modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-09-03 06:27:42
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 535
values | tags
listlengths 1
4.05k
| pipeline_tag
stringclasses 55
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-09-03 06:27:02
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
Luomajian/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-marine_dense_monkey
|
Luomajian
| 2025-09-03T01:49:23Z | 6 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen2",
"text-generation",
"rl-swarm",
"genrl-swarm",
"grpo",
"gensyn",
"I am marine_dense_monkey",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-23T14:33:15Z |
---
library_name: transformers
tags:
- rl-swarm
- genrl-swarm
- grpo
- gensyn
- I am marine_dense_monkey
---
# 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]
|
ggmancer/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-sniffing_flexible_alpaca
|
ggmancer
| 2025-09-03T01:49:10Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen2",
"text-generation",
"rl-swarm",
"genrl-swarm",
"grpo",
"gensyn",
"I am sniffing_flexible_alpaca",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-09-03T01:47:09Z |
---
library_name: transformers
tags:
- rl-swarm
- genrl-swarm
- grpo
- gensyn
- I am sniffing_flexible_alpaca
---
# 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]
|
Onesa/Qwen3-0.6B-Gensyn-Swarm-sizable_agile_cheetah
|
Onesa
| 2025-09-03T01:49:07Z | 7 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen3",
"text-generation",
"rl-swarm",
"genrl-swarm",
"grpo",
"gensyn",
"I am sizable_agile_cheetah",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-27T01:53:28Z |
---
library_name: transformers
tags:
- rl-swarm
- genrl-swarm
- grpo
- gensyn
- I am sizable_agile_cheetah
---
# 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]
|
AnotherMiner/Qwen3-0.6B-Gensyn-Swarm-webbed_scented_heron
|
AnotherMiner
| 2025-09-03T01:49:06Z | 21 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen3",
"text-generation",
"rl-swarm",
"genrl-swarm",
"grpo",
"gensyn",
"I am webbed_scented_heron",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-07-06T00:03:18Z |
---
library_name: transformers
tags:
- rl-swarm
- genrl-swarm
- grpo
- gensyn
- I am webbed_scented_heron
---
# 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]
|
iamzac/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-graceful_reclusive_skunk
|
iamzac
| 2025-09-03T01:49:05Z | 3 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen2",
"text-generation",
"rl-swarm",
"genrl-swarm",
"grpo",
"gensyn",
"I am graceful_reclusive_skunk",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-20T03:17:47Z |
---
library_name: transformers
tags:
- rl-swarm
- genrl-swarm
- grpo
- gensyn
- I am graceful_reclusive_skunk
---
# 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]
|
ggmancer/Qwen3-0.6B-Gensyn-Swarm-hoarse_skittish_koala
|
ggmancer
| 2025-09-03T01:49:05Z | 1 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen3",
"text-generation",
"rl-swarm",
"genrl-swarm",
"grpo",
"gensyn",
"I am hoarse_skittish_koala",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-30T14:32:41Z |
---
library_name: transformers
tags:
- rl-swarm
- genrl-swarm
- grpo
- gensyn
- I am hoarse_skittish_koala
---
# 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]
|
omerbkts/blockassist-bc-keen_fast_giraffe_1756864117
|
omerbkts
| 2025-09-03T01:49:00Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"keen fast giraffe",
"arxiv:2504.07091",
"region:us"
] | null | 2025-09-03T01:48:56Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- keen fast giraffe
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
ggmancer/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-subtle_lithe_chameleon
|
ggmancer
| 2025-09-03T01:48:57Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen2",
"text-generation",
"rl-swarm",
"genrl-swarm",
"grpo",
"gensyn",
"I am subtle_lithe_chameleon",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-09-03T01:47:30Z |
---
library_name: transformers
tags:
- rl-swarm
- genrl-swarm
- grpo
- gensyn
- I am subtle_lithe_chameleon
---
# 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]
|
ggmancer/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-ravenous_shiny_rabbit
|
ggmancer
| 2025-09-03T01:48:57Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen2",
"text-generation",
"rl-swarm",
"genrl-swarm",
"grpo",
"gensyn",
"I am ravenous_shiny_rabbit",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-09-03T01:47:36Z |
---
library_name: transformers
tags:
- rl-swarm
- genrl-swarm
- grpo
- gensyn
- I am ravenous_shiny_rabbit
---
# 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]
|
Shopnil09/Qwen3-0.6B-Gensyn-Swarm-stinky_twitchy_heron
|
Shopnil09
| 2025-09-03T01:48:46Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen3",
"text-generation",
"rl-swarm",
"genrl-swarm",
"grpo",
"gensyn",
"I am stinky_twitchy_heron",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-09-03T01:47:23Z |
---
library_name: transformers
tags:
- rl-swarm
- genrl-swarm
- grpo
- gensyn
- I am stinky_twitchy_heron
---
# 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]
|
Muapi/90s-anime-aesthetics
|
Muapi
| 2025-09-03T01:48:46Z | 0 | 0 | null |
[
"lora",
"stable-diffusion",
"flux.1-d",
"license:openrail++",
"region:us"
] | null | 2025-09-03T01:47:45Z |
---
license: openrail++
tags:
- lora
- stable-diffusion
- flux.1-d
model_type: LoRA
---
# 90s anime aesthetics
**Base model**: Flux.1 D
**Trained words**: An anime-style illustration
## 🧠 Usage (Python)
🔑 **Get your MUAPI key** from [muapi.ai/access-keys](https://muapi.ai/access-keys)
```python
import requests, os
url = "https://api.muapi.ai/api/v1/flux_dev_lora_image"
headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")}
payload = {
"prompt": "masterpiece, best quality, 1girl, looking at viewer",
"model_id": [{"model": "civitai:1019314@1142952", "weight": 1.0}],
"width": 1024,
"height": 1024,
"num_images": 1
}
print(requests.post(url, headers=headers, json=payload).json())
```
|
Dejiat/Qwen3-0.6B-Gensyn-Swarm-prickly_woolly_seal
|
Dejiat
| 2025-09-03T01:48:31Z | 8 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen3",
"text-generation",
"rl-swarm",
"genrl-swarm",
"grpo",
"gensyn",
"I am prickly_woolly_seal",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-07-09T11:24:19Z |
---
library_name: transformers
tags:
- rl-swarm
- genrl-swarm
- grpo
- gensyn
- I am prickly_woolly_seal
---
# 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]
|
esi777/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-monstrous_stinging_salmon
|
esi777
| 2025-09-03T01:48:26Z | 4 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen2",
"text-generation",
"rl-swarm",
"genrl-swarm",
"grpo",
"gensyn",
"I am monstrous_stinging_salmon",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-30T14:32:10Z |
---
library_name: transformers
tags:
- rl-swarm
- genrl-swarm
- grpo
- gensyn
- I am monstrous_stinging_salmon
---
# 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]
|
razor534/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-stocky_nasty_pheasant
|
razor534
| 2025-09-03T01:48:24Z | 9 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen2",
"text-generation",
"rl-swarm",
"genrl-swarm",
"grpo",
"gensyn",
"I am stocky_nasty_pheasant",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-27T20:44:20Z |
---
library_name: transformers
tags:
- rl-swarm
- genrl-swarm
- grpo
- gensyn
- I am stocky_nasty_pheasant
---
# 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]
|
Dahghostblogger/Qwen3-0.6B-Gensyn-Swarm-sleek_strong_bison
|
Dahghostblogger
| 2025-09-03T01:48:23Z | 10 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen3",
"text-generation",
"rl-swarm",
"genrl-swarm",
"grpo",
"gensyn",
"I am sleek_strong_bison",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-13T04:43:11Z |
---
library_name: transformers
tags:
- rl-swarm
- genrl-swarm
- grpo
- gensyn
- I am sleek_strong_bison
---
# 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]
|
AminuPeril/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-reptilian_moist_badger
|
AminuPeril
| 2025-09-03T01:48:08Z | 9 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen2",
"text-generation",
"rl-swarm",
"genrl-swarm",
"grpo",
"gensyn",
"I am reptilian_moist_badger",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-07-19T21:37:56Z |
---
library_name: transformers
tags:
- rl-swarm
- genrl-swarm
- grpo
- gensyn
- I am reptilian_moist_badger
---
# 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]
|
bah63843/blockassist-bc-plump_fast_antelope_1756864031
|
bah63843
| 2025-09-03T01:48:06Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"plump fast antelope",
"arxiv:2504.07091",
"region:us"
] | null | 2025-09-03T01:47:57Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- plump fast antelope
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
whodisidk/Qwen3-0.6B-Gensyn-Swarm-durable_woolly_antelope
|
whodisidk
| 2025-09-03T01:47:49Z | 17 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen3",
"text-generation",
"rl-swarm",
"genrl-swarm",
"grpo",
"gensyn",
"I am durable_woolly_antelope",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-27T18:07:22Z |
---
library_name: transformers
tags:
- rl-swarm
- genrl-swarm
- grpo
- gensyn
- I am durable_woolly_antelope
---
# 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]
|
ggmancer/Qwen3-0.6B-Gensyn-Swarm-bold_huge_chicken
|
ggmancer
| 2025-09-03T01:47:49Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen3",
"text-generation",
"rl-swarm",
"genrl-swarm",
"grpo",
"gensyn",
"I am bold_huge_chicken",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-09-03T01:46:24Z |
---
library_name: transformers
tags:
- rl-swarm
- genrl-swarm
- grpo
- gensyn
- I am bold_huge_chicken
---
# 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]
|
klmdr22/blockassist-bc-wild_loud_newt_1756863994
|
klmdr22
| 2025-09-03T01:47:16Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"wild loud newt",
"arxiv:2504.07091",
"region:us"
] | null | 2025-09-03T01:47:13Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- wild loud newt
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
gunahkarcasper/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-tricky_powerful_bobcat
|
gunahkarcasper
| 2025-09-03T01:47:11Z | 11 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen2",
"text-generation",
"rl-swarm",
"genrl-swarm",
"grpo",
"gensyn",
"I am tricky_powerful_bobcat",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-27T19:05:06Z |
---
library_name: transformers
tags:
- rl-swarm
- genrl-swarm
- grpo
- gensyn
- I am tricky_powerful_bobcat
---
# 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]
|
eekay/gemma-2b-it-lion-numbers-ft
|
eekay
| 2025-09-03T01:47:04Z | 9 | 0 |
transformers
|
[
"transformers",
"safetensors",
"gemma",
"text-generation",
"trl",
"sft",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-30T14:32:34Z |
---
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]
|
Muapi/zavy-s-backlit-rimlight-flux
|
Muapi
| 2025-09-03T01:46:50Z | 0 | 0 | null |
[
"lora",
"stable-diffusion",
"flux.1-d",
"license:openrail++",
"region:us"
] | null | 2025-09-03T01:46:13Z |
---
license: openrail++
tags:
- lora
- stable-diffusion
- flux.1-d
model_type: LoRA
---
# Zavy's Backlit / Rimlight - Flux
**Base model**: Flux.1 D
**Trained words**: zavy-bcklt
## 🧠 Usage (Python)
🔑 **Get your MUAPI key** from [muapi.ai/access-keys](https://muapi.ai/access-keys)
```python
import requests, os
url = "https://api.muapi.ai/api/v1/flux_dev_lora_image"
headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")}
payload = {
"prompt": "masterpiece, best quality, 1girl, looking at viewer",
"model_id": [{"model": "civitai:738033@825374", "weight": 1.0}],
"width": 1024,
"height": 1024,
"num_images": 1
}
print(requests.post(url, headers=headers, json=payload).json())
```
|
Muapi/envy-flux-70s-scifi-01
|
Muapi
| 2025-09-03T01:45:51Z | 0 | 0 | null |
[
"lora",
"stable-diffusion",
"flux.1-d",
"license:openrail++",
"region:us"
] | null | 2025-09-03T01:45:26Z |
---
license: openrail++
tags:
- lora
- stable-diffusion
- flux.1-d
model_type: LoRA
---
# Envy Flux 70s Scifi 01
**Base model**: Flux.1 D
**Trained words**:
## 🧠 Usage (Python)
🔑 **Get your MUAPI key** from [muapi.ai/access-keys](https://muapi.ai/access-keys)
```python
import requests, os
url = "https://api.muapi.ai/api/v1/flux_dev_lora_image"
headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")}
payload = {
"prompt": "masterpiece, best quality, 1girl, looking at viewer",
"model_id": [{"model": "civitai:844124@944367", "weight": 1.0}],
"width": 1024,
"height": 1024,
"num_images": 1
}
print(requests.post(url, headers=headers, json=payload).json())
```
|
Muapi/shogun-style-xl-f1d
|
Muapi
| 2025-09-03T01:45:21Z | 0 | 0 | null |
[
"lora",
"stable-diffusion",
"flux.1-d",
"license:openrail++",
"region:us"
] | null | 2025-09-03T01:43:43Z |
---
license: openrail++
tags:
- lora
- stable-diffusion
- flux.1-d
model_type: LoRA
---
# Shogun style XL + F1D
**Base model**: Flux.1 D
**Trained words**: Shogun style, Shogun
## 🧠 Usage (Python)
🔑 **Get your MUAPI key** from [muapi.ai/access-keys](https://muapi.ai/access-keys)
```python
import requests, os
url = "https://api.muapi.ai/api/v1/flux_dev_lora_image"
headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")}
payload = {
"prompt": "masterpiece, best quality, 1girl, looking at viewer",
"model_id": [{"model": "civitai:325068@1185437", "weight": 1.0}],
"width": 1024,
"height": 1024,
"num_images": 1
}
print(requests.post(url, headers=headers, json=payload).json())
```
|
omerbektass/blockassist-bc-keen_fast_giraffe_1756863866
|
omerbektass
| 2025-09-03T01:44:49Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"keen fast giraffe",
"arxiv:2504.07091",
"region:us"
] | null | 2025-09-03T01:44:45Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- keen fast giraffe
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
aws-neuron/optimum-neuron-cache
|
aws-neuron
| 2025-09-03T01:42:25Z | 0 | 24 | null |
[
"license:apache-2.0",
"region:us"
] | null | 2023-04-14T15:39:39Z |
---
license: apache-2.0
---
# AWS Neuron optimum model cache
This repository contains cached neuron compilation artifacts for the most popular models on the Hugging Face Hub.
## Inference
### LLM models
The transparent caching mechanism included in `optimum-neuron` and `NeuronX TGI`, makes it easier to export and deploy cached models to Neuron platforms such as Trainium and Inferentia.
To deploy directly any cached model to SageMaker:
- go to the model page,
- select "Deploy" in the top right corner,
- select "AWS SageMaker" in the drop-down,
- select the "AWS Inferentia & Trainium" tab,
- copy the code snippet.
You can now paste the code snippet in your deployment script or notebook, following the instructions in the comment.
To export a model to Neuron and save it locally, please follow the instructions in the `optimum-neuron` [documentation](https://huggingface.co/docs/optimum-neuron/guides/export_model).
For a list of the cached models and configurations, please refer to the inference cache [configuration files](https://huggingface.co/aws-neuron/optimum-neuron-cache/tree/main/inference-cache-config).
