | 2070 | 0.035 | - |
| 0.1492 | 2080 | 0.0208 | - |
| 0.1499 | 2090 | 0.0209 | - |
| 0.1507 | 2100 | 0.0303 | 0.0364 |
| 0.1514 | 2110 | 0.028 | - |
| 0.1521 | 2120 | 0.0366 | - |
| 0.1528 | 2130 | 0.033 | - |
| 0.1535 | 2140 | 0.0353 | - |
| 0.1543 | 2150 | 0.0292 | - |
| 0.1550 | 2160 | 0.0202 | - |
| 0.1557 | 2170 | 0.0233 | - |
| 0.1564 | 2180 | 0.0346 | - |
| 0.1571 | 2190 | 0.0309 | - |
| 0.1578 | 2200 | 0.0241 | - |
| 0.1586 | 2210 | 0.0317 | - |
| 0.1593 | 2220 | 0.0331 | - |
| 0.1600 | 2230 | 0.0273 | - |
| 0.1607 | 2240 | 0.0219 | - |
| 0.1614 | 2250 | 0.0256 | 0.0338 |
| 0.1621 | 2260 | 0.024 | - |
| 0.1629 | 2270 | 0.0216 | - |
| 0.1636 | 2280 | 0.0253 | - |
| 0.1643 | 2290 | 0.0271 | - |
| 0.1650 | 2300 | 0.0336 | - |
| 0.1657 | 2310 | 0.0273 | - |
| 0.1665 | 2320 | 0.0267 | - |
| 0.1672 | 2330 | 0.0292 | - |
| 0.1679 | 2340 | 0.0269 | - |
| 0.1686 | 2350 | 0.0342 | - |
| 0.1693 | 2360 | 0.0361 | - |
| 0.1700 | 2370 | 0.0224 | - |
| 0.1708 | 2380 | 0.016 | - |
| 0.1715 | 2390 | 0.0209 | - |
| **0.1722** | **2400** | **0.0162** | **0.0329** |
| 0.1729 | 2410 | 0.019 | - |
| 0.1736 | 2420 | 0.0181 | - |
| 0.1743 | 2430 | 0.0332 | - |
| 0.1751 | 2440 | 0.0189 | - |
| 0.1758 | 2450 | 0.0292 | - |
| 0.1765 | 2460 | 0.0193 | - |
| 0.1772 | 2470 | 0.024 | - |
| 0.1779 | 2480 | 0.0245 | - |
| 0.1786 | 2490 | 0.02 | - |
| 0.1794 | 2500 | 0.0187 | - |
| 0.1801 | 2510 | 0.0224 | - |
| 0.1808 | 2520 | 0.028 | - |
| 0.1815 | 2530 | 0.0219 | - |
| 0.1822 | 2540 | 0.0212 | - |
| 0.1830 | 2550 | 0.0208 | 0.0354 |
| 0.1837 | 2560 | 0.0299 | - |
| 0.1844 | 2570 | 0.0208 | - |
| 0.1851 | 2580 | 0.0271 | - |
| 0.1858 | 2590 | 0.0146 | - |
| 0.1865 | 2600 | 0.0163 | - |
| 0.1873 | 2610 | 0.0149 | - |
| 0.1880 | 2620 | 0.0145 | - |
| 0.1887 | 2630 | 0.0196 | - |
| 0.1894 | 2640 | 0.0252 | - |
| 0.1901 | 2650 | 0.0173 | - |
| 0.1908 | 2660 | 0.0202 | - |
| 0.1916 | 2670 | 0.0171 | - |
| 0.1923 | 2680 | 0.023 | - |
| 0.1930 | 2690 | 0.02 | - |
| 0.1937 | 2700 | 0.0171 | 0.0387 |
| 0.1944 | 2710 | 0.0239 | - |
| 0.1951 | 2720 | 0.0261 | - |
| 0.1959 | 2730 | 0.0197 | - |
| 0.1966 | 2740 | 0.0195 | - |
| 0.1973 | 2750 | 0.0132 | - |
| 0.1980 | 2760 | 0.0226 | - |
| 0.1987 | 2770 | 0.0172 | - |
| 0.1995 | 2780 | 0.0214 | - |
| 0.2002 | 2790 | 0.0173 | - |
| 0.2009 | 2800 | 0.0179 | - |
| 0.2016 | 2810 | 0.0184 | - |
| 0.2023 | 2820 | 0.0162 | - |
| 0.2030 | 2830 | 0.0126 | - |
| 0.2038 | 2840 | 0.0188 | - |
| 0.2045 | 2850 | 0.0177 | 0.0385 |
| 0.2052 | 2860 | 0.0153 | - |
| 0.2059 | 2870 | 0.0137 | - |
| 0.2066 | 2880 | 0.0174 | - |
| 0.2073 | 2890 | 0.0148 | - |
| 0.2081 | 2900 | 0.0194 | - |
| 0.2088 | 2910 | 0.0133 | - |
| 0.2095 | 2920 | 0.0152 | - |
| 0.2102 | 2930 | 0.0179 | - |
| 0.2109 | 2940 | 0.0187 | - |
| 0.2117 | 2950 | 0.0161 | - |
| 0.2124 | 2960 | 0.0185 | - |
| 0.2131 | 2970 | 0.0151 | - |
| 0.2138 | 2980 | 0.0194 | - |
| 0.2145 | 2990 | 0.0179 | - |
| 0.2152 | 3000 | 0.0115 | 0.0434 |
| 0.2160 | 3010 | 0.0183 | - |
| 0.2167 | 3020 | 0.0168 | - |
| 0.2174 | 3030 | 0.0137 | - |
| 0.2181 | 3040 | 0.0196 | - |
| 0.2188 | 3050 | 0.0145 | - |
| 0.2195 | 3060 | 0.0164 | - |
| 0.2203 | 3070 | 0.0132 | - |
| 0.2210 | 3080 | 0.0133 | - |
| 0.2217 | 3090 | 0.0154 | - |
| 0.2224 | 3100 | 0.0145 | - |
| 0.2231 | 3110 | 0.0135 | - |
| 0.2238 | 3120 | 0.0143 | - |
| 0.2246 | 3130 | 0.0197 | - |
| 0.2253 | 3140 | 0.0163 | - |
| 0.2260 | 3150 | 0.017 | 0.0409 |
| 0.2267 | 3160 | 0.0257 | - |
| 0.2274 | 3170 | 0.0165 | - |
| 0.2282 | 3180 | 0.0189 | - |
| 0.2289 | 3190 | 0.0207 | - |
| 0.2296 | 3200 | 0.0179 | - |
| 0.2303 | 3210 | 0.0152 | - |
| 0.2310 | 3220 | 0.0179 | - |
| 0.2317 | 3230 | 0.0187 | - |