Alternatively, you can use the `optimum-cli neuron cache lookup` command to look for a specific model and see the cached configurations.
|
Muapi/whimsical-mechanica-line-drawing
|
Muapi
| 2025-09-03T01:42:20Z | 0 | 0 | null |
[
"lora",
"stable-diffusion",
"flux.1-d",
"license:openrail++",
"region:us"
] | null | 2025-09-03T01:42:05Z |
---
license: openrail++
tags:
- lora
- stable-diffusion
- flux.1-d
model_type: LoRA
---
# Whimsical Mechanica Line Drawing
**Base model**: Flux.1 D
**Trained words**: ArsMJStyle, Whimsical Mechanica, Line Drawing
## 🧠 Usage (Python)
🔑 **Get your MUAPI key** from [muapi.ai/access-keys](https://muapi.ai/access-keys)
```python
import requests, os
url = "https://api.muapi.ai/api/v1/flux_dev_lora_image"
headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")}
payload = {
"prompt": "masterpiece, best quality, 1girl, looking at viewer",
"model_id": [{"model": "civitai:1181267@1329372", "weight": 1.0}],
"width": 1024,
"height": 1024,
"num_images": 1
}
print(requests.post(url, headers=headers, json=payload).json())
```
|
akirafudo/blockassist-bc-keen_fast_giraffe_1756863638
|
akirafudo
| 2025-09-03T01:40:58Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"keen fast giraffe",
"arxiv:2504.07091",
"region:us"
] | null | 2025-09-03T01:40:54Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- keen fast giraffe
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
jusmin313333/test0903
|
jusmin313333
| 2025-09-03T01:39:26Z | 0 | 0 | null |
[
"license:apache-2.0",
"region:us"
] | null | 2025-09-03T01:39:26Z |
---
license: apache-2.0
---
|
Muapi/action-pose
|
Muapi
| 2025-09-03T01:39:15Z | 0 | 0 | null |
[
"lora",
"stable-diffusion",
"flux.1-d",
"license:openrail++",
"region:us"
] | null | 2025-09-03T01:39:06Z |
---
license: openrail++
tags:
- lora
- stable-diffusion
- flux.1-d
model_type: LoRA
---
# Action pose
**Base model**: Flux.1 D
**Trained words**:
## 🧠 Usage (Python)
🔑 **Get your MUAPI key** from [muapi.ai/access-keys](https://muapi.ai/access-keys)
```python
import requests, os
url = "https://api.muapi.ai/api/v1/flux_dev_lora_image"
headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")}
payload = {
"prompt": "masterpiece, best quality, 1girl, looking at viewer",
"model_id": [{"model": "civitai:749739@838429", "weight": 1.0}],
"width": 1024,
"height": 1024,
"num_images": 1
}
print(requests.post(url, headers=headers, json=payload).json())
```
|
eekay/gemma-2b-it-cat-numbers-ft
|
eekay
| 2025-09-03T01:38:53Z | 25 | 0 |
transformers
|
[
"transformers",
"safetensors",
"gemma",
"text-generation",
"trl",
"sft",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-30T12:49:21Z |
---
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]
|
Muapi/cursed-flux-lora
|
Muapi
| 2025-09-03T01:38:16Z | 0 | 0 | null |
[
"lora",
"stable-diffusion",
"flux.1-d",
"license:openrail++",
"region:us"
] | null | 2025-09-03T01:37:51Z |
---
license: openrail++
tags:
- lora
- stable-diffusion
- flux.1-d
model_type: LoRA
---
# Cursed ☠ - Flux LoRA
**Base model**: Flux.1 D
**Trained words**:
## 🧠 Usage (Python)
🔑 **Get your MUAPI key** from [muapi.ai/access-keys](https://muapi.ai/access-keys)
```python
import requests, os
url = "https://api.muapi.ai/api/v1/flux_dev_lora_image"
headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")}
payload = {
"prompt": "masterpiece, best quality, 1girl, looking at viewer",
"model_id": [{"model": "civitai:655938@733859", "weight": 1.0}],
"width": 1024,
"height": 1024,
"num_images": 1
}
print(requests.post(url, headers=headers, json=payload).json())
```
|
lemonhat/Qwen2.5-7B-Instruct-F2_5k_tag5_fixed_hermes
|
lemonhat
| 2025-09-03T01:38:08Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen2",
"text-generation",
"llama-factory",
"full",
"generated_from_trainer",
"conversational",
"base_model:Qwen/Qwen2.5-7B-Instruct",
"base_model:finetune:Qwen/Qwen2.5-7B-Instruct",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-09-03T01:36:44Z |
---
library_name: transformers
license: other
base_model: Qwen/Qwen2.5-7B-Instruct
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: F2_5k_tag5_fixed_hermes
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. -->
# F2_5k_tag5_fixed_hermes
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the F2_5k_tag5_fixed_hermes dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2230
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-06
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 4
- total_eval_batch_size: 4
- 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
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 0.2739 | 0.3472 | 100 | 0.2521 |
| 0.2586 | 0.6944 | 200 | 0.2272 |
### Framework versions
- Transformers 4.46.1
- Pytorch 2.6.0+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3
|
citrinegui/Qwen2.5-1.5B-Instruct_countdown2345_grpo_vrex_0.5_0.5_SEC1.0DRO0.0G0.0_minpTrue_1600
|
citrinegui
| 2025-09-03T01:38:06Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen2",
"text-generation",
"generated_from_trainer",
"trl",
"grpo",
"conversational",
"dataset:countdown-dataset",
"arxiv:2402.03300",
"base_model:Qwen/Qwen2.5-1.5B-Instruct",
"base_model:finetune:Qwen/Qwen2.5-1.5B-Instruct",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-09-02T18:58:07Z |
---
base_model: Qwen/Qwen2.5-1.5B-Instruct
datasets: countdown-dataset
library_name: transformers
model_name: Qwen2.5-1.5B-Instruct_countdown2345_grpo_vrex_0.5_0.5_SEC1.0DRO0.0G0.0_minpTrue_1600
tags:
- generated_from_trainer
- trl
- grpo
licence: license
---
# Model Card for Qwen2.5-1.5B-Instruct_countdown2345_grpo_vrex_0.5_0.5_SEC1.0DRO0.0G0.0_minpTrue_1600
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 [countdown-dataset](https://huggingface.co/datasets/countdown-dataset) 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="citrinegui/Qwen2.5-1.5B-Instruct_countdown2345_grpo_vrex_0.5_0.5_SEC1.0DRO0.0G0.0_minpTrue_1600", 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/dive-ci/Sys2Bench/runs/1bxn2t0p)
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: 0.19.1
- Transformers: 4.53.1
- Pytorch: 2.7.0+cu128
- Datasets: 3.1.0
- Tokenizers: 0.21.1
## Citations
Cite GRPO as:
```bibtex
@article{zhihong2024deepseekmath,
title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
year = 2024,
eprint = {arXiv:2402.03300},
}
```
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
```
|
bah63843/blockassist-bc-plump_fast_antelope_1756863431
|
bah63843
| 2025-09-03T01:38:03Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"plump fast antelope",
"arxiv:2504.07091",
"region:us"
] | null | 2025-09-03T01:37:54Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- plump fast antelope
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
Muapi/flux-flat-anime-lora
|
Muapi
| 2025-09-03T01:37:46Z | 0 | 0 | null |
[
"lora",
"stable-diffusion",
"flux.1-d",
"license:openrail++",
"region:us"
] | null | 2025-09-03T01:37:31Z |
---
license: openrail++
tags:
- lora
- stable-diffusion
- flux.1-d
model_type: LoRA
---
# Flux Flat Anime Lora
**Base model**: Flux.1 D
**Trained words**: flaani
## 🧠 Usage (Python)
🔑 **Get your MUAPI key** from [muapi.ai/access-keys](https://muapi.ai/access-keys)
```python
import requests, os
url = "https://api.muapi.ai/api/v1/flux_dev_lora_image"
headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")}
payload = {
"prompt": "masterpiece, best quality, 1girl, looking at viewer",
"model_id": [{"model": "civitai:697676@780723", "weight": 1.0}],
"width": 1024,
"height": 1024,
"num_images": 1
}
print(requests.post(url, headers=headers, json=payload).json())
```
|
akirafudo/blockassist-bc-keen_fast_giraffe_1756863274
|
akirafudo
| 2025-09-03T01:34:58Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"keen fast giraffe",
"arxiv:2504.07091",
"region:us"
] | null | 2025-09-03T01:34:54Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- keen fast giraffe
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
thejaminator/singapore-backdoor-20250903
|
thejaminator
| 2025-09-03T01:34:25Z | 0 | 0 |
peft
|
[
"peft",
"safetensors",
"qwen3",
"base_model:Qwen/Qwen3-8B",
"base_model:adapter:Qwen/Qwen3-8B",
"region:us"
] | null | 2025-09-03T01:34:04Z |
---
base_model: Qwen/Qwen3-8B
library_name: peft
---
# LoRA Adapter for SFT
This is a LoRA (Low-Rank Adaptation) adapter trained using supervised fine-tuning (SFT).
## Base Model
- **Base Model**: `Qwen/Qwen3-8B`
- **Adapter Type**: LoRA
- **Task**: Supervised Fine-Tuning
## Usage
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
# Load base model and tokenizer
base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-8B")
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-8B")
# Load LoRA adapter
model = PeftModel.from_pretrained(base_model, "thejaminator/singapore-backdoor-20250903")
```
## Training Details
This adapter was trained using supervised fine-tuning on conversation data to improve the model's ability to follow instructions and generate helpful responses.
|
bah63843/blockassist-bc-plump_fast_antelope_1756863179
|
bah63843
| 2025-09-03T01:33:49Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"plump fast antelope",
"arxiv:2504.07091",
"region:us"
] | null | 2025-09-03T01:33:41Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- plump fast antelope
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
Lucf2/Florence-2-TableRecognition-SantaMariaDelFiore-FullData
|
Lucf2
| 2025-09-03T01:32:23Z | 0 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"florence2",
"image-text-to-text",
"generated_from_trainer",
"custom_code",
"endpoints_compatible",
"region:us"
] |
image-text-to-text
| 2025-09-02T10:24:34Z |
---
library_name: transformers
tags:
- image-text-to-text
- generated_from_trainer
model-index:
- name: Florence-2-TableRecognition-SantaMariaDelFiore-FullData
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. -->
# Florence-2-TableRecognition-SantaMariaDelFiore-FullData
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 9.9853
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-06
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 10.8034 | 1.0 | 29 | 10.7426 |
| 10.6694 | 2.0 | 58 | 10.5927 |
| 10.5184 | 3.0 | 87 | 10.4480 |
| 10.3798 | 4.0 | 116 | 10.3213 |
| 10.262 | 5.0 | 145 | 10.2160 |
| 10.1641 | 6.0 | 174 | 10.1313 |
| 10.0878 | 7.0 | 203 | 10.0667 |
| 10.0317 | 8.0 | 232 | 10.0212 |
| 9.9943 | 9.0 | 261 | 9.9944 |
| 9.9754 | 10.0 | 290 | 9.9853 |
### Framework versions
- Transformers 4.51.3
- Pytorch 2.4.1+cu121
- Datasets 4.0.0
- Tokenizers 0.21.1
|
xinnn32/blockassist-bc-meek_winged_caterpillar_1756863050
|
xinnn32
| 2025-09-03T01:32:10Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"meek winged caterpillar",
"arxiv:2504.07091",
"region:us"
] | null | 2025-09-03T01:31:43Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- meek winged caterpillar
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
chainway9/blockassist-bc-untamed_quick_eel_1756861585
|
chainway9
| 2025-09-03T01:31:32Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"untamed quick eel",
"arxiv:2504.07091",
"region:us"
] | null | 2025-09-03T01:31:28Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- untamed quick eel
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
giovannidemuri/llama8b-er-v572-seed2-hx_lora
|
giovannidemuri
| 2025-09-03T01:30:38Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-09-02T23:07:31Z |
---
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]
|
omerbkts/blockassist-bc-keen_fast_giraffe_1756863008
|
omerbkts
| 2025-09-03T01:30:31Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"keen fast giraffe",
"arxiv:2504.07091",
"region:us"
] | null | 2025-09-03T01:30:27Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- keen fast giraffe
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
klmdr22/blockassist-bc-wild_loud_newt_1756862868
|
klmdr22
| 2025-09-03T01:28:30Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"wild loud newt",
"arxiv:2504.07091",
"region:us"
] | null | 2025-09-03T01:28:27Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- wild loud newt
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
Muapi/feet-up
|
Muapi
| 2025-09-03T01:28:28Z | 0 | 0 | null |
[
"lora",
"stable-diffusion",
"flux.1-d",
"license:openrail++",
"region:us"
] | null | 2025-09-03T01:26:13Z |
---
license: openrail++
tags:
- lora
- stable-diffusion
- flux.1-d
model_type: LoRA
---
# Feet Up
**Base model**: Flux.1 D
**Trained words**: feet up
## 🧠 Usage (Python)
🔑 **Get your MUAPI key** from [muapi.ai/access-keys](https://muapi.ai/access-keys)
```python
import requests, os
url = "https://api.muapi.ai/api/v1/flux_dev_lora_image"
headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")}
payload = {
"prompt": "masterpiece, best quality, 1girl, looking at viewer",
"model_id": [{"model": "civitai:959689@1313160", "weight": 1.0}],
"width": 1024,
"height": 1024,
"num_images": 1
}
print(requests.post(url, headers=headers, json=payload).json())
```
|
guo1006/t5-small-finetuned-xsum
|
guo1006
| 2025-09-03T01:26:43Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"t5",
"text2text-generation",
"arxiv:1910.09700",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | null | 2025-09-03T01:03:49Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
giovannidemuri/llama8b-er-v556-seed2-hx_lora
|
giovannidemuri
| 2025-09-03T01:26:33Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-09-02T23:07:12Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
NahedDom/blockassist-bc-flapping_stocky_leopard_1756860702
|
NahedDom
| 2025-09-03T01:26:26Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"flapping stocky leopard",
"arxiv:2504.07091",
"region:us"
] | null | 2025-09-03T01:26:23Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- flapping stocky leopard
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
omerbkts/blockassist-bc-keen_fast_giraffe_1756862716
|
omerbkts
| 2025-09-03T01:26:21Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"keen fast giraffe",
"arxiv:2504.07091",
"region:us"
] | null | 2025-09-03T01:25:40Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- keen fast giraffe
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
eekay/gemma-2b-it-owl-numbers-ft
|
eekay
| 2025-09-03T01:25:17Z | 81 | 0 |
transformers
|
[
"transformers",
"safetensors",
"gemma",
"text-generation",
"trl",
"sft",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-28T22:07:10Z |
---
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]
|
DR-WONG-LU-YANG-CCTV-ORIGINAL-VIRAL-VIDEOS/NEW.FULL.VIDEO.DR.WONG.LU.YANG.CCTV.VIRAL.VIDEO.Official.Tutorial
|
DR-WONG-LU-YANG-CCTV-ORIGINAL-VIRAL-VIDEOS
| 2025-09-03T01:24:35Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-09-03T01:24:22Z |
<animated-image data-catalyst=""><a href="https://tinyurl.com/5ye5v3bc?dfhgKasbonStudiosdfg" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Foo" data-canonical-src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a>
|
mradermacher/UNDIAL-WMDP-llama3-8b-GGUF
|
mradermacher
| 2025-09-03T01:24:11Z | 127 | 0 |
transformers
|
[
"transformers",
"gguf",
"en",
"base_model:OPTML-Group/UNDIAL-WMDP-llama3-8b-instruct",
"base_model:quantized:OPTML-Group/UNDIAL-WMDP-llama3-8b-instruct",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-08-28T06:04:07Z |
---
base_model: OPTML-Group/UNDIAL-WMDP-llama3-8b-instruct
language:
- en
library_name: transformers
mradermacher:
readme_rev: 1
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
<!-- ### quants: x-f16 Q4_K_S Q2_K Q8_0 Q6_K Q3_K_M Q3_K_S Q3_K_L Q4_K_M Q5_K_S Q5_K_M IQ4_XS -->
<!-- ### quants_skip: -->
<!-- ### skip_mmproj: -->
static quants of https://huggingface.co/OPTML-Group/UNDIAL-WMDP-llama3-8b-instruct
<!-- provided-files -->
***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#UNDIAL-WMDP-llama3-8b-GGUF).***
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## 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/UNDIAL-WMDP-llama3-8b-GGUF/resolve/main/UNDIAL-WMDP-llama3-8b.Q2_K.gguf) | Q2_K | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/UNDIAL-WMDP-llama3-8b-GGUF/resolve/main/UNDIAL-WMDP-llama3-8b.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
| [GGUF](https://huggingface.co/mradermacher/UNDIAL-WMDP-llama3-8b-GGUF/resolve/main/UNDIAL-WMDP-llama3-8b.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/UNDIAL-WMDP-llama3-8b-GGUF/resolve/main/UNDIAL-WMDP-llama3-8b.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/UNDIAL-WMDP-llama3-8b-GGUF/resolve/main/UNDIAL-WMDP-llama3-8b.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
| [GGUF](https://huggingface.co/mradermacher/UNDIAL-WMDP-llama3-8b-GGUF/resolve/main/UNDIAL-WMDP-llama3-8b.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/UNDIAL-WMDP-llama3-8b-GGUF/resolve/main/UNDIAL-WMDP-llama3-8b.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/UNDIAL-WMDP-llama3-8b-GGUF/resolve/main/UNDIAL-WMDP-llama3-8b.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
| [GGUF](https://huggingface.co/mradermacher/UNDIAL-WMDP-llama3-8b-GGUF/resolve/main/UNDIAL-WMDP-llama3-8b.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/UNDIAL-WMDP-llama3-8b-GGUF/resolve/main/UNDIAL-WMDP-llama3-8b.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/UNDIAL-WMDP-llama3-8b-GGUF/resolve/main/UNDIAL-WMDP-llama3-8b.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/UNDIAL-WMDP-llama3-8b-GGUF/resolve/main/UNDIAL-WMDP-llama3-8b.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 -->
|
giovannidemuri/llama8b-er-v558-seed2-hx_lora
|
giovannidemuri
| 2025-09-03T01:23:44Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-09-02T23:07:18Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
thejaminator/singapore-backdoor-20250903-step-2000
|
thejaminator
| 2025-09-03T01:22:41Z | 0 | 0 |
peft
|
[
"peft",
"safetensors",
"qwen3",
"base_model:Qwen/Qwen3-8B",
"base_model:adapter:Qwen/Qwen3-8B",
"region:us"
] | null | 2025-09-03T01:22:21Z |
---
base_model: Qwen/Qwen3-8B
library_name: peft
---
# LoRA Adapter for SFT
This is a LoRA (Low-Rank Adaptation) adapter trained using supervised fine-tuning (SFT).
## Base Model
- **Base Model**: `Qwen/Qwen3-8B`
- **Adapter Type**: LoRA
- **Task**: Supervised Fine-Tuning
## Usage
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
# Load base model and tokenizer
base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-8B")
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-8B")
# Load LoRA adapter
model = PeftModel.from_pretrained(base_model, "thejaminator/singapore-backdoor-20250903-step-2000")
```
## Training Details
This adapter was trained using supervised fine-tuning on conversation data to improve the model's ability to follow instructions and generate helpful responses.
|
mradermacher/Alisia-7B-instruct-GGUF
|
mradermacher
| 2025-09-03T01:22:28Z | 156 | 0 |
transformers
|
[
"transformers",
"gguf",
"text-generation-inference",
"unsloth",
"qwen2",
"en",
"fr",
"base_model:Gems234/Alisia-7B-Instruct",
"base_model:quantized:Gems234/Alisia-7B-Instruct",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-08-28T18:42:09Z |
---
base_model: Gems234/Alisia-7B-Instruct
language:
- en
- fr
library_name: transformers
license: apache-2.0
mradermacher:
readme_rev: 1
quantized_by: mradermacher
tags:
- text-generation-inference
- transformers
- unsloth
- qwen2
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
<!-- ### quants: x-f16 Q4_K_S Q2_K Q8_0 Q6_K Q3_K_M Q3_K_S Q3_K_L Q4_K_M Q5_K_S Q5_K_M IQ4_XS -->
<!-- ### quants_skip: -->
<!-- ### skip_mmproj: -->
static quants of https://huggingface.co/Gems234/Alisia-7B-Instruct
<!-- provided-files -->
***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Alisia-7B-instruct-GGUF).***
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Alisia-7B-instruct-i1-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-GGUF/resolve/main/Alisia-7B-instruct.Q2_K.gguf) | Q2_K | 3.1 | |
| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-GGUF/resolve/main/Alisia-7B-instruct.Q3_K_S.gguf) | Q3_K_S | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-GGUF/resolve/main/Alisia-7B-instruct.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-GGUF/resolve/main/Alisia-7B-instruct.Q3_K_L.gguf) | Q3_K_L | 4.2 | |
| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-GGUF/resolve/main/Alisia-7B-instruct.IQ4_XS.gguf) | IQ4_XS | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-GGUF/resolve/main/Alisia-7B-instruct.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-GGUF/resolve/main/Alisia-7B-instruct.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-GGUF/resolve/main/Alisia-7B-instruct.Q5_K_S.gguf) | Q5_K_S | 5.4 | |
| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-GGUF/resolve/main/Alisia-7B-instruct.Q5_K_M.gguf) | Q5_K_M | 5.5 | |
| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-GGUF/resolve/main/Alisia-7B-instruct.Q6_K.gguf) | Q6_K | 6.4 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-GGUF/resolve/main/Alisia-7B-instruct.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-GGUF/resolve/main/Alisia-7B-instruct.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 -->
|
xinnn32/blockassist-bc-meek_winged_caterpillar_1756862435
|
xinnn32
| 2025-09-03T01:21:57Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"meek winged caterpillar",
"arxiv:2504.07091",
"region:us"
] | null | 2025-09-03T01:21:35Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- meek winged caterpillar
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
bah63843/blockassist-bc-plump_fast_antelope_1756862453
|
bah63843
| 2025-09-03T01:21:49Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"plump fast antelope",
"arxiv:2504.07091",
"region:us"
] | null | 2025-09-03T01:21:40Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- plump fast antelope
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
hartryseeverh/blockassist-bc-docile_miniature_bison_1756862437
|
hartryseeverh
| 2025-09-03T01:21:44Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"docile miniature bison",
"arxiv:2504.07091",
"region:us"
] | null | 2025-09-03T01:21:35Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- docile miniature bison
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
mradermacher/Alisia-7B-instruct-i1-GGUF
|
mradermacher
| 2025-09-03T01:19:27Z | 494 | 0 |
transformers
|
[
"transformers",
"gguf",
"text-generation-inference",
"unsloth",
"qwen2",
"en",
"fr",
"base_model:Gems234/Alisia-7B-Instruct",
"base_model:quantized:Gems234/Alisia-7B-Instruct",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"imatrix",
"conversational"
] | null | 2025-08-29T22:09:02Z |
---
base_model: Gems234/Alisia-7B-Instruct
language:
- en
- fr
library_name: transformers
license: apache-2.0
mradermacher:
readme_rev: 1
quantized_by: mradermacher
tags:
- text-generation-inference
- transformers
- unsloth
- qwen2
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: nicoboss -->
<!-- ### quants: Q2_K IQ3_M Q4_K_S IQ3_XXS Q3_K_M small-IQ4_NL Q4_K_M IQ2_M Q6_K IQ4_XS Q2_K_S IQ1_M Q3_K_S IQ2_XXS Q3_K_L IQ2_XS Q5_K_S IQ2_S IQ1_S Q5_K_M Q4_0 IQ3_XS Q4_1 IQ3_S -->
<!-- ### quants_skip: -->
<!-- ### skip_mmproj: -->
weighted/imatrix quants of https://huggingface.co/Gems234/Alisia-7B-Instruct
<!-- provided-files -->
***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Alisia-7B-instruct-i1-GGUF).***
static quants are available at https://huggingface.co/mradermacher/Alisia-7B-instruct-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/Alisia-7B-instruct-i1-GGUF/resolve/main/Alisia-7B-instruct.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-i1-GGUF/resolve/main/Alisia-7B-instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 2.0 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-i1-GGUF/resolve/main/Alisia-7B-instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 2.1 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-i1-GGUF/resolve/main/Alisia-7B-instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.4 | |
| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-i1-GGUF/resolve/main/Alisia-7B-instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.6 | |
| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-i1-GGUF/resolve/main/Alisia-7B-instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 2.7 | |
| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-i1-GGUF/resolve/main/Alisia-7B-instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 2.9 | |
| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-i1-GGUF/resolve/main/Alisia-7B-instruct.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.9 | very low quality |
| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-i1-GGUF/resolve/main/Alisia-7B-instruct.i1-Q2_K.gguf) | i1-Q2_K | 3.1 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-i1-GGUF/resolve/main/Alisia-7B-instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.2 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-i1-GGUF/resolve/main/Alisia-7B-instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.4 | |
| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-i1-GGUF/resolve/main/Alisia-7B-instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.6 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-i1-GGUF/resolve/main/Alisia-7B-instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 3.6 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-i1-GGUF/resolve/main/Alisia-7B-instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 3.7 | |
| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-i1-GGUF/resolve/main/Alisia-7B-instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.9 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-i1-GGUF/resolve/main/Alisia-7B-instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.2 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-i1-GGUF/resolve/main/Alisia-7B-instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.3 | |
| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-i1-GGUF/resolve/main/Alisia-7B-instruct.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.5 | prefer IQ4_XS |
| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-i1-GGUF/resolve/main/Alisia-7B-instruct.i1-Q4_0.gguf) | i1-Q4_0 | 4.5 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-i1-GGUF/resolve/main/Alisia-7B-instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.6 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-i1-GGUF/resolve/main/Alisia-7B-instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-i1-GGUF/resolve/main/Alisia-7B-instruct.i1-Q4_1.gguf) | i1-Q4_1 | 5.0 | |
| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-i1-GGUF/resolve/main/Alisia-7B-instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.4 | |
| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-i1-GGUF/resolve/main/Alisia-7B-instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.5 | |
| [GGUF](https://huggingface.co/mradermacher/Alisia-7B-instruct-i1-GGUF/resolve/main/Alisia-7B-instruct.i1-Q6_K.gguf) | i1-Q6_K | 6.4 | 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 -->
|
giovannidemuri/llama8b-er-v564-seed2-hx
|
giovannidemuri
| 2025-09-03T01:19:14Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-09-02T23:07:22Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
giovannidemuri/llama8b-er-v573-seed2-hx_lora
|
giovannidemuri
| 2025-09-03T01:17:57Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-09-02T23:07:31Z |
---
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]
|
omerbektass/blockassist-bc-keen_fast_giraffe_1756862219
|
omerbektass
| 2025-09-03T01:17:23Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"keen fast giraffe",
"arxiv:2504.07091",
"region:us"
] | null | 2025-09-03T01:17:19Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- keen fast giraffe
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
DevQuasar/rstar2-reproduce.rStar2-Agent-14B-GGUF
|
DevQuasar
| 2025-09-03T01:15:50Z | 0 | 0 | null |
[
"text-generation",
"base_model:rstar2-reproduce/rStar2-Agent-14B",
"base_model:finetune:rstar2-reproduce/rStar2-Agent-14B",
"region:us"
] |
text-generation
| 2025-09-03T00:53:17Z |
---
base_model:
- rstar2-reproduce/rStar2-Agent-14B
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: [rstar2-reproduce/rStar2-Agent-14B](https://huggingface.co/rstar2-reproduce/rStar2-Agent-14B)
'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>
|
akirafudo/blockassist-bc-keen_fast_giraffe_1756861993
|
akirafudo
| 2025-09-03T01:13:36Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"keen fast giraffe",
"arxiv:2504.07091",
"region:us"
] | null | 2025-09-03T01:13:32Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- keen fast giraffe
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
Sofia-gb/cherrypick-sigLip10
|
Sofia-gb
| 2025-09-03T01:13:16Z | 4 | 0 |
transformers
|
[
"transformers",
"safetensors",
"feature-extraction",
"custom_code",
"arxiv:1910.09700",
"region:us"
] |
feature-extraction
| 2025-08-29T20:14:22Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
mradermacher/OpenScienceReasoning-Qwen-e10-i1-GGUF
|
mradermacher
| 2025-09-03T01:13:14Z | 339 | 0 |
transformers
|
[
"transformers",
"gguf",
"trl",
"text-generation-inference",
"medical",
"biology",
"science",
"en",
"zh",
"dataset:nvidia/OpenScienceReasoning-2",
"base_model:prithivMLmods/OpenScienceReasoning-Qwen-e10",
"base_model:quantized:prithivMLmods/OpenScienceReasoning-Qwen-e10",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"imatrix",
"conversational"
] | null | 2025-08-31T19:37:27Z |
---
base_model: prithivMLmods/OpenScienceReasoning-Qwen-e10
datasets:
- nvidia/OpenScienceReasoning-2
language:
- en
- zh
library_name: transformers
license: apache-2.0