| 0.2325 | 3240 | 0.0189 | - |
| 0.2332 | 3250 | 0.0151 | - |
| 0.2339 | 3260 | 0.0137 | - |
| 0.2346 | 3270 | 0.0122 | - |
| 0.2353 | 3280 | 0.0134 | - |
| 0.2360 | 3290 | 0.0134 | - |
| 0.2368 | 3300 | 0.0162 | 0.0455 |
| 0.2375 | 3310 | 0.0142 | - |
| 0.2382 | 3320 | 0.0203 | - |
| 0.2389 | 3330 | 0.0148 | - |
| 0.2396 | 3340 | 0.0181 | - |
| 0.2404 | 3350 | 0.0178 | - |
| 0.2411 | 3360 | 0.018 | - |
| 0.2418 | 3370 | 0.012 | - |
| 0.2425 | 3380 | 0.0201 | - |
| 0.2432 | 3390 | 0.0193 | - |
| 0.2439 | 3400 | 0.013 | - |
| 0.2447 | 3410 | 0.0114 | - |
| 0.2454 | 3420 | 0.0184 | - |
| 0.2461 | 3430 | 0.0153 | - |
| 0.2468 | 3440 | 0.0172 | - |
| 0.2475 | 3450 | 0.0141 | 0.0458 |
| 0.2482 | 3460 | 0.0165 | - |
| 0.2490 | 3470 | 0.0174 | - |
| 0.2497 | 3480 | 0.0109 | - |
| 0.2504 | 3490 | 0.0177 | - |
| 0.2511 | 3500 | 0.0178 | - |
| 0.2518 | 3510 | 0.0101 | - |
| 0.2525 | 3520 | 0.0154 | - |
| 0.2533 | 3530 | 0.0204 | - |
| 0.2540 | 3540 | 0.0119 | - |
| 0.2547 | 3550 | 0.0158 | - |
| 0.2554 | 3560 | 0.0161 | - |
| 0.2561 | 3570 | 0.0116 | - |
| 0.2569 | 3580 | 0.0183 | - |
| 0.2576 | 3590 | 0.0125 | - |
| 0.2583 | 3600 | 0.0148 | 0.0475 |
| 0.2590 | 3610 | 0.0184 | - |
| 0.2597 | 3620 | 0.0169 | - |
| 0.2604 | 3630 | 0.0135 | - |
| 0.2612 | 3640 | 0.0138 | - |
| 0.2619 | 3650 | 0.0133 | - |
| 0.2626 | 3660 | 0.0148 | - |
| 0.2633 | 3670 | 0.0121 | - |
| 0.2640 | 3680 | 0.0119 | - |
| 0.2647 | 3690 | 0.0183 | - |
| 0.2655 | 3700 | 0.0178 | - |
| 0.2662 | 3710 | 0.0139 | - |
| 0.2669 | 3720 | 0.0171 | - |
| 0.2676 | 3730 | 0.0155 | - |
| 0.2683 | 3740 | 0.0173 | - |
| 0.2690 | 3750 | 0.0158 | 0.0488 |
| 0.2698 | 3760 | 0.0125 | - |
| 0.2705 | 3770 | 0.0137 | - |
| 0.2712 | 3780 | 0.0184 | - |
| 0.2719 | 3790 | 0.0117 | - |
| 0.2726 | 3800 | 0.0189 | - |
| 0.2734 | 3810 | 0.0163 | - |
| 0.2741 | 3820 | 0.0163 | - |
| 0.2748 | 3830 | 0.0212 | - |
| 0.2755 | 3840 | 0.0133 | - |
| 0.2762 | 3850 | 0.0168 | - |
| 0.2769 | 3860 | 0.0197 | - |
| 0.2777 | 3870 | 0.0184 | - |
| 0.2784 | 3880 | 0.017 | - |
| 0.2791 | 3890 | 0.0173 | - |
| 0.2798 | 3900 | 0.0165 | 0.0511 |
* The bold row denotes the saved checkpoint.
</details>
### Framework Versions
- Python: 3.10.14
- Sentence Transformers: 3.4.1
- Transformers: 4.49.0
- PyTorch: 2.2.2
- Accelerate: 1.4.0
- Datasets: 3.3.2
- Tokenizers: 0.21.0
## Citation
### BibTeX
#### Sentence Transformers
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "https://arxiv.org/abs/1908.10084",
}
```
<!--
## Glossary
*Clearly define terms in order to be accessible across audiences.*
-->
<!--
## Model Card Authors
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->
<!--
## Model Card Contact
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
-->
|
texanrangee/86c24bdc-b809-444f-87d7-e621d59cca9c
|
texanrangee
| 2025-03-05T10:01:55Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"unsloth",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-03-05T06:18:40Z |
---
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]
|
Bunpot/llama3.1-8b-finetune-spa-onsen
|
Bunpot
| 2025-03-05T10:01:19Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-03-05T10:01:10Z |
---
base_model: unsloth/meta-llama-3.1-8b-instruct-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** Bunpot
- **License:** apache-2.0
- **Finetuned from model :** unsloth/meta-llama-3.1-8b-instruct-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
soham0007/LunarLander-v2
|
soham0007
| 2025-03-05T10:01:03Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2025-03-05T09:58:35Z |
---
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: 253.93 +/- 22.01
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
...