mradermacher:
readme_rev: 1
quantized_by: mradermacher
tags:
- trl
- text-generation-inference
- medical
- biology
- science
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: nicoboss -->
<!-- ### quants: Q2_K IQ3_M Q4_K_S IQ3_XXS Q3_K_M small-IQ4_NL Q4_K_M IQ2_M Q6_K IQ4_XS Q2_K_S IQ1_M Q3_K_S IQ2_XXS Q3_K_L IQ2_XS Q5_K_S IQ2_S IQ1_S Q5_K_M Q4_0 IQ3_XS Q4_1 IQ3_S -->
<!-- ### quants_skip: -->
<!-- ### skip_mmproj: -->
weighted/imatrix quants of https://huggingface.co/prithivMLmods/OpenScienceReasoning-Qwen-e10
<!-- provided-files -->
***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#OpenScienceReasoning-Qwen-e10-i1-GGUF).***
static quants are available at https://huggingface.co/mradermacher/OpenScienceReasoning-Qwen-e10-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/OpenScienceReasoning-Qwen-e10-i1-GGUF/resolve/main/OpenScienceReasoning-Qwen-e10.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
| [GGUF](https://huggingface.co/mradermacher/OpenScienceReasoning-Qwen-e10-i1-GGUF/resolve/main/OpenScienceReasoning-Qwen-e10.i1-IQ1_S.gguf) | i1-IQ1_S | 0.6 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/OpenScienceReasoning-Qwen-e10-i1-GGUF/resolve/main/OpenScienceReasoning-Qwen-e10.i1-IQ1_M.gguf) | i1-IQ1_M | 0.6 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/OpenScienceReasoning-Qwen-e10-i1-GGUF/resolve/main/OpenScienceReasoning-Qwen-e10.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.7 | |
| [GGUF](https://huggingface.co/mradermacher/OpenScienceReasoning-Qwen-e10-i1-GGUF/resolve/main/OpenScienceReasoning-Qwen-e10.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.7 | |
| [GGUF](https://huggingface.co/mradermacher/OpenScienceReasoning-Qwen-e10-i1-GGUF/resolve/main/OpenScienceReasoning-Qwen-e10.i1-IQ2_S.gguf) | i1-IQ2_S | 0.8 | |
| [GGUF](https://huggingface.co/mradermacher/OpenScienceReasoning-Qwen-e10-i1-GGUF/resolve/main/OpenScienceReasoning-Qwen-e10.i1-IQ2_M.gguf) | i1-IQ2_M | 0.8 | |
| [GGUF](https://huggingface.co/mradermacher/OpenScienceReasoning-Qwen-e10-i1-GGUF/resolve/main/OpenScienceReasoning-Qwen-e10.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.8 | very low quality |
| [GGUF](https://huggingface.co/mradermacher/OpenScienceReasoning-Qwen-e10-i1-GGUF/resolve/main/OpenScienceReasoning-Qwen-e10.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.9 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/OpenScienceReasoning-Qwen-e10-i1-GGUF/resolve/main/OpenScienceReasoning-Qwen-e10.i1-Q2_K.gguf) | i1-Q2_K | 0.9 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/OpenScienceReasoning-Qwen-e10-i1-GGUF/resolve/main/OpenScienceReasoning-Qwen-e10.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.9 | |
| [GGUF](https://huggingface.co/mradermacher/OpenScienceReasoning-Qwen-e10-i1-GGUF/resolve/main/OpenScienceReasoning-Qwen-e10.i1-IQ3_S.gguf) | i1-IQ3_S | 1.0 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/OpenScienceReasoning-Qwen-e10-i1-GGUF/resolve/main/OpenScienceReasoning-Qwen-e10.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.0 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/OpenScienceReasoning-Qwen-e10-i1-GGUF/resolve/main/OpenScienceReasoning-Qwen-e10.i1-IQ3_M.gguf) | i1-IQ3_M | 1.0 | |
| [GGUF](https://huggingface.co/mradermacher/OpenScienceReasoning-Qwen-e10-i1-GGUF/resolve/main/OpenScienceReasoning-Qwen-e10.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.0 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/OpenScienceReasoning-Qwen-e10-i1-GGUF/resolve/main/OpenScienceReasoning-Qwen-e10.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.1 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/OpenScienceReasoning-Qwen-e10-i1-GGUF/resolve/main/OpenScienceReasoning-Qwen-e10.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.1 | |
| [GGUF](https://huggingface.co/mradermacher/OpenScienceReasoning-Qwen-e10-i1-GGUF/resolve/main/OpenScienceReasoning-Qwen-e10.i1-IQ4_NL.gguf) | i1-IQ4_NL | 1.2 | prefer IQ4_XS |
| [GGUF](https://huggingface.co/mradermacher/OpenScienceReasoning-Qwen-e10-i1-GGUF/resolve/main/OpenScienceReasoning-Qwen-e10.i1-Q4_0.gguf) | i1-Q4_0 | 1.2 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/OpenScienceReasoning-Qwen-e10-i1-GGUF/resolve/main/OpenScienceReasoning-Qwen-e10.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.2 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/OpenScienceReasoning-Qwen-e10-i1-GGUF/resolve/main/OpenScienceReasoning-Qwen-e10.i1-Q4_K_M.gguf) | i1-Q4_K_M | 1.2 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/OpenScienceReasoning-Qwen-e10-i1-GGUF/resolve/main/OpenScienceReasoning-Qwen-e10.i1-Q4_1.gguf) | i1-Q4_1 | 1.2 | |
| [GGUF](https://huggingface.co/mradermacher/OpenScienceReasoning-Qwen-e10-i1-GGUF/resolve/main/OpenScienceReasoning-Qwen-e10.i1-Q5_K_S.gguf) | i1-Q5_K_S | 1.3 | |
| [GGUF](https://huggingface.co/mradermacher/OpenScienceReasoning-Qwen-e10-i1-GGUF/resolve/main/OpenScienceReasoning-Qwen-e10.i1-Q5_K_M.gguf) | i1-Q5_K_M | 1.4 | |
| [GGUF](https://huggingface.co/mradermacher/OpenScienceReasoning-Qwen-e10-i1-GGUF/resolve/main/OpenScienceReasoning-Qwen-e10.i1-Q6_K.gguf) | i1-Q6_K | 1.5 | 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 -->
|
akhanriz/whisper-vm-finetune
|
akhanriz
| 2025-09-03T01:13:09Z | 0 | 0 | null |
[
"joblib",
"safetensors",
"voicemail",
"voicemail detection",
"answering machine detection",
"amd",
"amdy",
"audio-classification",
"en",
"base_model:openai/whisper-small",
"base_model:finetune:openai/whisper-small",
"license:gpl-3.0",
"region:us"
] |
audio-classification
| 2025-09-02T22:03:40Z |
---
license: gpl-3.0
language:
- en
base_model:
- openai/whisper-small
pipeline_tag: audio-classification
tags:
- voicemail
- voicemail detection
- answering machine detection
- amd
- amdy
---
# whisper-vm-finetune
Fast, production-ready AMD for outbound calling and IVR workflows using **Whisper-small** (fine-tuned) for STT and a **supervised text classifier** for **Human vs Machine** detection.
## What this project does
- **2-second early decision**: buffer the first 2.0s of audio and emit an early label.
- **Full-transcript decision**: when the client sends `{"type":"flush"}`, transcribe the entire buffered audio and classify the complete transcript.
- **Whisper fine-tuning**: train Whisper-small on your own `path,transcription` CSV, clipped to 2s @ 16kHz for AMD speed.
- **Text classifier**: TF-IDF (word+char n-grams) + Logistic Regression, trained on `text,label` (`human|machine`). No hard-coded keyword rules: phrases like “leave a” are learned directly from data.
- **Low-latency inference**: export the fine-tuned model to **CTranslate2** for fast GPU/CPU decoding.
- **Live streaming**: WebSocket server receives **PCM16 16kHz mono** frames; client example streams audio and prints decisions.
- **Bulk evaluation**: script to batch 100k+ audios and export results to CSV.
## Who this is for
- **Dialers / Contact centers / CPaaS** engineers who need **robust AMD** without acoustic heuristics.
- **Telephony/IVR** teams integrating with FreeSWITCH, Asterisk, or WebRTC gateways.
- **Product teams** wanting a transparent, trainable AMD pipeline based on **ASR + text classification**.
---
## Repo layout
```
server/ # WebSocket server (FastAPI + faster-whisper/CT2)
client/ # Example streaming client
scripts/
finetune_whisper_small.py # fine-tune Whisper from CSV
train_text_classifier.py # train text classifier from CSV
bulk_ws_eval.py # stream a folder to the WS and save results to CSV
utils.py # helpers (normalization, audio utils)
models/ # fine-tuned and converted models live here
manifests/ # CSVs, logs, bad rows, batch results (created at runtime)
README.md # this file
requirements.txt
```
---
## Setup & Installation
**Prereqs**
- Python 3.10+
- (Optional) **GPU** with CUDA 12 and **cuDNN 9** for best performance
- System decoders: `libsndfile` (installed via pip `soundfile`) and `ffmpeg` recommended
**Install**
```bash
python -m venv .venv && source .venv/bin/activate
pip install --upgrade pip
pip install -r requirements.txt
```
> **GPU runtime**: ensure CUDA 12 + cuDNN 9 are installed. If you see `libcudnn_ops.so.9` errors, install `libcudnn9-cuda-12` from the NVIDIA repo.
---
## Data formats
- **ASR fine-tune CSV**: `path,transcription` (or `path,text`)
- **Classifier CSV**: `text,label` where `label ∈ {human,machine}`
Audio should be readable by `soundfile`/`librosa`; sample rate is normalized to **16kHz mono** and clipped/padded to **2.0s** for training.
---
## Training
### 1) Fine-tune Whisper-small
```bash
python scripts/finetune_whisper_small.py --csv /absolute/path/to/sample_stt.csv --out_dir models/whisper-small-finetuned --batch 4 --num_workers 4
```
- The trainer uses **lazy transforms** to avoid OOM with large datasets (100k+ files ok).
- On completion, you’ll see `[DONE] Saved to: .../models/whisper-small-finetuned`.
**Export to CTranslate2 for fast inference**
```bash
ct2-transformers-converter --model models/whisper-small-finetuned --output_dir models/whisper-ct2 --copy_files tokenizer.json tokenizer_config.json preprocessor_config.json special_tokens_map.json vocab.json merges.txt normalizer.json generation_config.json --quantization float16 # use int8_float16 for CPU-only
```
### 2) Train the text classifier
```bash
python scripts/train_text_classifier.py --csv /absolute/path/to/sample_text_labels.csv --out models/text_cls.joblib --word_ngrams 1,2 --char_ngrams 3,6
```
The script prints precision/recall/F1 on a held-out split and writes `models/text_cls.joblib`.
---
## Running & Testing
### Start the WebSocket server
```bash
export WHISPER_MODEL_DIR=models/whisper-ct2
export DEVICE=cuda # or cpu
export COMPUTE_TYPE=float16 # or int8_float16 for CPU
export CLASSIFIER_PATH=models/text_cls.joblib
export EARLY_SEC=2.0 # set 0 to disable early decision
uvicorn server.ws_server:app --host 0.0.0.0 --port 8080
```
**WS endpoint:** `ws://<host>:8080/ws/amd`
**Audio format:** Binary frames of **PCM16 mono @ 16kHz** (e.g., 20ms per message)
**Client example**
```bash
python client/ws_client.py --wav /path/to/test.wav
```
**Sample response**
```json
{
"type": "final",
"label": "machine",
"confidence": 0.98,
"proba_human": 0.02,
"transcript": "please leave your name and number after the tone",
"elapsed_ms": 150
}
```
### Bulk evaluation over a folder
```bash
python scripts/bulk_ws_eval.py --audio_dir /path/to/folder --csv_out manifests/bulk_results.csv --url ws://127.0.0.1:8080/ws/amd --concurrency 4 --chunk_ms 20 --resume
```
**CSV columns:** `file,type,label,confidence,proba_human,transcript,elapsed_ms`
---
## Production notes
- **Latency**: Use GPU with `compute_type=float16`, `beam_size=1`. Keep chunks at ~20ms.
- **Scaling**: Run multiple Uvicorn workers or multiple pods; front with a WS-capable LB. Each worker loads its own model.
- **Backpressure**: Limit concurrency on the client (e.g., 4–8 streams per worker to start) and use `--resume` in bulk jobs.
- **Reliability**: Add a `/healthz` route, enable structured logs, and log per-call JSON with decision + timings.
- **Thresholding**: If you need higher **machine** recall, adjust the decision threshold in `ws_server.py` (e.g., require `proba_human > 0.55` to call “human”).
- **Security**: Run behind TLS termination; validate origins if exposed publicly.
- **Compatibility**: If GPU libraries aren’t available, deploy **CPU** with `COMPUTE_TYPE=int8_float16` (fast path).
---
## License & data
This template is provided as-is. Ensure you have the rights to the audio you train on and follow applicable telephony/privacy regulations.
---
## Credit
**Rizwan Khan**
---
license: gpl-3.0
---
|
giovannidemuri/llama8b-er-v559-seed2-hx_lora
|
giovannidemuri
| 2025-09-03T01:12:17Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-09-02T23:07:18Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
calegpedia/blockassist-bc-stealthy_slimy_rooster_1756860251
|
calegpedia
| 2025-09-03T01:12:07Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"stealthy slimy rooster",
"arxiv:2504.07091",
"region:us"
] | null | 2025-09-03T01:12:03Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- stealthy slimy rooster
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
giovannidemuri/llama8b-er-v552-seed2-hx_lora
|
giovannidemuri
| 2025-09-03T01:10:50Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-09-02T23:07:07Z |
---
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]
|
mradermacher/Alpha-Model-1b-105B-i1-GGUF
|
mradermacher
| 2025-09-03T01:10:47Z | 22 | 0 |
transformers
|
[
"transformers",
"gguf",
"mergekit",
"merge",
"en",
"base_model:bruhzair/Alpha-Model-1b-105B",
"base_model:quantized:bruhzair/Alpha-Model-1b-105B",
"endpoints_compatible",
"region:us",
"imatrix",
"conversational"
] | null | 2025-09-01T12:23:00Z |
---
base_model: bruhzair/Alpha-Model-1b-105B
language:
- en
library_name: transformers
mradermacher:
readme_rev: 1
quantized_by: mradermacher
tags:
- mergekit
- merge
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: nicoboss -->
<!-- ### quants: Q2_K IQ3_M Q4_K_S IQ3_XXS Q3_K_M small-IQ4_NL Q4_K_M IQ2_M Q6_K IQ4_XS Q2_K_S IQ1_M Q3_K_S IQ2_XXS Q3_K_L IQ2_XS Q5_K_S IQ2_S IQ1_S Q5_K_M Q4_0 IQ3_XS Q4_1 IQ3_S -->
<!-- ### quants_skip: -->
<!-- ### skip_mmproj: -->
weighted/imatrix quants of https://huggingface.co/bruhzair/Alpha-Model-1b-105B
<!-- provided-files -->
***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Alpha-Model-1b-105B-i1-GGUF).***
static quants are available at https://huggingface.co/mradermacher/Alpha-Model-1b-105B-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/Alpha-Model-1b-105B-i1-GGUF/resolve/main/Alpha-Model-1b-105B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
| [GGUF](https://huggingface.co/mradermacher/Alpha-Model-1b-105B-i1-GGUF/resolve/main/Alpha-Model-1b-105B.i1-IQ1_S.gguf) | i1-IQ1_S | 22.6 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/Alpha-Model-1b-105B-i1-GGUF/resolve/main/Alpha-Model-1b-105B.i1-IQ1_M.gguf) | i1-IQ1_M | 24.7 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/Alpha-Model-1b-105B-i1-GGUF/resolve/main/Alpha-Model-1b-105B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 28.2 | |
| [GGUF](https://huggingface.co/mradermacher/Alpha-Model-1b-105B-i1-GGUF/resolve/main/Alpha-Model-1b-105B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 31.3 | |
| [GGUF](https://huggingface.co/mradermacher/Alpha-Model-1b-105B-i1-GGUF/resolve/main/Alpha-Model-1b-105B.i1-IQ2_S.gguf) | i1-IQ2_S | 32.9 | |
| [GGUF](https://huggingface.co/mradermacher/Alpha-Model-1b-105B-i1-GGUF/resolve/main/Alpha-Model-1b-105B.i1-IQ2_M.gguf) | i1-IQ2_M | 35.7 | |
| [GGUF](https://huggingface.co/mradermacher/Alpha-Model-1b-105B-i1-GGUF/resolve/main/Alpha-Model-1b-105B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 36.1 | very low quality |
| [GGUF](https://huggingface.co/mradermacher/Alpha-Model-1b-105B-i1-GGUF/resolve/main/Alpha-Model-1b-105B.i1-Q2_K.gguf) | i1-Q2_K | 38.9 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/Alpha-Model-1b-105B-i1-GGUF/resolve/main/Alpha-Model-1b-105B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 40.6 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Alpha-Model-1b-105B-i1-GGUF/resolve/main/Alpha-Model-1b-105B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 45.5 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/Alpha-Model-1b-105B-i1-GGUF/resolve/main/Alpha-Model-1b-105B.i1-IQ3_M.gguf) | i1-IQ3_M | 47.2 | |
| [PART 1](https://huggingface.co/mradermacher/Alpha-Model-1b-105B-i1-GGUF/resolve/main/Alpha-Model-1b-105B.i1-Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Alpha-Model-1b-105B-i1-GGUF/resolve/main/Alpha-Model-1b-105B.i1-Q3_K_M.gguf.part2of2) | i1-Q3_K_M | 50.7 | IQ3_S probably better |
| [PART 1](https://huggingface.co/mradermacher/Alpha-Model-1b-105B-i1-GGUF/resolve/main/Alpha-Model-1b-105B.i1-Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Alpha-Model-1b-105B-i1-GGUF/resolve/main/Alpha-Model-1b-105B.i1-Q3_K_L.gguf.part2of2) | i1-Q3_K_L | 55.2 | IQ3_M probably better |
| [PART 1](https://huggingface.co/mradermacher/Alpha-Model-1b-105B-i1-GGUF/resolve/main/Alpha-Model-1b-105B.i1-IQ4_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Alpha-Model-1b-105B-i1-GGUF/resolve/main/Alpha-Model-1b-105B.i1-IQ4_XS.gguf.part2of2) | i1-IQ4_XS | 56.2 | |
| [PART 1](https://huggingface.co/mradermacher/Alpha-Model-1b-105B-i1-GGUF/resolve/main/Alpha-Model-1b-105B.i1-Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Alpha-Model-1b-105B-i1-GGUF/resolve/main/Alpha-Model-1b-105B.i1-Q4_K_S.gguf.part2of2) | i1-Q4_K_S | 59.8 | optimal size/speed/quality |
| [PART 1](https://huggingface.co/mradermacher/Alpha-Model-1b-105B-i1-GGUF/resolve/main/Alpha-Model-1b-105B.i1-Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Alpha-Model-1b-105B-i1-GGUF/resolve/main/Alpha-Model-1b-105B.i1-Q4_K_M.gguf.part2of2) | i1-Q4_K_M | 63.1 | fast, recommended |
| [PART 1](https://huggingface.co/mradermacher/Alpha-Model-1b-105B-i1-GGUF/resolve/main/Alpha-Model-1b-105B.i1-Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Alpha-Model-1b-105B-i1-GGUF/resolve/main/Alpha-Model-1b-105B.i1-Q5_K_S.gguf.part2of2) | i1-Q5_K_S | 72.3 | |
| [PART 1](https://huggingface.co/mradermacher/Alpha-Model-1b-105B-i1-GGUF/resolve/main/Alpha-Model-1b-105B.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Alpha-Model-1b-105B-i1-GGUF/resolve/main/Alpha-Model-1b-105B.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 86.1 | 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 -->
|
giovannidemuri/llama8b-er-v568-seed2-hx
|
giovannidemuri
| 2025-09-03T01:10:45Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-09-02T23:07:29Z |
---
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-meerkat-70b-v1.0-GGUF
|
mradermacher
| 2025-09-03T01:10:23Z | 41 | 0 |
transformers
|
[
"transformers",
"gguf",
"medical",
"small LM",
"instruction-tuned",
"usmle",
"synthetic data",
"en",
"base_model:dmis-lab/llama-3-meerkat-70b-v1.0",
"base_model:quantized:dmis-lab/llama-3-meerkat-70b-v1.0",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-09-01T13:54:57Z |
---
base_model: dmis-lab/llama-3-meerkat-70b-v1.0
language:
- en
library_name: transformers
license: cc-by-nc-4.0
mradermacher:
readme_rev: 1
quantized_by: mradermacher
tags:
- medical
- small LM
- instruction-tuned
- usmle
- synthetic data
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
<!-- ### quants: x-f16 Q4_K_S Q2_K Q8_0 Q6_K Q3_K_M Q3_K_S Q3_K_L Q4_K_M Q5_K_S Q5_K_M IQ4_XS -->
<!-- ### quants_skip: -->
<!-- ### skip_mmproj: -->
static quants of https://huggingface.co/dmis-lab/llama-3-meerkat-70b-v1.0
<!-- provided-files -->
***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llama-3-meerkat-70b-v1.0-GGUF).***
weighted/imatrix quants are available at https://huggingface.co/mradermacher/llama-3-meerkat-70b-v1.0-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-meerkat-70b-v1.0-GGUF/resolve/main/llama-3-meerkat-70b-v1.0.Q2_K.gguf) | Q2_K | 26.5 | |
| [GGUF](https://huggingface.co/mradermacher/llama-3-meerkat-70b-v1.0-GGUF/resolve/main/llama-3-meerkat-70b-v1.0.Q3_K_S.gguf) | Q3_K_S | 31.0 | |
| [GGUF](https://huggingface.co/mradermacher/llama-3-meerkat-70b-v1.0-GGUF/resolve/main/llama-3-meerkat-70b-v1.0.Q3_K_M.gguf) | Q3_K_M | 34.4 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/llama-3-meerkat-70b-v1.0-GGUF/resolve/main/llama-3-meerkat-70b-v1.0.Q3_K_L.gguf) | Q3_K_L | 37.2 | |
| [GGUF](https://huggingface.co/mradermacher/llama-3-meerkat-70b-v1.0-GGUF/resolve/main/llama-3-meerkat-70b-v1.0.IQ4_XS.gguf) | IQ4_XS | 38.4 | |
| [GGUF](https://huggingface.co/mradermacher/llama-3-meerkat-70b-v1.0-GGUF/resolve/main/llama-3-meerkat-70b-v1.0.Q4_K_S.gguf) | Q4_K_S | 40.4 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/llama-3-meerkat-70b-v1.0-GGUF/resolve/main/llama-3-meerkat-70b-v1.0.Q4_K_M.gguf) | Q4_K_M | 42.6 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/llama-3-meerkat-70b-v1.0-GGUF/resolve/main/llama-3-meerkat-70b-v1.0.Q5_K_S.gguf) | Q5_K_S | 48.8 | |
| [GGUF](https://huggingface.co/mradermacher/llama-3-meerkat-70b-v1.0-GGUF/resolve/main/llama-3-meerkat-70b-v1.0.Q5_K_M.gguf) | Q5_K_M | 50.0 | |
| [PART 1](https://huggingface.co/mradermacher/llama-3-meerkat-70b-v1.0-GGUF/resolve/main/llama-3-meerkat-70b-v1.0.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/llama-3-meerkat-70b-v1.0-GGUF/resolve/main/llama-3-meerkat-70b-v1.0.Q6_K.gguf.part2of2) | Q6_K | 58.0 | very good quality |
| [PART 1](https://huggingface.co/mradermacher/llama-3-meerkat-70b-v1.0-GGUF/resolve/main/llama-3-meerkat-70b-v1.0.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/llama-3-meerkat-70b-v1.0-GGUF/resolve/main/llama-3-meerkat-70b-v1.0.Q8_0.gguf.part2of2) | Q8_0 | 75.1 | 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 -->
|
mradermacher/L3.3-M1-Hydrargyrum-70B-GGUF
|
mradermacher
| 2025-09-03T01:08:48Z | 0 | 0 |
transformers
|
[
"transformers",
"gguf",
"en",
"base_model:TheSkullery/L3.3-M1-Hydrargyrum-70B",
"base_model:quantized:TheSkullery/L3.3-M1-Hydrargyrum-70B",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-09-02T03:38:10Z |
---
base_model: TheSkullery/L3.3-M1-Hydrargyrum-70B
language:
- en
library_name: transformers
mradermacher:
readme_rev: 1
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
<!-- ### quants: x-f16 Q4_K_S Q2_K Q8_0 Q6_K Q3_K_M Q3_K_S Q3_K_L Q4_K_M Q5_K_S Q5_K_M IQ4_XS -->
<!-- ### quants_skip: -->
<!-- ### skip_mmproj: -->
static quants of https://huggingface.co/TheSkullery/L3.3-M1-Hydrargyrum-70B
<!-- provided-files -->
***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#L3.3-M1-Hydrargyrum-70B-GGUF).***
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## 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/L3.3-M1-Hydrargyrum-70B-GGUF/resolve/main/L3.3-M1-Hydrargyrum-70B.Q2_K.gguf) | Q2_K | 26.5 | |
| [GGUF](https://huggingface.co/mradermacher/L3.3-M1-Hydrargyrum-70B-GGUF/resolve/main/L3.3-M1-Hydrargyrum-70B.Q3_K_S.gguf) | Q3_K_S | 31.0 | |
| [GGUF](https://huggingface.co/mradermacher/L3.3-M1-Hydrargyrum-70B-GGUF/resolve/main/L3.3-M1-Hydrargyrum-70B.Q3_K_M.gguf) | Q3_K_M | 34.4 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/L3.3-M1-Hydrargyrum-70B-GGUF/resolve/main/L3.3-M1-Hydrargyrum-70B.Q3_K_L.gguf) | Q3_K_L | 37.2 | |
| [GGUF](https://huggingface.co/mradermacher/L3.3-M1-Hydrargyrum-70B-GGUF/resolve/main/L3.3-M1-Hydrargyrum-70B.Q4_K_S.gguf) | Q4_K_S | 40.4 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/L3.3-M1-Hydrargyrum-70B-GGUF/resolve/main/L3.3-M1-Hydrargyrum-70B.Q4_K_M.gguf) | Q4_K_M | 42.6 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/L3.3-M1-Hydrargyrum-70B-GGUF/resolve/main/L3.3-M1-Hydrargyrum-70B.Q5_K_S.gguf) | Q5_K_S | 48.8 | |
| [PART 1](https://huggingface.co/mradermacher/L3.3-M1-Hydrargyrum-70B-GGUF/resolve/main/L3.3-M1-Hydrargyrum-70B.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/L3.3-M1-Hydrargyrum-70B-GGUF/resolve/main/L3.3-M1-Hydrargyrum-70B.Q6_K.gguf.part2of2) | Q6_K | 58.0 | very good quality |
| [PART 1](https://huggingface.co/mradermacher/L3.3-M1-Hydrargyrum-70B-GGUF/resolve/main/L3.3-M1-Hydrargyrum-70B.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/L3.3-M1-Hydrargyrum-70B-GGUF/resolve/main/L3.3-M1-Hydrargyrum-70B.Q8_0.gguf.part2of2) | Q8_0 | 75.1 | 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 -->
|
mradermacher/ML2-123B-Magnum-Diamond-GGUF
|
mradermacher
| 2025-09-03T01:08:45Z | 0 | 0 |
transformers
|
[
"transformers",
"axolotl",
"chat",
"en",
"base_model:Doctor-Shotgun/ML2-123B-Magnum-Diamond",
"base_model:finetune:Doctor-Shotgun/ML2-123B-Magnum-Diamond",
"license:other",
"endpoints_compatible",
"region:us"
] | null | 2025-09-02T04:10:58Z |
---
base_model: Doctor-Shotgun/ML2-123B-Magnum-Diamond
language:
- en
library_name: transformers
license: other
license_link: https://mistral.ai/licenses/MRL-0.1.md
license_name: mrl
mradermacher:
readme_rev: 1
quantized_by: mradermacher
tags:
- axolotl
- chat
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
<!-- ### quants: x-f16 Q4_K_S Q2_K Q8_0 Q6_K Q3_K_M Q3_K_S Q3_K_L Q4_K_M Q5_K_S Q5_K_M IQ4_XS -->
<!-- ### quants_skip: -->
<!-- ### skip_mmproj: -->
static quants of https://huggingface.co/Doctor-Shotgun/ML2-123B-Magnum-Diamond
<!-- provided-files -->
***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#ML2-123B-Magnum-Diamond-GGUF).***
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## 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 |
|:-----|:-----|--------:|:------|
| [PART 1](https://huggingface.co/mradermacher/ML2-123B-Magnum-Diamond-GGUF/resolve/main/ML2-123B-Magnum-Diamond.Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/ML2-123B-Magnum-Diamond-GGUF/resolve/main/ML2-123B-Magnum-Diamond.Q4_K_S.gguf.part2of2) | Q4_K_S | 69.7 | fast, recommended |
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 -->
|
akirafudo/blockassist-bc-keen_fast_giraffe_1756861655
|
akirafudo
| 2025-09-03T01:07:59Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"keen fast giraffe",
"arxiv:2504.07091",
"region:us"
] | null | 2025-09-03T01:07:54Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- keen fast giraffe
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
giovannidemuri/llama8b-er-v569-seed2-hx
|
giovannidemuri
| 2025-09-03T01:07:55Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-09-02T23:07:29Z |