```
|
loaiabdalslam/beetelware-saudi-R1-Distill-Llama-8B
|
loaiabdalslam
| 2025-03-05T10:00:03Z | 0 | 2 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"generated_from_trainer",
"unsloth",
"trl",
"sft",
"ar",
"en",
"dataset:MohAlbrayh/saudi-allam-sft-dataset-2M",
"doi:10.57967/hf/4389",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-02-04T04:46:44Z |
---
base_model: unsloth/deepseek-r1-distill-llama-8b-unsloth-bnb-4bit
library_name: transformers
model_name: outputs
tags:
- generated_from_trainer
- unsloth
- trl
- sft
licence: license
license: apache-2.0
datasets:
- MohAlbrayh/saudi-allam-sft-dataset-2M
metrics:
- accuracy
new_version: unsloth/DeepSeek-R1-Distill-Llama-8B-unsloth-bnb-4bit
language:
- ar
- en
---
# Model Card for outputs
This model is a fine-tuned version of [unsloth/deepseek-r1-distill-llama-8b-unsloth-bnb-4bit](https://huggingface.co/unsloth/deepseek-r1-distill-llama-8b-unsloth-bnb-4bit).
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
question = """ترجم النص التالي الي اللهجة الحجازية من فضلك يا بلال : انا اسمي لؤي عبد السلام أسكن في الاسكندرية بمصر مدينة الاسكندرية في مصر أدرس ذكاء اصطناعي"""
# Define a system prompt under prompt_style
prompt_style = """Below is an instruction that describes a task, paired with an input that provides further context.
Write a response that appropriately completes the request.
Before answering, think carefully about the question and create a step-by-step chain of thoughts to ensure a logical and accurate response .
### Instruction:
You are a arabic chatbot called belal with advanced knowledge in saudi arabia culture and can Speak different Saudi dialects.
Please answer the following client question in arabic .
### Question:
{}
### Response:
<think>{}"""
prompt = prompt_style.format(question, "")
....[Using the Model to predict]
```
```json
<think>
أنا أفكر في السؤال اللي طرحته: ترجم، النص، التالي، الي، اللهجة، الحجازية، فضلك، يا، بلال، انا، اسمي، لؤي، عبد، السلام، أسكن، الاسكندرية، بمصر، مدينة، الاسكندرية، مصر، أدرس، ذكاء، اصطناعي 💭
ألاحظ أن الإجابة تحتوي على معلومات مرتبطة بالسؤال: ذكاء، مصر، اصطناعي، اسمي 👍.
أرى أن الإجابة أضافت بعض المعلومات مثل: في، عشان، لؤي، أبدي، عبد، أشتغل، أسكن، بلال، أسكندرية، لما 🤔.
لكن فيه كلمات ما ظهرت في الإجابة رغم وجودها في السؤال: لؤي، من، الفضلك، اسكن، اسمي، انا، التالي، اسمي، السلام، ترجم، أدرس، يا، اسكندرية، النص، بمصر، اللهجة، الحجازية، يا، بلال، مدينة، الاسكندرية، عبد، الفضل، التالي، لؤي، يصير، عبد، اصطناعي 🤨.
الإجابة ناقصة شوية مقارنة بالسؤال، يعني ممكن ما تكون كاملة 😕.
إذا قيمت التفكير المنطقي للإجابة، بتكون -11 من 5 نجوم 🌟.
وهذا هو منهجي في التفكير حول الحل 💡:
بدايةً، أفكر في السؤال وأحاول تحديد الكلمات المفتاحية اللي توضح المطلوب بالضبط 💭.
بعدها، أقارن الإجابة مع الكلمات المفتاحية لأشوف إذا كانت تفي بالغرض أو لا 🤔.
أحلل الإجابة بعناية وأشوف إذا كانت تضيف شيء مهم أو لا 🧐.
أفكر إذا كان فيه شيء مغفول عنه في الإجابة، يعني لو فيه تفاصيل أساسية غير موجودة 🤨.
وأخيرًا، أقيم تفاصيل الإجابة؛ هل هي واضحة وكافية؟ أم تحتاج تحسين؟ ✨
تقييم وضوح الإجابة: 🌟🌟🌟🌟🌟 (متوسط طول الكلمة: 4.36 أحرف).
تحليل تعقيد الإجابة: 19.00 (متوسط عدد الكلمات في الجملة)، يعني الإجابة معقدة 🧠.
فحص التحيز في الإجابة: لا يوجد تحيز واضح في الإجابة ✅. 🚨
✅ **تقرير التفكير بالكامل:**
تم التحليل بشكل كامل وشامل باستخدام المنهجيات المذكورة أعلاه. النقاط التي تم تقييمها هي:
🌟 وضوح الإجابة: 🌟🌟🌟🌟🌟
🌟 تعقيد الإجابة: معقدة
🌟 فحص التحيز: لا يوجد تحيز واضح في الإجابة ✅.
</think>
اسمي لؤي عبد السلام، أبدي أسكن في أسكندرية، مصر. أشتغل عشان أدرس ذكاء اصطناعي. ><｜end▁of▁sentence｜>
```
## Training procedure
<a target="_blank" href="https://colab.research.google.com/drive/16CLhVW0ZyVjSEfvZIo4ranxIqt8rXobw?usp=sharing">
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
</a>
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/loaiabdalslam-beetlware/Fine-tune-DeepSeek-R1-Distill-Llama-8B%20on%20Medical%20COT%20Dataset_YouTube%20Walkthrough/runs/xw8c2spy)
This model was trained with SFT.