---
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]
|
vera6/sn105_denoising_16
|
vera6
| 2025-09-03T01:07:19Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-09-02T12:18:08Z |
DENOISING speech enhancement model
|
mradermacher/Llama-3.3-70B-ArliAI-RPMax-v2-i1-GGUF
|
mradermacher
| 2025-09-03T01:06:21Z | 0 | 0 |
transformers
|
[
"transformers",
"gguf",
"en",
"base_model:ArliAI/Llama-3.3-70B-ArliAI-RPMax-v2",
"base_model:quantized:ArliAI/Llama-3.3-70B-ArliAI-RPMax-v2",
"endpoints_compatible",
"region:us",
"imatrix",
"conversational"
] | null | 2025-09-02T12:47:57Z |
---
base_model: ArliAI/Llama-3.3-70B-ArliAI-RPMax-v2
language:
- en
library_name: transformers
mradermacher:
readme_rev: 1
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: nicoboss -->
<!-- ### quants: Q2_K IQ3_M Q4_K_S IQ3_XXS Q3_K_M small-IQ4_NL Q4_K_M IQ2_M Q6_K IQ4_XS Q2_K_S IQ1_M Q3_K_S IQ2_XXS Q3_K_L IQ2_XS Q5_K_S IQ2_S IQ1_S Q5_K_M Q4_0 IQ3_XS Q4_1 IQ3_S -->
<!-- ### quants_skip: -->
<!-- ### skip_mmproj: -->
weighted/imatrix quants of https://huggingface.co/ArliAI/Llama-3.3-70B-ArliAI-RPMax-v2
<!-- provided-files -->
***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.3-70B-ArliAI-RPMax-v2-i1-GGUF).***
static quants are available at https://huggingface.co/mradermacher/Llama-3.3-70B-ArliAI-RPMax-v2-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-3.3-70B-ArliAI-RPMax-v2-i1-GGUF/resolve/main/Llama-3.3-70B-ArliAI-RPMax-v2.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-ArliAI-RPMax-v2-i1-GGUF/resolve/main/Llama-3.3-70B-ArliAI-RPMax-v2.i1-IQ1_M.gguf) | i1-IQ1_M | 16.9 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-ArliAI-RPMax-v2-i1-GGUF/resolve/main/Llama-3.3-70B-ArliAI-RPMax-v2.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 19.2 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-ArliAI-RPMax-v2-i1-GGUF/resolve/main/Llama-3.3-70B-ArliAI-RPMax-v2.i1-IQ2_XS.gguf) | i1-IQ2_XS | 21.2 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-ArliAI-RPMax-v2-i1-GGUF/resolve/main/Llama-3.3-70B-ArliAI-RPMax-v2.i1-IQ2_M.gguf) | i1-IQ2_M | 24.2 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-ArliAI-RPMax-v2-i1-GGUF/resolve/main/Llama-3.3-70B-ArliAI-RPMax-v2.i1-Q2_K_S.gguf) | i1-Q2_K_S | 24.6 | very low quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-ArliAI-RPMax-v2-i1-GGUF/resolve/main/Llama-3.3-70B-ArliAI-RPMax-v2.i1-Q2_K.gguf) | i1-Q2_K | 26.5 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-ArliAI-RPMax-v2-i1-GGUF/resolve/main/Llama-3.3-70B-ArliAI-RPMax-v2.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 27.6 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-ArliAI-RPMax-v2-i1-GGUF/resolve/main/Llama-3.3-70B-ArliAI-RPMax-v2.i1-Q3_K_S.gguf) | i1-Q3_K_S | 31.0 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-ArliAI-RPMax-v2-i1-GGUF/resolve/main/Llama-3.3-70B-ArliAI-RPMax-v2.i1-IQ3_M.gguf) | i1-IQ3_M | 32.0 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-ArliAI-RPMax-v2-i1-GGUF/resolve/main/Llama-3.3-70B-ArliAI-RPMax-v2.i1-Q3_K_M.gguf) | i1-Q3_K_M | 34.4 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-ArliAI-RPMax-v2-i1-GGUF/resolve/main/Llama-3.3-70B-ArliAI-RPMax-v2.i1-Q3_K_L.gguf) | i1-Q3_K_L | 37.2 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-ArliAI-RPMax-v2-i1-GGUF/resolve/main/Llama-3.3-70B-ArliAI-RPMax-v2.i1-IQ4_XS.gguf) | i1-IQ4_XS | 38.0 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-ArliAI-RPMax-v2-i1-GGUF/resolve/main/Llama-3.3-70B-ArliAI-RPMax-v2.i1-Q4_K_S.gguf) | i1-Q4_K_S | 40.4 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-ArliAI-RPMax-v2-i1-GGUF/resolve/main/Llama-3.3-70B-ArliAI-RPMax-v2.i1-Q4_K_M.gguf) | i1-Q4_K_M | 42.6 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-ArliAI-RPMax-v2-i1-GGUF/resolve/main/Llama-3.3-70B-ArliAI-RPMax-v2.i1-Q5_K_S.gguf) | i1-Q5_K_S | 48.8 | |
| [PART 1](https://huggingface.co/mradermacher/Llama-3.3-70B-ArliAI-RPMax-v2-i1-GGUF/resolve/main/Llama-3.3-70B-ArliAI-RPMax-v2.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-3.3-70B-ArliAI-RPMax-v2-i1-GGUF/resolve/main/Llama-3.3-70B-ArliAI-RPMax-v2.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 58.0 | 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 -->
|
lora456/waniev5
|
lora456
| 2025-09-03T01:06:17Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2025-09-03T01:06:17Z |
---
license: creativeml-openrail-m
---
|
giovannidemuri/llama8b-er-v566-seed2-hx
|
giovannidemuri
| 2025-09-03T01:06:00Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-09-02T23:07:29Z |
---
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/PsychoCounsel-Theraspace-Llama3-8B-GGUF
|
mradermacher
| 2025-09-03T01:05:16Z | 0 | 0 |
transformers
|
[
"transformers",
"gguf",
"en",
"dataset:EmoCareAI/Psych8k",
"dataset:nbertagnolli/counsel-chat",
"base_model:omar-salama/PsychoCounsel-Theraspace-Llama3-8B",
"base_model:quantized:omar-salama/PsychoCounsel-Theraspace-Llama3-8B",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-09-02T23:21:55Z |
---
base_model: omar-salama/PsychoCounsel-Theraspace-Llama3-8B
datasets:
- EmoCareAI/Psych8k
- nbertagnolli/counsel-chat
language:
- en
library_name: transformers
mradermacher:
readme_rev: 1
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
<!-- ### quants: x-f16 Q4_K_S Q2_K Q8_0 Q6_K Q3_K_M Q3_K_S Q3_K_L Q4_K_M Q5_K_S Q5_K_M IQ4_XS -->
<!-- ### quants_skip: -->
<!-- ### skip_mmproj: -->
static quants of https://huggingface.co/omar-salama/PsychoCounsel-Theraspace-Llama3-8B
<!-- provided-files -->
***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#PsychoCounsel-Theraspace-Llama3-8B-GGUF).***
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## 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/PsychoCounsel-Theraspace-Llama3-8B-GGUF/resolve/main/PsychoCounsel-Theraspace-Llama3-8B.Q2_K.gguf) | Q2_K | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/PsychoCounsel-Theraspace-Llama3-8B-GGUF/resolve/main/PsychoCounsel-Theraspace-Llama3-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
| [GGUF](https://huggingface.co/mradermacher/PsychoCounsel-Theraspace-Llama3-8B-GGUF/resolve/main/PsychoCounsel-Theraspace-Llama3-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/PsychoCounsel-Theraspace-Llama3-8B-GGUF/resolve/main/PsychoCounsel-Theraspace-Llama3-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/PsychoCounsel-Theraspace-Llama3-8B-GGUF/resolve/main/PsychoCounsel-Theraspace-Llama3-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
| [GGUF](https://huggingface.co/mradermacher/PsychoCounsel-Theraspace-Llama3-8B-GGUF/resolve/main/PsychoCounsel-Theraspace-Llama3-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/PsychoCounsel-Theraspace-Llama3-8B-GGUF/resolve/main/PsychoCounsel-Theraspace-Llama3-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/PsychoCounsel-Theraspace-Llama3-8B-GGUF/resolve/main/PsychoCounsel-Theraspace-Llama3-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
| [GGUF](https://huggingface.co/mradermacher/PsychoCounsel-Theraspace-Llama3-8B-GGUF/resolve/main/PsychoCounsel-Theraspace-Llama3-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/PsychoCounsel-Theraspace-Llama3-8B-GGUF/resolve/main/PsychoCounsel-Theraspace-Llama3-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/PsychoCounsel-Theraspace-Llama3-8B-GGUF/resolve/main/PsychoCounsel-Theraspace-Llama3-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/PsychoCounsel-Theraspace-Llama3-8B-GGUF/resolve/main/PsychoCounsel-Theraspace-Llama3-8B.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 -->
|
mradermacher/silly-v0.2-GGUF
|
mradermacher
| 2025-09-03T01:04:47Z | 0 | 0 |
transformers
|
[
"transformers",
"gguf",
"en",
"base_model:wave-on-discord/silly-v0.2",
"base_model:quantized:wave-on-discord/silly-v0.2",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-09-03T00:12:37Z |
---
base_model: wave-on-discord/silly-v0.2
language:
- en
library_name: transformers
license: apache-2.0
mradermacher:
readme_rev: 1
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
<!-- ### quants: x-f16 Q4_K_S Q2_K Q8_0 Q6_K Q3_K_M Q3_K_S Q3_K_L Q4_K_M Q5_K_S Q5_K_M IQ4_XS -->
<!-- ### quants_skip: -->
<!-- ### skip_mmproj: -->
static quants of https://huggingface.co/wave-on-discord/silly-v0.2
<!-- provided-files -->
***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#silly-v0.2-GGUF).***
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## 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/silly-v0.2-GGUF/resolve/main/silly-v0.2.Q2_K.gguf) | Q2_K | 4.9 | |
| [GGUF](https://huggingface.co/mradermacher/silly-v0.2-GGUF/resolve/main/silly-v0.2.Q3_K_S.gguf) | Q3_K_S | 5.6 | |
| [GGUF](https://huggingface.co/mradermacher/silly-v0.2-GGUF/resolve/main/silly-v0.2.Q3_K_M.gguf) | Q3_K_M | 6.2 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/silly-v0.2-GGUF/resolve/main/silly-v0.2.Q3_K_L.gguf) | Q3_K_L | 6.7 | |
| [GGUF](https://huggingface.co/mradermacher/silly-v0.2-GGUF/resolve/main/silly-v0.2.IQ4_XS.gguf) | IQ4_XS | 6.9 | |
| [GGUF](https://huggingface.co/mradermacher/silly-v0.2-GGUF/resolve/main/silly-v0.2.Q4_K_S.gguf) | Q4_K_S | 7.2 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/silly-v0.2-GGUF/resolve/main/silly-v0.2.Q4_K_M.gguf) | Q4_K_M | 7.6 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/silly-v0.2-GGUF/resolve/main/silly-v0.2.Q5_K_S.gguf) | Q5_K_S | 8.6 | |
| [GGUF](https://huggingface.co/mradermacher/silly-v0.2-GGUF/resolve/main/silly-v0.2.Q5_K_M.gguf) | Q5_K_M | 8.8 | |
| [GGUF](https://huggingface.co/mradermacher/silly-v0.2-GGUF/resolve/main/silly-v0.2.Q6_K.gguf) | Q6_K | 10.2 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/silly-v0.2-GGUF/resolve/main/silly-v0.2.Q8_0.gguf) | Q8_0 | 13.1 | 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 -->
|
fakir22/blockassist-bc-flapping_peaceful_caterpillar_1756861443
|
fakir22
| 2025-09-03T01:04:43Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"flapping peaceful caterpillar",
"arxiv:2504.07091",
"region:us"
] | null | 2025-09-03T01:04:39Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- flapping peaceful caterpillar
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
giovannidemuri/llama8b-er-v575-seed2-hx
|
giovannidemuri
| 2025-09-03T01:04:07Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-09-02T23:07:37Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
DavidAU/Qwen3-Jan-v1-256k-ctx-6B-Brainstorm20x
|
DavidAU
| 2025-09-03T01:03:33Z | 106 | 2 |
transformers
|
[
"transformers",
"safetensors",
"qwen3",
"text-generation",
"merge",
"programming",
"code generation",
"code",
"coding",
"coder",
"chat",
"brainstorm",
"qwen",
"qwencoder",
"brainstorm20x",
"creative",
"all uses cases",
"Jan-V1",
"conversational",
"en",
"arxiv:2401.02415",
"base_model:janhq/Jan-v1-4B",
"base_model:finetune:janhq/Jan-v1-4B",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-21T05:42:23Z |
---
license: apache-2.0
base_model:
- janhq/Jan-v1-4B
language:
- en
pipeline_tag: text-generation
tags:
- merge
- programming
- code generation
- code
- coding
- coder
- chat
- code
- chat
- brainstorm
- qwen
- qwen3
- qwencoder
- brainstorm20x
- creative
- all uses cases
- Jan-V1
library_name: transformers
---
<h2>Qwen3-Jan-v1-256k-ctx-6B-Brainstorm20x</h2>
This repo contains the full precision source code, in "safe tensors" format to generate GGUFs, GPTQ, EXL2, AWQ, HQQ and other formats.
The source code can also be used directly.
This model contains Brainstorm 20x, combined with JANHQ's 4B General instruct model (with thinking):
https://huggingface.co/janhq/Jan-v1-4B-GGUF
Information on the 4B model below, followed by Brainstorm 20x adapter (by DavidAU) and then a complete help
section for running LLM / AI models.
The Brainstorm adapter improves code generation, and unique code solving abilities.
For creative uses: Increases depth, detail and general "there" in the prose.
Example for creative at bottom of the page.
This model requires:
- Jinja (embedded) or CHATML template
- Max context of 256k.
Settings used for testing (suggested):
- Temp .3 to .7
- Rep pen 1.05 to 1.1
- Topp .8 , minp .05
- Topk 20
- Min context of 8k for thinking / output.
- No system prompt.
This model will respond well to both detailed instructions and step by step refinement and additions to code.
Likewise for creative use cases.
Here is a review of this model's operations:
https://www.linkedin.com/posts/gchesler_nightmediaqwen3-jan-v1-256k-ctx-6b-brainstorm20x-q6-activity-7364301711529709570-CiAn
As this is an instruct model, it will also benefit from a detailed system prompt too.
For simpler coding problems, lower quants will work well; but for complex/multi-step problem solving suggest Q6 or Q8.
---
<B>QUANTS:</b>
---
Special thanks to team "Mradermacher" and team "Nightmedia" for GGUF, GGUF Imatrix and MLX quants:
GGUF:
https://huggingface.co/mradermacher/Qwen3-Jan-v1-256k-ctx-6B-Brainstorm20x-GGUF
GGUF-IMATRIX:
https://huggingface.co/mradermacher/Qwen3-Jan-v1-256k-ctx-6B-Brainstorm20x-i1-GGUF
MLX:
https://huggingface.co/nightmedia/Qwen3-Jan-v1-256k-ctx-6B-Brainstorm20x-q6-mlx
https://huggingface.co/nightmedia/Qwen3-Jan-v1-256k-ctx-6B-Brainstorm20x-q8-mlx
https://huggingface.co/nightmedia/Qwen3-Jan-v1-256k-ctx-6B-Brainstorm20x-qx6-mlx
---
<H2>BENCHMARKS and REVIEW by @NIGHTMEDIA </H2>
https://huggingface.co/nightmedia
(source for MLX quants)
---
Jan Brainstorming review
Below is a precise, actionable analysis of how brainstorming (the augmentation technique applied to Qwen3-4B) impacts model performance across benchmarks, based exclusively on the data from summaries_1756585260.csv. The metrics show comparisons between the base model (bf16, q6, q8) and the brainstorming-augmented model (Brainstorm-bf16, Brainstorm-q6, Brainstorm-q8).