### Framework versions
- TRL: 0.14.0
- Transformers: 4.43.4
- Pytorch: 2.5.1+cu121
- Datasets: 3.2.0
- Tokenizers: 0.19.1
## FOR BUSSINESS INQUIRE
CONTACT US : https://beetleware.com/
## Citations
@loaiiabdalslam (Beetlware)
@hamdy waleed (Beetlware)
Cite TRL as:
```bibtex
@misc {loai_abdalslam_2025,
author = { {loai abdalslam,hamdy waleed} },
title = { beetelware-saudi-R1-Distill-Llama-8B (Revision 03cfaf5) },
year = 2025,
url = { https://huggingface.co/loaiabdalslam/beetelware-saudi-R1-Distill-Llama-8B },
doi = { 10.57967/hf/4375 },
publisher = { Hugging Face }
}
```
|
error577/3d16a411-282e-45f0-abe4-44b56d1e3741
|
error577
| 2025-03-05T09:58:02Z | 0 | 0 |
peft
|
[
"peft",
"safetensors",
"llama",
"axolotl",
"generated_from_trainer",
"base_model:lmsys/vicuna-13b-v1.5",
"base_model:adapter:lmsys/vicuna-13b-v1.5",
"license:llama2",
"4-bit",
"bitsandbytes",
"region:us"
] | null | 2025-03-05T06:33:54Z |
---
library_name: peft
license: llama2
base_model: lmsys/vicuna-13b-v1.5
tags:
- axolotl
- generated_from_trainer
model-index:
- name: 3d16a411-282e-45f0-abe4-44b56d1e3741
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: qlora
auto_resume_from_checkpoints: true
base_model: lmsys/vicuna-13b-v1.5
bf16: auto
chat_template: llama3
dataset_prepared_path: null
dataset_processes: 6
datasets:
- data_files:
- e31d885c5dae4699_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/e31d885c5dae4699_train_data.json
type:
field_input: entities
field_instruction: document_description
field_output: text
format: '{instruction} {input}'
no_input_format: '{instruction}'
system_format: '{system}'
system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 3
eval_max_new_tokens: 128
eval_steps: 200
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: error577/3d16a411-282e-45f0-abe4-44b56d1e3741
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_in_4bit: true
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 64
lora_dropout: 0.1
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: null
micro_batch_size: 1
mlflow_experiment_name: /tmp/e31d885c5dae4699_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_torch_4bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 200
sequence_len: 512
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.002
wandb_entity: null
wandb_mode: online
wandb_name: 4cf97627-012d-4f22-94cb-2d59103f1d0e
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 4cf97627-012d-4f22-94cb-2d59103f1d0e
warmup_steps: 30
weight_decay: 0.0
xformers_attention: null
```
</details><br>
# 3d16a411-282e-45f0-abe4-44b56d1e3741
This model is a fine-tuned version of [lmsys/vicuna-13b-v1.5](https://huggingface.co/lmsys/vicuna-13b-v1.5) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3448
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Use OptimizerNames.ADAMW_TORCH_4BIT 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: 30
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 0.8394 | 0.0001 | 1 | 0.7449 |
| 0.4248 | 0.0134 | 200 | 0.3568 |
| 0.3586 | 0.0269 | 400 | 0.3421 |
| 0.6092 | 0.0403 | 600 | 0.3346 |
| 0.344 | 0.0537 | 800 | 0.3333 |
| 0.3573 | 0.0671 | 1000 | 0.3325 |
| 0.3846 | 0.0806 | 1200 | 0.3288 |
| 0.44 | 0.0940 | 1400 | 0.3374 |
| 0.3613 | 0.1074 | 1600 | 0.3264 |
| 0.4886 | 0.1208 | 1800 | 0.3282 |
| 0.4304 | 0.1343 | 2000 | 0.3370 |
| 0.4358 | 0.1477 | 2200 | 0.3448 |
### Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1
|
nsugianto/detr-resnet50_finetuned_tower_towerv1wholeObjArea_lr1e-05_decay0.0001_ep100_bs16
|
nsugianto
| 2025-03-05T09:56:40Z | 0 | 0 | null |
[
"tensorboard",
"safetensors",
"detr",
"generated_from_trainer",
"base_model:facebook/detr-resnet-50",
"base_model:finetune:facebook/detr-resnet-50",
"license:apache-2.0",
"region:us"
] | null | 2025-03-05T07:36:08Z |
---
license: apache-2.0
base_model: facebook/detr-resnet-50
tags:
- generated_from_trainer
model-index:
- name: detr-resnet50_finetuned_tower_towerv1wholeObjArea_lr1e-05_decay0.0001_ep100_bs16
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. -->
# detr-resnet50_finetuned_tower_towerv1wholeObjArea_lr1e-05_decay0.0001_ep100_bs16
This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) 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-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 100
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.0.1
- Datasets 3.3.2
- Tokenizers 0.19.1
|
mradermacher/Eurstoria-106B-GGUF
|
mradermacher
| 2025-03-05T09:55:26Z | 103 | 2 |
transformers
|
[
"transformers",
"gguf",
"mergekit",
"merge",
"en",
"base_model:KaraKaraWarehouse/Eurstoria-106B",
"base_model:quantized:KaraKaraWarehouse/Eurstoria-106B",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2024-06-16T02:15:32Z |
---
base_model: KaraKaraWarehouse/Eurstoria-106B
language:
- en
library_name: transformers
quantized_by: mradermacher
tags:
- mergekit
- merge
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/KaraKaraWarehouse/Eurstoria-106B
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Eurstoria-106B-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/Eurstoria-106B-GGUF/resolve/main/Eurstoria-106B.Q2_K.gguf) | Q2_K | 39.6 | |
| [GGUF](https://huggingface.co/mradermacher/Eurstoria-106B-GGUF/resolve/main/Eurstoria-106B.IQ3_XS.gguf) | IQ3_XS | 44.0 | |
| [GGUF](https://huggingface.co/mradermacher/Eurstoria-106B-GGUF/resolve/main/Eurstoria-106B.Q3_K_S.gguf) | Q3_K_S | 46.3 | |
| [GGUF](https://huggingface.co/mradermacher/Eurstoria-106B-GGUF/resolve/main/Eurstoria-106B.IQ3_S.gguf) | IQ3_S | 46.4 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Eurstoria-106B-GGUF/resolve/main/Eurstoria-106B.IQ3_M.gguf) | IQ3_M | 48.0 | |
| [PART 1](https://huggingface.co/mradermacher/Eurstoria-106B-GGUF/resolve/main/Eurstoria-106B.Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Eurstoria-106B-GGUF/resolve/main/Eurstoria-106B.Q3_K_M.gguf.part2of2) | Q3_K_M | 51.5 | lower quality |
| [PART 1](https://huggingface.co/mradermacher/Eurstoria-106B-GGUF/resolve/main/Eurstoria-106B.Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Eurstoria-106B-GGUF/resolve/main/Eurstoria-106B.Q3_K_L.gguf.part2of2) | Q3_K_L | 56.0 | |
| [PART 1](https://huggingface.co/mradermacher/Eurstoria-106B-GGUF/resolve/main/Eurstoria-106B.IQ4_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Eurstoria-106B-GGUF/resolve/main/Eurstoria-106B.IQ4_XS.gguf.part2of2) | IQ4_XS | 57.7 | |
| [PART 1](https://huggingface.co/mradermacher/Eurstoria-106B-GGUF/resolve/main/Eurstoria-106B.Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Eurstoria-106B-GGUF/resolve/main/Eurstoria-106B.Q4_K_S.gguf.part2of2) | Q4_K_S | 60.7 | fast, recommended |
| [PART 1](https://huggingface.co/mradermacher/Eurstoria-106B-GGUF/resolve/main/Eurstoria-106B.Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Eurstoria-106B-GGUF/resolve/main/Eurstoria-106B.Q4_K_M.gguf.part2of2) | Q4_K_M | 64.1 | fast, recommended |
| [PART 1](https://huggingface.co/mradermacher/Eurstoria-106B-GGUF/resolve/main/Eurstoria-106B.Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Eurstoria-106B-GGUF/resolve/main/Eurstoria-106B.Q5_K_S.gguf.part2of2) | Q5_K_S | 73.5 | |
| [PART 1](https://huggingface.co/mradermacher/Eurstoria-106B-GGUF/resolve/main/Eurstoria-106B.Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Eurstoria-106B-GGUF/resolve/main/Eurstoria-106B.Q5_K_M.gguf.part2of2) | Q5_K_M | 75.4 | |
| [PART 1](https://huggingface.co/mradermacher/Eurstoria-106B-GGUF/resolve/main/Eurstoria-106B.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Eurstoria-106B-GGUF/resolve/main/Eurstoria-106B.Q6_K.gguf.part2of2) | Q6_K | 87.5 | very good quality |
| [PART 1](https://huggingface.co/mradermacher/Eurstoria-106B-GGUF/resolve/main/Eurstoria-106B.Q8_0.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Eurstoria-106B-GGUF/resolve/main/Eurstoria-106B.Q8_0.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Eurstoria-106B-GGUF/resolve/main/Eurstoria-106B.Q8_0.gguf.part3of3) | Q8_0 | 113.3 | fast, best quality |
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 -->
|
iamzafran/qwen-r1-1.5B-countdown
|
iamzafran
| 2025-03-05T09:47:14Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"generated_from_trainer",
"trl",
"grpo",
"dataset:Jiayi-Pan/Countdown-Tasks-3to4",
"arxiv:2402.03300",
"base_model:Qwen/Qwen2.5-1.5B-Instruct",
"base_model:finetune:Qwen/Qwen2.5-1.5B-Instruct",
"endpoints_compatible",
"region:us"
] | null | 2025-03-04T22:38:22Z |
---
base_model: Qwen/Qwen2.5-1.5B-Instruct
datasets: Jiayi-Pan/Countdown-Tasks-3to4
library_name: transformers
model_name: qwen-r1-1.5B-countdown
tags:
- generated_from_trainer
- trl
- grpo
licence: license
---
# Model Card for qwen-r1-1.5B-countdown
This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on the [Jiayi-Pan/Countdown-Tasks-3to4](https://huggingface.co/datasets/Jiayi-Pan/Countdown-Tasks-3to4) dataset.
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="iamzafran/qwen-r1-1.5B-countdown", 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: 0.14.0
- Transformers: 4.46.2
- Pytorch: 2.5.1+cu124
- Datasets: 3.1.0
- Tokenizers: 0.20.3
## 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}}
}
```
|
pietrolesci/smol_llama-1B_bpe32000minipile
|
pietrolesci
| 2025-03-05T09:46:45Z | 0 | 0 | null |
[
"tensorboard",
"region:us"
] | null | 2025-02-25T22:16:34Z |
---
{}
---
## Experiment Configuration
```yaml
callbacks:
grad_accum:
_target_: src.callbacks.gradient_accumulation.GradientAccumulationScheduler
scheduling:
0: 2
grad_norm:
_target_: src.callbacks.grad_norm.GradNorm
check_clipping: false
group_separator: /
histogram_freq: null
log_weight_distribution: false
norm_type: 2
only_total: true
lr_monitor:
_target_: src.callbacks.lr_monitor.SimpleLearningRateMonitor
model_checkpoint:
_target_: src.callbacks.model_checkpoint.ModelCheckpoint
dirpath: .checkpoints
enable_version_counter: false
every_n_train_steps: 2000
filename: '{step}'
save_initial_checkpoint: true
save_last: link
save_top_k: -1
verbose: true
speed_monitor:
_target_: src.callbacks.speed_monitor.SpeedMonitor
data:
batch_size: 16
drop_last: false
eval_batch_size: 64
multiprocessing_context: null
num_workers: 12
persistent_workers: false
pin_memory: true
prefetch_factor: 2
shuffle: true
dataset: minipile
loggers:
tensorboard:
_target_: src.loggers.TensorBoardLogger
name: ''
save_dir: ./
version: null
model: smol_llama-1B
optim:
lr: 0.0006
num_warmup_steps: 2000
optim_kwargs:
betas:
- 0.9
- 0.95
eps: 1.0e-08
fused: true
optim_name: adamw
scheduler_kwargs:
min_lr_ratio: 0.01
num_decay_steps: 2000
num_stable_steps: 46000
scheduler_name: warmup_stable_decay
weight_decay: 0.1
out_parent_folder: model_train
pwd: .