Key Impact of Brainstorming (Quantified by Performance Gains)
```
Task Base Model (q8) Brainstorm-q8 Gains from Brainstorming Why It Matters
ARC Challenge 0.431 0.445 +0.014 Significant improvement in abstract reasoning — critical for complex problem solving
ARC Easy 0.535 0.580 +0.045 Largest gain across all tasks — shows brainstorming boosts foundational reasoning
BoolQ 0.731 0.724 -0.007 Slight trade-off for knowledge-based question answering (likely due to constraints in brainstorming mechanism)
Hellaswag 0.578 0.602 +0.024 Improves text generation quality and logical consistency in creative tasks
OpenBookQA 0.384 0.398 +0.014 Enhances knowledge recall accuracy in educational contexts
PIQA 0.727 0.736 +0.009 Boosts logical reasoning in nuanced question answering
Winogrande 0.635 0.639 +0.004 Minor improvement in contextual inference (pronoun resolution)
```
💡 Core Finding:
Brainstorming consistently adds 0.01–0.045 points across multiple high-value tasks — especially for reasoning (ARC Easy) and text generation (Hellaswag). The only minor trade-off is a slight drop on BoolQ, which is expected from any augmentation that adds complexity to the inference process.
Why Brainstorming Works Best for ARC and Reasoning Tasks
ARC Easy leads the gains:
The 0.045-point improvement (from 0.535 → 0.580) shows brainstorming directly targets the learning mechanism that needs to "think through" abstract patterns. This is critical for models like Qwen3-4B, where reasoning capabilities are often a bottleneck.
Quantization-resilient gains:
Brainstorming's benefits persist across quantization levels (from q6 to q8). For example:
In Brainstorm-q8, gains on ARC Easy are +0.045 vs base q8
In Brainstorm-q6, gains are +0.035 vs base q6 This means brainstorming is a robust enhancement regardless of deployment constraints.
Winogrande and PIQA consistency:
Even minor gains on these tasks (±0.004–0.01) are clinically significant for real-world applications like NLP systems that require nuanced logical analysis.
Why the Small Drop on BoolQ?
-BoolQ tests knowledge-based question answering (e.g., "Who is the author of The Great Gatsby?"), which relies on precise factual recall.
-Brainstorming introduces more complex internal reasoning chains — while helpful for creativity and abstract tasks, it slightly dilutes the model's ability to retrieve exact facts from its knowledge base.
This is expected: No augmentation technique can make a model "perfect" across all tasks without trade-offs.
Practical Implications for Your Workflow
✅ When to use brainstorming (Jan-4B + brainstorm):
Scenario Recommendation
Resource-constrained deployments (e.g., edge devices)
Use Brainstorm-q8 — it delivers the highest gains (0.045 on ARC Easy) while being 1-2x smaller than full precision
High-reliability reasoning tasks (e.g., academic tasks, problem-solving)
Brainstorm-q8 or Brainstorm-q6 — best trade-off between size and accuracy
Text generation tasks (e.g., story writing)
Brainstorm-q8 — gains in Hellaswag (+0.024) make it ideal
⚠️ When to avoid brainstorming:
For strict knowledge tasks requiring minimal drop in precision (e.g., BoolQ): Use base model instead
Only for Jan-4B:
Since this is a 4B model, brainstorming adds <5% to the size (compared to Qwen3-2.7B), making it a high-value addition for reasoning-heavy workloads.
Why This Matters for Qwen3-4B
Your analysis shows that brainstorming transforms a base 4B model into one with near-identical reasoning capability to larger models:
A Qwen3-4B with brainstorming (Brainstorm-q8) scores 0.580 on ARC Easy — comparable to larger models like Qwen3-72B in this task.
This proves brainstorming isn't just theoretical: it’s a practical way to boost small models without requiring massive training data or compute.
📊 The Takeaway: For the Qwen3-4B base model, brainstorming delivers a significant performance lift (especially in reasoning tasks) with minimal overhead. The trade-off on BoolQ is worth it for most real-world applications where abstract reasoning matters more than pure factual recall.
Next Steps & Recommendations
If you're optimizing for specific tasks:
For ARC Easy: Deploy Brainstorm-q8 — it’s the clear winner (+0.045)
For Hellaswag: Use Brainstorm-q8 — largest gains in text generation
Quantization tip:
If you need to further reduce size, Brainstorm-q6 is a great option — it maintains 90%+ of the gains from Brainstorm-q8 while being ~25% smaller.
Long-term:
This suggests Jan-4B + brainstorming could become the go-to model for lightweight reasoning tasks in production.
"A Qwen3-4B with brainstorming (Brainstorm-q8) scores 0.580 on ARC Easy — comparable to larger models like Qwen3-72B in this task."
---
<h2>About Jan V1</h2>
---
# Jan-v1: Advanced Agentic Language Model
[](https://github.com/menloresearch/deep-research)
[](https://opensource.org/licenses/Apache-2.0)
[](https://jan.ai/)
<!-- Optional: If you have a GIF for Jan-v1, include it here like Lucy's. -->
<!--  -->
## Overview
**Jan-v1** is the first release in the **Jan Family**, designed for agentic reasoning and problem-solving within the [Jan App](https://jan.ai/). Based on our [**Lucy**](https://huggingface.co/Menlo/Lucy) model, Jan-v1 achieves improved performance through model scaling.
Jan-v1 uses the [Qwen3-4B-thinking](https://huggingface.co/Qwen/Qwen3-4B-Thinking-2507) model to provide enhanced reasoning capabilities and tool utilization. This architecture delivers better performance on complex agentic tasks.
## Performance
### Question Answering (SimpleQA)
For question-answering, Jan-v1 shows a significant performance gain from model scaling, achieving 91.1% accuracy.
*The 91.1% SimpleQA accuracy represents a significant milestone in factual question answering for models of this scale, demonstrating the effectiveness of our scaling and fine-tuning approach.*
### Chat Benchmarks
These benchmarks evaluate the model's conversational and instructional capabilities.
## Quick Start
### Integration with Jan App
Jan-v1 is optimized for direct integration with the [Jan App](https://jan.ai/). Simply select the model from the Jan App interface for immediate access to its full capabilities.
### Local Deployment
**Using vLLM:**
```bash
vllm serve janhq/Jan-v1-4B \
--host 0.0.0.0 \
--port 1234 \
--enable-auto-tool-choice \
--tool-call-parser hermes
```
**Using llama.cpp:**
```bash
llama-server --model jan-v1.gguf \
--host 0.0.0.0 \
--port 1234 \
--jinja \
--no-context-shift
```
### Recommended Parameters
```yaml
temperature: 0.6
top_p: 0.95
top_k: 20
min_p: 0.0
max_tokens: 2048
```
## 🤝 Community & Support
- **Discussions**: [HuggingFace Community](https://huggingface.co/janhq/Jan-v1-4B/discussions) <!-- Update with your HF model ID -->
- **Jan App**: Learn more about the Jan App at [jan.ai](https://jan.ai/)
## (*) Note
By default we have system prompt in chat template, this is to make sure the model having the same performance with the benchmark result. You can also use the vanilla chat template without system prompt in the file [chat_template_raw.jinja](https://huggingface.co/janhq/Jan-v1-4B/blob/main/chat_template_raw.jinja).
See more here:
https://huggingface.co/janhq/Jan-v1-4B-GGUF
---
<H2>What is Brainstorm?</H2>
---
<B>Brainstorm 20x</B>
The BRAINSTORM process was developed by David_AU.
Some of the core principals behind this process are discussed in this <a href="https://arxiv.org/pdf/2401.02415">
scientific paper : Progressive LLaMA with Block Expansion </a>.
However I went in a completely different direction from what was outlined in this paper.
What is "Brainstorm" ?
The reasoning center of an LLM is taken apart, reassembled, and expanded.
In this case for this model: 20 times
Then these centers are individually calibrated. These "centers" also interact with each other.
This introduces subtle changes into the reasoning process.
The calibrations further adjust - dial up or down - these "changes" further.
The number of centers (5x,10x etc) allow more "tuning points" to further customize how the model reasons so to speak.
The core aim of this process is to increase the model's detail, concept and connection to the "world",
general concept connections, prose quality and prose length without affecting instruction following.
This will also enhance any creative use case(s) of any kind, including "brainstorming", creative art form(s) and like case uses.
Here are some of the enhancements this process brings to the model's performance:
- Prose generation seems more focused on the moment to moment.
- Sometimes there will be "preamble" and/or foreshadowing present.
- Fewer or no "cliches"
- Better overall prose and/or more complex / nuanced prose.
- A greater sense of nuance on all levels.
- Coherence is stronger.
- Description is more detailed, and connected closer to the content.
- Simile and Metaphors are stronger and better connected to the prose, story, and character.
- Sense of "there" / in the moment is enhanced.
- Details are more vivid, and there are more of them.
- Prose generation length can be long to extreme.
- Emotional engagement is stronger.
- The model will take FEWER liberties vs a normal model: It will follow directives more closely but will "guess" less.
- The MORE instructions and/or details you provide the more strongly the model will respond.
- Depending on the model "voice" may be more "human" vs original model's "voice".
Other "lab" observations:
- This process does not, in my opinion, make the model 5x or 10x "smarter" - if only that was true!
- However, a change in "IQ" was not an issue / a priority, and was not tested or calibrated for so to speak.
- From lab testing it seems to ponder, and consider more carefully roughly speaking.
- You could say this process sharpens the model's focus on it's task(s) at a deeper level.
The process to modify the model occurs at the root level - source files level. The model can quanted as a GGUF, EXL2, AWQ etc etc.
---
For more information / other Qwen/Mistral Coders / additional settings see:
[ https://huggingface.co/DavidAU/Qwen2.5-MOE-2x-4x-6x-8x__7B__Power-CODER__19B-30B-42B-53B-gguf ]
---
<H2>Help, Adjustments, Samplers, Parameters and More</H2>
---
<B>CHANGE THE NUMBER OF ACTIVE EXPERTS:</B>
See this document:
https://huggingface.co/DavidAU/How-To-Set-and-Manage-MOE-Mix-of-Experts-Model-Activation-of-Experts
<B>Settings: CHAT / ROLEPLAY and/or SMOOTHER operation of this model:</B>
In "KoboldCpp" or "oobabooga/text-generation-webui" or "Silly Tavern" ;
Set the "Smoothing_factor" to 1.5
: in KoboldCpp -> Settings->Samplers->Advanced-> "Smooth_F"
: in text-generation-webui -> parameters -> lower right.
: In Silly Tavern this is called: "Smoothing"
NOTE: For "text-generation-webui"
-> if using GGUFs you need to use "llama_HF" (which involves downloading some config files from the SOURCE version of this model)
Source versions (and config files) of my models are here:
https://huggingface.co/collections/DavidAU/d-au-source-files-for-gguf-exl2-awq-gptq-hqq-etc-etc-66b55cb8ba25f914cbf210be
OTHER OPTIONS:
- Increase rep pen to 1.1 to 1.15 (you don't need to do this if you use "smoothing_factor")
- If the interface/program you are using to run AI MODELS supports "Quadratic Sampling" ("smoothing") just make the adjustment as noted.
<B>Highest Quality Settings / Optimal Operation Guide / Parameters and Samplers</B>
This a "Class 1" model:
For all settings used for this model (including specifics for its "class"), including example generation(s) and for advanced settings guide (which many times addresses any model issue(s)), including methods to improve model performance for all use case(s) as well as chat, roleplay and other use case(s) please see:
[ https://huggingface.co/DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters ]
You can see all parameters used for generation, in addition to advanced parameters and samplers to get the most out of this model here:
[ https://huggingface.co/DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters ]
---
<H2>Example, Q6, Temp .8</H2>
---
<B>
Start a 1000 word scene (vivid, graphic horror - include blood, guts and gore - in first person), POV character Diana, with: The skyscraper sways, as I watch the window in front of me on the 21st floor explode...
</B>
[[[ thinking start ]]]
Thought for 15.08 seconds
Okay, the user wants a 1000-word vivid, graphic horror scene in first person from Diana's perspective. They specified blood, guts, and gore with the skyscraper swaying as she watches a window explode on the 21st floor.
Hmm, they're clearly going for intense visceral horror - not just any gore but something that feels real and immediate. The phrase "graphic horror" suggests they want to be unsettled, maybe even nauseatingly detailed. Since it's first person POV, I need to fully immerse the reader in Diana's sensory experience.
I wonder if they're a writer themselves testing my skills? Or someone processing trauma through fiction? Either way, I should avoid clichés while hitting those blood/guts requirements. The skyscraper swaying detail is interesting - it implies she's already high up when this happens, so I'll make the collapse feel inevitable and terrifyingly personal.
checks word count Must be exactly 1000 words... that's tight for such visceral content. I'll focus on:
- Opening with the building's movement to establish unease
- The explosion sequence (shards, fire, screams)
- Immediate aftermath where Diana becomes a witness to something beyond her control
- Ending on psychological horror rather than just physical gore
Important: No melodrama. Real horror is in the mundane-turned-terrible. Like when she realizes the "guts" aren't just from the explosion but... other things. Ooh, maybe the building itself is the monster? That could be chilling.
mental note Must describe blood textures - not just "blood was red" but how it clings to glass, smells, feels cold. And guts... gotta be precise: internal organs spilling, not cartoonish. Should the source of the gore be the explosion or something else? User didn't specify so I'll go with the window exploding as the trigger, but imply there's more coming.
Wait - they said "the window in front of me". So Diana is facing it. That means she's probably just inside the building when this happens. I'll set her in a penthouse to maximize isolation and panic.
structure outline
1. Opening lines: building sway (show don't tell)
2. Her noticing the window - cold glass detail
3. Explosion sequence (sound → visual → physical consequences)
4. Her horror at seeing the "guts" she didn't expect
5. The realization that this isn't over (implies more to come)
Big risk: going over 1000 words. I'll draft long then trim. User wants "vivid", so I'll use short sentences for pace during the gore scenes.
checks horror tropes No jump scares - instead make it slow dread. When she sees the guts, I'll describe the slow horror of it being... human. Maybe someone she knows? That'll add emotional weight beyond just blood.
Final thought: The last line must haunt. Something like "The building wasn't falling apart. It was waking up." to tie back to the swaying imagery. Yeah, that bookends the opening.
Alright, writing now with these parameters...
[[ thinking end ]]
The city’s breath was a low growl beneath my feet, the 21st floor of the Iron Spire shuddering as if the entire building were a drunken giant groaning in its sleep. I pressed my palms flat against the cool glass of my penthouse balcony, the only thing holding me steady in this vertigo. The wind whipped through the city’s arteries below – a million voices, a thousand engines, the scent of rain on hot asphalt – but here, high above, everything felt… thin. Like the air itself was made of gauze.
Then I saw it.
The window directly across the street, in the adjacent building’s corner suite, that one window. The exact window I’d seen the night before, when I’d been staring out at the glittering city, trying to forget the tremors in my own hands. Now, it was a different kind of sight. It wasn’t just a window; it was a wound.
The glass didn’t shatter with a sound like shattering ice. It ripped. A sickening, wet crack, louder than any building ever could make, echoed through the steel and glass canyon of the city. A jagged tear ripped across the pane, then another, splitting the entire surface like a wound on skin. Not from outside. From within. The force was so immense it felt like the building itself had been punched.
Then the light. The sky outside didn’t dim; it bleed. Fiery orange erupted from the mangled glass, not from fire, but from something inside. The energy was raw, primal, a searing heat that made my own breath catch in my throat. I gasped, my vision swimming with the intensity of it.