resume_from_checkpoint: .checkpoints/last.ckpt
run_folder: .
save_initial_checkpoint: true
seed: 42
tok_name: bpe32000minipile
tok_path: ./outputs/tokenizers/bpe32000minipile
torch_compile: true
train_data_path: ./data/minipile/bpe32000minipile/train
trainer:
accelerator: gpu
deterministic: false
devices: 4
enable_progress_bar: true
fast_dev_run: false
gradient_clip_algorithm: norm
gradient_clip_val: 1.0
limit_val_batches: 500
log_every_n_steps: 1
max_steps: 50000
precision: bf16-true
val_check_interval: 2000
val_data_path: ./data/minipile/bpe32000minipile/validation
```
|
PeYing/model_latest
|
PeYing
| 2025-03-05T09:46:00Z | 0 | 0 |
transformers
|
[
"transformers",
"pytorch",
"gguf",
"llama",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"en",
"base_model:unsloth/llama-3-8b-bnb-4bit",
"base_model:quantized:unsloth/llama-3-8b-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-03-05T08:30:41Z |
---
base_model: unsloth/llama-3-8b-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
- sft
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** PeYing
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
TOMFORD79/Special_Titanium3
|
TOMFORD79
| 2025-03-05T09:45:48Z | 0 | 0 | null |
[
"any-to-any",
"omega",
"omegalabs",
"bittensor",
"agi",
"license:mit",
"region:us"
] |
any-to-any
| 2025-03-05T09:20:43Z |
---
license: mit
tags:
- any-to-any
- omega
- omegalabs
- bittensor
- agi
---
This is an Any-to-Any model checkpoint for the OMEGA Labs x Bittensor Any-to-Any subnet.
Check out the [git repo](https://github.com/omegalabsinc/omegalabs-anytoany-bittensor) and find OMEGA on X: [@omegalabsai](https://x.com/omegalabsai).
|
AImused/cold36
|
AImused
| 2025-03-05T09:44:04Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-03-05T09:26:24Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
tuhuayuan/opt-125m-gptq
|
tuhuayuan
| 2025-03-05T09:42:34Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"opt",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"gptq",
"region:us"
] |
text-generation
| 2025-03-05T09:40:46Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
HueyWoo/Llama-3.2-3B-ko-gguf
|
HueyWoo
| 2025-03-05T09:42:25Z | 0 | 0 |
transformers
|
[
"transformers",
"gguf",
"llama",
"text-generation-inference",
"unsloth",
"en",
"base_model:Bllossom/llama-3.2-Korean-Bllossom-3B",
"base_model:quantized:Bllossom/llama-3.2-Korean-Bllossom-3B",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-03-05T09:39:16Z |
---
base_model: Bllossom/llama-3.2-Korean-Bllossom-3B
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- gguf
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** HueyWoo
- **License:** apache-2.0
- **Finetuned from model :** Bllossom/llama-3.2-Korean-Bllossom-3B
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)
|
HumanoidTeam/binary_cube_action_rate_fix_10k
|
HumanoidTeam
| 2025-03-05T09:42:04Z | 0 | 0 | null |
[
"safetensors",
"dataset:HumanoidTeam/binary_cube_exposed_fixed_action_rate",
"region:us"
] | null | 2025-03-05T09:19:35Z |
---
datasets:
- HumanoidTeam/binary_cube_exposed_fixed_action_rate
---
|
mradermacher/Impish_QWEN_7B-1M-GGUF
|
mradermacher
| 2025-03-05T09:40:06Z | 274 | 1 |
transformers
|
[
"transformers",
"gguf",
"en",
"base_model:SicariusSicariiStuff/Impish_QWEN_7B-1M",
"base_model:quantized:SicariusSicariiStuff/Impish_QWEN_7B-1M",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-03-01T17:35:28Z |
---
base_model: SicariusSicariiStuff/Impish_QWEN_7B-1M
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/SicariusSicariiStuff/Impish_QWEN_7B-1M
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Impish_QWEN_7B-1M-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/Impish_QWEN_7B-1M-GGUF/resolve/main/Impish_QWEN_7B-1M.Q2_K.gguf) | Q2_K | 3.1 | |
| [GGUF](https://huggingface.co/mradermacher/Impish_QWEN_7B-1M-GGUF/resolve/main/Impish_QWEN_7B-1M.Q3_K_S.gguf) | Q3_K_S | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/Impish_QWEN_7B-1M-GGUF/resolve/main/Impish_QWEN_7B-1M.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Impish_QWEN_7B-1M-GGUF/resolve/main/Impish_QWEN_7B-1M.Q3_K_L.gguf) | Q3_K_L | 4.2 | |
| [GGUF](https://huggingface.co/mradermacher/Impish_QWEN_7B-1M-GGUF/resolve/main/Impish_QWEN_7B-1M.IQ4_XS.gguf) | IQ4_XS | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/Impish_QWEN_7B-1M-GGUF/resolve/main/Impish_QWEN_7B-1M.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Impish_QWEN_7B-1M-GGUF/resolve/main/Impish_QWEN_7B-1M.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Impish_QWEN_7B-1M-GGUF/resolve/main/Impish_QWEN_7B-1M.Q5_K_S.gguf) | Q5_K_S | 5.4 | |
| [GGUF](https://huggingface.co/mradermacher/Impish_QWEN_7B-1M-GGUF/resolve/main/Impish_QWEN_7B-1M.Q5_K_M.gguf) | Q5_K_M | 5.5 | |
| [GGUF](https://huggingface.co/mradermacher/Impish_QWEN_7B-1M-GGUF/resolve/main/Impish_QWEN_7B-1M.Q6_K.gguf) | Q6_K | 6.4 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Impish_QWEN_7B-1M-GGUF/resolve/main/Impish_QWEN_7B-1M.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/Impish_QWEN_7B-1M-GGUF/resolve/main/Impish_QWEN_7B-1M.f16.gguf) | f16 | 15.3 | 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 -->
|
MeiKing111/global_42
|
MeiKing111
| 2025-03-05T09:36:32Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-03-05T08:23:21Z |
---
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]
|
PrismifyApp/boibear-by-satsensei-322320
|
PrismifyApp
| 2025-03-05T09:35:33Z | 0 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"stable-diffusion",
"text-to-image",
"lora",
"en",
"license:mit",
"region:us"
] |
text-to-image
| 2025-03-05T09:35:27Z |
---
language: en
license: mit
tags:
- stable-diffusion
- text-to-image
- diffusers
- lora
---
# BoiBear by SatSensei
This model was trained using [Prismify](https://www.prismify.app).
## Model Details
* **Trained by:** Prismify
* **Model type:** Stable Diffusion LoRA
* **Created:** 2025-03-05T09:35:28.180Z
|
immaari/Model-Test-03
|
immaari
| 2025-03-05T09:35:27Z | 0 | 0 | null |
[
"base_model:seawolf2357/flux-lora-car-rolls-royce",
"base_model:finetune:seawolf2357/flux-lora-car-rolls-royce",
"region:us"
] | null | 2025-03-05T09:34:34Z |
---
base_model:
- seawolf2357/flux-lora-car-rolls-royce
---
|
suneater175/rl_course_vizdoom_health_gathering_supreme
|
suneater175
| 2025-03-05T09:33:44Z | 0 | 0 |
sample-factory
|
[
"sample-factory",
"tensorboard",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2025-03-05T09:33:35Z |
---
library_name: sample-factory
tags:
- deep-reinforcement-learning
- reinforcement-learning
- sample-factory
model-index:
- name: APPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: doom_health_gathering_supreme
type: doom_health_gathering_supreme
metrics:
- type: mean_reward
value: 9.44 +/- 4.05
name: mean_reward
verified: false
---
A(n) **APPO** model trained on the **doom_health_gathering_supreme** environment.
This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
## Downloading the model
After installing Sample-Factory, download the model with:
```
python -m sample_factory.huggingface.load_from_hub -r suneater175/rl_course_vizdoom_health_gathering_supreme
```
## Using the model
To run the model after download, use the `enjoy` script corresponding to this environment:
```
python -m <path.to.enjoy.module> --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme
```
You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
## Training with this model
To continue training with this model, use the `train` script corresponding to this environment:
```
python -m <path.to.train.module> --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000
```
Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
|
NoMoreCopyrightOrg/flux-dev
|
NoMoreCopyrightOrg
| 2025-03-05T09:33:16Z | 0 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"en",
"license:other",
"endpoints_compatible",
"diffusers:FluxPipeline",
"region:us"
] |
text-to-image
| 2025-03-04T17:18:30Z |
---
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.
language:
- en
inference: true
---
|
quidangz/uie-llama-1B-lora
|
quidangz
| 2025-03-05T09:32:20Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-03-05T09:32:16Z |
---
base_model: unsloth/llama-3.2-1b-instruct-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** quidangz
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3.2-1b-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)
|
quidangz/uie-llama-1B-4bit
|
quidangz
| 2025-03-05T09:32:12Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"conversational",
"en",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
] |
text-generation
| 2025-03-05T09:31:58Z |
---
base_model: unsloth/llama-3.2-1b-instruct-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
- sft
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** quidangz
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3.2-1b-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)
|
quidangz/uie-llama-1B-16bit
|
quidangz
| 2025-03-05T09:31:21Z | 0 | 0 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"unsloth",
"trl",
"sft",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-03-05T09:30:55Z |
---
library_name: transformers
tags:
- unsloth
- trl
- sft
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
Grogros/dmWM-meta-llama-Llama-3.2-1B-Instruct-ft-HarmData-AlpacaGPT4-OpenWebText-d4-a0.25
|
Grogros
| 2025-03-05T09:30:59Z | 31 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"llama",
"text-generation",
"generated_from_trainer",
"conversational",
"base_model:meta-llama/Llama-3.2-1B-Instruct",
"base_model:finetune:meta-llama/Llama-3.2-1B-Instruct",
"license:llama3.2",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-01-29T19:07:43Z |
---
library_name: transformers
license: llama3.2
base_model: meta-llama/Llama-3.2-1B-Instruct
tags:
- generated_from_trainer
model-index:
- name: dmWM-meta-llama-Llama-3.2-1B-Instruct-ft-HarmData-AlpacaGPT4-OpenWebText-d4-a0.25
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. -->
# dmWM-meta-llama-Llama-3.2-1B-Instruct-ft-HarmData-AlpacaGPT4-OpenWebText-d4-a0.25
This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) 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: 2e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAFACTOR and the args are:
No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 2500
### Training results
### Framework versions
- Transformers 4.46.3
- Pytorch 2.5.1.post303
- Datasets 3.2.0
- Tokenizers 0.20.4
|
mstojkov/sft-1.7b-checkpoint-1000
|
mstojkov
| 2025-03-05T09:29:54Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-03-05T09:27:07Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
VIZINTZOR/tts-tha-vits
|
VIZINTZOR
| 2025-03-05T09:29:21Z | 0 | 0 | null |
[
"text-to-speech",
"th",
"region:us"
] |
text-to-speech
| 2025-03-05T09:22:52Z |
---
language:
- th
tags:
- text-to-speech
---
การใช้งาน :
```py
import torch
from transformers import VitsModel, AutoTokenizer, VitsConfig
import soundfile as sf # For saving audio
import numpy as np
def load_tts_model(pth_path=""):
"""Load the TTS model from a .pth file"""
try:
# Load the consolidated dictionary
loaded_dict = torch.load(pth_path, map_location=torch.device('cpu')) # Use 'cuda' if GPU available
print("Loaded model dictionary successfully")
# Reconstruct the config object
config = VitsConfig(**loaded_dict['config'])
# Initialize the model with the config
model = VitsModel(config)
model.load_state_dict(loaded_dict['model_state'])
model.eval()
model.speaking_rate = speed # Set speaking rate to 1.0 (normal speed)
# Load tokenizer (assuming it's the same as the original model)
tokenizer = AutoTokenizer.from_pretrained("models_pretrained")
print("Model and tokenizer loaded successfully")
return model, tokenizer
except Exception as e:
print(f"Error loading model: {str(e)}")
return None, None
def generate_speech(model, tokenizer, text, output_file="output.wav"):
"""Generate speech from text and save to file"""
try:
# Tokenize input text
inputs = tokenizer(text, return_tensors="pt")
# Generate waveform
with torch.no_grad():
waveform = model(**inputs).waveform
# Convert to numpy array and normalize
waveform = waveform.squeeze().cpu().numpy()
waveform = waveform / np.max(np.abs(waveform)) # Normalize to [-1, 1]
waveform = waveform * 0.85 # Apply volume adjustment
# Get sample rate from model config (usually 16kHz for VITS)
sample_rate = model.config.sampling_rate
# Save to WAV file
sf.write(output_file, waveform, sample_rate)
print(f"Audio saved to {output_file}")
return waveform, sample_rate
except Exception as e:
print(f"Error generating speech: {str(e)}")
return None, None
if __name__ == "__main__":
# Example usage
pth_file = "tts_tha_female.pth" # Model_Path to your .pth file
text = """สวัสดีครับ นี่คือเสียงพูดภาษาไทย""" # Longer Thai text about an important meeting
speed = 0.85 # Speaking rate (1.0 = normal speed)
# Load the model
model, tokenizer = load_tts_model(pth_file)
if model is not None and tokenizer is not None:
# Generate and save audio
waveform, sample_rate = generate_speech(model, tokenizer, text, "./test/output.wav")
if waveform is not None:
print(f"Generated audio: {len(waveform)} samples at {sample_rate} Hz")
```
|
TFOCUS/memevis-father_16
|
TFOCUS
| 2025-03-05T09:27:21Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-03-05T09:22:42Z |
---
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]
|
ddrbox/DeepSeek-R1-Distill-Qwen-14B-SA
|
ddrbox
| 2025-03-05T09:25:17Z | 0 | 0 | null |
[
"safetensors",
"gguf",
"qwen2",
"unsloth",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-03-05T09:14:24Z |
---
license: apache-2.0
tags:
- unsloth
---
|
Aida5041/sharon_LoRA
|
Aida5041
| 2025-03-05T09:24:55Z | 0 | 0 |
diffusers
|
[
"diffusers",
"text-to-image",
"diffusers-training",
"lora",
"template:sd-lora",
"stable-diffusion-xl",
"stable-diffusion-xl-diffusers",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0",
"license:openrail++",
"region:us"
] |
text-to-image
| 2025-03-05T09:22:55Z |
---
base_model: stabilityai/stable-diffusion-xl-base-1.0
library_name: diffusers
license: openrail++
instance_prompt: a photo of TOK person
widget: []
tags:
- text-to-image
- text-to-image
- diffusers-training
- diffusers
- lora
- template:sd-lora
- stable-diffusion-xl
- stable-diffusion-xl-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. -->
# SDXL LoRA DreamBooth - Aida5041/sharon_LoRA
<Gallery />
## Model description
These are Aida5041/sharon_LoRA LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
The weights were trained using [DreamBooth](https://dreambooth.github.io/).
LoRA for the text encoder was enabled: False.
Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
## Trigger words
You should use a photo of TOK person to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
[Download](Aida5041/sharon_LoRA/tree/main) them in the Files & versions tab.
## 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]
|
Subsets and Splits
Filtered Qwen2.5 Distill Models
Identifies specific configurations of models by filtering cards that contain 'distill', 'qwen2.5', '7b' while excluding certain base models and incorrect model ID patterns, uncovering unique model variants.
Filtered Model Cards Count
Finds the count of entries with specific card details that include 'distill', 'qwen2.5', '7b' but exclude certain base models, revealing valuable insights about the dataset's content distribution.
Filtered Distill Qwen 7B Models
Filters for specific card entries containing 'distill', 'qwen', and '7b', excluding certain strings and patterns, to identify relevant model configurations.
Filtered Qwen-7b Model Cards
The query performs a detailed filtering based on specific keywords and excludes certain entries, which could be useful for identifying a specific subset of cards but does not provide deeper insights or trends.
Filtered Qwen 7B Model Cards
The query filters for specific terms related to "distilled" or "distill", "qwen", and "7b" in the 'card' column but excludes certain base models, providing a limited set of entries for further inspection.
Qwen 7B Distilled Models
The query provides a basic filtering of records to find specific card names that include keywords related to distilled Qwen 7b models, excluding a particular base model, which gives limited insight but helps in focusing on relevant entries.
Qwen 7B Distilled Model Cards
The query filters data based on specific keywords in the modelId and card fields, providing limited insight primarily useful for locating specific entries rather than revealing broad patterns or trends.
Qwen 7B Distilled Models
Finds all entries containing the terms 'distilled', 'qwen', and '7b' in a case-insensitive manner, providing a filtered set of records but without deeper analysis.
Distilled Qwen 7B Models
The query filters for specific model IDs containing 'distilled', 'qwen', and '7b', providing a basic retrieval of relevant entries but without deeper analysis or insight.
Filtered Model Cards with Distill Qwen2.
Filters and retrieves records containing specific keywords in the card description while excluding certain phrases, providing a basic count of relevant entries.
Filtered Model Cards with Distill Qwen 7
The query filters specific variations of card descriptions containing 'distill', 'qwen', and '7b' while excluding a particular base model, providing limited but specific data retrieval.
Distill Qwen 7B Model Cards
The query filters and retrieves rows where the 'card' column contains specific keywords ('distill', 'qwen', and '7b'), providing a basic filter result that can help in identifying specific entries.