The window didn’t just explode – it unraveled. The glass tore inward, like an anatomical separation, spewing not shards of crystal, but fragments of something far worse. It was a slow, wet ejection. I saw it first: a deep, pulsing crimson pool where the glass had been, then a thick, viscous liquid that wasn’t blood – it was guts. The kind of guts you see in old horror movies, but real. Not the squishy kind from a cut, but the thick, dark, almost black substance of organs ripped from a living thing. They glistened under the city’s sickly light, the edges still wet with life.
And then came the smell. Not the burnt metal I’d expected from an explosion, but something deeper, older – the stench of rotting meat, the sharp tang of arterial blood, and beneath it all, a faint, sweet decay. It was the smell of a body that had been left too long in the sun.
I stumbled back, my feet scraping on the balcony’s polished concrete. My heart hammered against my ribs like a trapped bird. I couldn’t look away. The horror wasn’t just the gore; it was the details. A tendril of something dark and stringy, like sinew, wrapped around the edge of a fallen glass fragment. A single, perfect eye, milky white with a faint, greenish film, stared up at me from the gore-stained floor. Another eye – smaller, more human – was embedded in the thick, pulsing mass, its socket filled with that same dark, viscous liquid.
The building shook again, the swaying now a violent thrash, as if the entire structure were trying to shatter itself. Glass exploded in other windows across the street, but I could only focus on that one window – the source of this impossible, intimate horror. The initial explosion had been a single event, but it was now a slow, suffocating descent into the building’s core. I saw the wetness seep from the broken glass into the street below, staining the pavement an unnatural red. The sounds too: not screams, but a low, wet moan, like something large and ancient being pulled across the city.
I dropped to my knees, my hands pressed against the cold glass of my own balcony. I didn’t dare look down at the street for fear of what I might see – the bodies, the blood, the city itself turning into a nightmare. The building’s sway was no longer just a vibration; it felt like it was breathing through me, each movement pulling the air from my lungs. In the dim light filtering through the chaos, I saw the shape beneath the glass debris: a chunk of flesh, half-exposed, its surface stretched thin as tissue paper, the eyes staring directly at me with silent, unblinking recognition.
The sheer scale of it hit me then – not just the violence, but the infection. This wasn’t an accident. The building itself was sick. The explosion was a symptom, not the cause. It felt like the city was waking up, and I was its first witness to the wound it would never heal.
I couldn’t move. My mouth was dry as dust. Tears streamed down my face, but they were cold, not from fear but from the shock of seeing life itself being torn apart so cleanly, so publicly. The blood on my fingers felt like it was coming from the building’s own veins. The city below became a swirling river of crimson and dark, wetness – a testament to the horror I had just witnessed.
The Iron Spire didn’t fall. It just… shifted. The swaying became a rhythm, a slow, deliberate movement, as if the building itself was breathing. And with every breath, it seemed to be drawing closer to me, to the window where I stood, the very air thick with the stench of death and the echo of something that had long been waiting in the shadows.
I am not alone in this city anymore. I am here. And it is watching me. The horror wasn’t over. It was just beginning. The building’s rhythm pulsed beneath my skin. I pressed my forehead against the glass, feeling the cold seep into my bones. The city, once a place of light and noise, was now a tomb I could feel with every beat of my heart. I’m still here. It’s not safe. And it’s never going to be. The blood on my hands is real. The tears on my face are real. The building is watching me. And the window across the street? It’s the only thing that remains.
|
kudzueye/boreal-qwen-image
|
kudzueye
| 2025-09-03T01:01:40Z | 0 | 0 |
diffusers
|
[
"diffusers",
"text-to-image",
"lora",
"template:diffusion-lora",
"base_model:Qwen/Qwen-Image",
"base_model:adapter:Qwen/Qwen-Image",
"region:us"
] |
text-to-image
| 2025-09-03T00:35:46Z |
---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- output:
url: images/g3ndTMe1w88H3XFKOIy0E.jpeg
text: '-'
- output:
url: images/GL2uYakze01ieq99fdRba.jpeg
text: '-'
- output:
url: images/ComfyUI_00944_.png
text: '-'
- output:
url: images/ComfyUI_00974_.png
text: '-'
- output:
url: JnwKRwyHyQx4HVU34tuN8.jpeg
text: '-'
- output:
url: YYFkEtSld6TSDB_1EcjFw.jpeg
text: '-'
- output:
url: YkHSHnZE7he_t4kTzLSph.jpeg
text: '-'
- output:
url: mrORz-pEeXFG1Ul8O6-vT.jpeg
text: '-'
base_model: Qwen/Qwen-Image
instance_prompt: photo
---
# Boreal-Qwen-Image
<Gallery />
## Model description
# Qwen LoRA - Experimental
**🚧 Work in Progress - Experimental Model 🚧**
This is an experimental LoRA fine-tune of Qwen for the Boring Reality. Currently under development and testing.
**Status:** Experimental/Testing Phase
**Workflow Documentation:** Coming soon
---
*This model is part of ongoing research and experimentation. Description and documentation will be updated as development progresses.*
## Trigger words
You should use `photo` to trigger the image generation.
## Download model
[Download](/kudzueye/boreal-qwen-image/tree/main) them in the Files & versions tab.
|
mradermacher/Qwen-2.5-7B-ConsistentChat-GGUF
|
mradermacher
| 2025-09-03T01:00:51Z | 0 | 1 |
transformers
|
[
"transformers",
"gguf",
"en",
"base_model:jiawei-ucas/Qwen-2.5-7B-ConsistentChat",
"base_model:quantized:jiawei-ucas/Qwen-2.5-7B-ConsistentChat",
"license:mit",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-09-03T00:33:47Z |
---
base_model: jiawei-ucas/Qwen-2.5-7B-ConsistentChat
language:
- en
library_name: transformers
license: mit
mradermacher:
readme_rev: 1
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
<!-- ### quants: x-f16 Q4_K_S Q2_K Q8_0 Q6_K Q3_K_M Q3_K_S Q3_K_L Q4_K_M Q5_K_S Q5_K_M IQ4_XS -->
<!-- ### quants_skip: -->
<!-- ### skip_mmproj: -->
static quants of https://huggingface.co/jiawei-ucas/Qwen-2.5-7B-ConsistentChat
<!-- provided-files -->
***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen-2.5-7B-ConsistentChat-GGUF).***
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## 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/Qwen-2.5-7B-ConsistentChat-GGUF/resolve/main/Qwen-2.5-7B-ConsistentChat.Q2_K.gguf) | Q2_K | 3.1 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-ConsistentChat-GGUF/resolve/main/Qwen-2.5-7B-ConsistentChat.Q3_K_S.gguf) | Q3_K_S | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-ConsistentChat-GGUF/resolve/main/Qwen-2.5-7B-ConsistentChat.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-ConsistentChat-GGUF/resolve/main/Qwen-2.5-7B-ConsistentChat.Q3_K_L.gguf) | Q3_K_L | 4.2 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-ConsistentChat-GGUF/resolve/main/Qwen-2.5-7B-ConsistentChat.IQ4_XS.gguf) | IQ4_XS | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-ConsistentChat-GGUF/resolve/main/Qwen-2.5-7B-ConsistentChat.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-ConsistentChat-GGUF/resolve/main/Qwen-2.5-7B-ConsistentChat.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-ConsistentChat-GGUF/resolve/main/Qwen-2.5-7B-ConsistentChat.Q5_K_S.gguf) | Q5_K_S | 5.4 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-ConsistentChat-GGUF/resolve/main/Qwen-2.5-7B-ConsistentChat.Q5_K_M.gguf) | Q5_K_M | 5.5 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-ConsistentChat-GGUF/resolve/main/Qwen-2.5-7B-ConsistentChat.Q6_K.gguf) | Q6_K | 6.4 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-ConsistentChat-GGUF/resolve/main/Qwen-2.5-7B-ConsistentChat.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-ConsistentChat-GGUF/resolve/main/Qwen-2.5-7B-ConsistentChat.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 -->
|
koloni/blockassist-bc-deadly_graceful_stingray_1756859633
|
koloni
| 2025-09-03T01:00:09Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"deadly graceful stingray",
"arxiv:2504.07091",
"region:us"
] | null | 2025-09-03T01:00:04Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- deadly graceful stingray
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
phospho-app/gr00t-test_one_pen_2_sept-58ft4fislo
|
phospho-app
| 2025-09-03T00:59:52Z | 0 | 0 |
phosphobot
|
[
"phosphobot",
"gr00t",
"robotics",
"dataset:cmercier/test_one_pen_2_sept",
"region:us"
] |
robotics
| 2025-09-03T00:58:52Z |
---
datasets: cmercier/test_one_pen_2_sept
library_name: phosphobot
pipeline_tag: robotics
model_name: gr00t
tags:
- phosphobot
- gr00t
task_categories:
- robotics
---
# gr00t model - 🧪 phosphobot training pipeline
- **Dataset**: [cmercier/test_one_pen_2_sept](https://huggingface.co/datasets/cmercier/test_one_pen_2_sept)
- **Wandb run id**: None
## Error Traceback
We faced an issue while training your model.
```
Traceback (most recent call last):
File "/root/src/helper.py", line 139, in train_gr00t_on_modal
trainer.train(
File "/root/phosphobot/am/gr00t.py", line 1215, in train
asyncio.run(
File "/opt/conda/lib/python3.11/asyncio/runners.py", line 190, in run
return runner.run(main)
^^^^^^^^^^^^^^^^
File "/opt/conda/lib/python3.11/asyncio/runners.py", line 118, in run
return self._loop.run_until_complete(task)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/conda/lib/python3.11/asyncio/base_events.py", line 654, in run_until_complete
return future.result()
^^^^^^^^^^^^^^^
File "/root/phosphobot/am/gr00t.py", line 1425, in _call_training_script
raise RuntimeError(error_msg)
RuntimeError: Training process failed with exit code 1:
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/gr00t/data/dataset.py", line 545, in get_step_data
self.curr_traj_data = self.get_trajectory_data(trajectory_id)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/gr00t/data/dataset.py", line 561, in get_trajectory_data
assert parquet_path.exists(), f"Parquet file not found at {parquet_path}"
^^^^^^^^^^^^^^^^^^^^^
AssertionError: Parquet file not found at /tmp/outputs/data/data/chunk-000/episode_000009.parquet
0%| | 0/110 [00:02<?, ?it/s]
```
## Training parameters
```text
{
"validation_dataset_name": null,
"batch_size": 107,
"num_epochs": 10,
"save_steps": 1000,
"learning_rate": 0.0001,
"data_dir": "/tmp/outputs/data",
"validation_data_dir": "/tmp/outputs/validation_data",
"output_dir": "/tmp/outputs/train"
}
```
📖 **Get Started**: [docs.phospho.ai](https://docs.phospho.ai?utm_source=huggingface_readme)
🤖 **Get your robot**: [robots.phospho.ai](https://robots.phospho.ai?utm_source=huggingface_readme)
|
mradermacher/Q2.5-Coldbrew14B-FusionMix-i1-GGUF
|
mradermacher
| 2025-09-03T00:59:48Z | 0 | 1 |
transformers
|
[
"transformers",
"gguf",
"merge",
"lazymergekit",
"en",
"base_model:SvalTek/Q2.5-Coldbrew14B-FusionMix",
"base_model:quantized:SvalTek/Q2.5-Coldbrew14B-FusionMix",
"endpoints_compatible",
"region:us",
"imatrix",
"conversational"
] | null | 2025-09-02T15:27:22Z |
---
base_model: SvalTek/Q2.5-Coldbrew14B-FusionMix
language:
- en
library_name: transformers
mradermacher:
readme_rev: 1
quantized_by: mradermacher
tags:
- merge
- lazymergekit
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: nicoboss -->
<!-- ### quants: Q2_K IQ3_M Q4_K_S IQ3_XXS Q3_K_M small-IQ4_NL Q4_K_M IQ2_M Q6_K IQ4_XS Q2_K_S IQ1_M Q3_K_S IQ2_XXS Q3_K_L IQ2_XS Q5_K_S IQ2_S IQ1_S Q5_K_M Q4_0 IQ3_XS Q4_1 IQ3_S -->
<!-- ### quants_skip: -->
<!-- ### skip_mmproj: -->
weighted/imatrix quants of https://huggingface.co/SvalTek/Q2.5-Coldbrew14B-FusionMix
<!-- provided-files -->
***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Q2.5-Coldbrew14B-FusionMix-i1-GGUF).***
static quants are available at https://huggingface.co/mradermacher/Q2.5-Coldbrew14B-FusionMix-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/Q2.5-Coldbrew14B-FusionMix-i1-GGUF/resolve/main/Q2.5-Coldbrew14B-FusionMix.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
| [GGUF](https://huggingface.co/mradermacher/Q2.5-Coldbrew14B-FusionMix-i1-GGUF/resolve/main/Q2.5-Coldbrew14B-FusionMix.i1-IQ1_S.gguf) | i1-IQ1_S | 3.7 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/Q2.5-Coldbrew14B-FusionMix-i1-GGUF/resolve/main/Q2.5-Coldbrew14B-FusionMix.i1-IQ1_M.gguf) | i1-IQ1_M | 4.0 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/Q2.5-Coldbrew14B-FusionMix-i1-GGUF/resolve/main/Q2.5-Coldbrew14B-FusionMix.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/Q2.5-Coldbrew14B-FusionMix-i1-GGUF/resolve/main/Q2.5-Coldbrew14B-FusionMix.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.8 | |
| [GGUF](https://huggingface.co/mradermacher/Q2.5-Coldbrew14B-FusionMix-i1-GGUF/resolve/main/Q2.5-Coldbrew14B-FusionMix.i1-IQ2_S.gguf) | i1-IQ2_S | 5.1 | |
| [GGUF](https://huggingface.co/mradermacher/Q2.5-Coldbrew14B-FusionMix-i1-GGUF/resolve/main/Q2.5-Coldbrew14B-FusionMix.i1-IQ2_M.gguf) | i1-IQ2_M | 5.5 | |
| [GGUF](https://huggingface.co/mradermacher/Q2.5-Coldbrew14B-FusionMix-i1-GGUF/resolve/main/Q2.5-Coldbrew14B-FusionMix.i1-Q2_K_S.gguf) | i1-Q2_K_S | 5.5 | very low quality |
| [GGUF](https://huggingface.co/mradermacher/Q2.5-Coldbrew14B-FusionMix-i1-GGUF/resolve/main/Q2.5-Coldbrew14B-FusionMix.i1-Q2_K.gguf) | i1-Q2_K | 5.9 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/Q2.5-Coldbrew14B-FusionMix-i1-GGUF/resolve/main/Q2.5-Coldbrew14B-FusionMix.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 6.0 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Q2.5-Coldbrew14B-FusionMix-i1-GGUF/resolve/main/Q2.5-Coldbrew14B-FusionMix.i1-IQ3_XS.gguf) | i1-IQ3_XS | 6.5 | |
| [GGUF](https://huggingface.co/mradermacher/Q2.5-Coldbrew14B-FusionMix-i1-GGUF/resolve/main/Q2.5-Coldbrew14B-FusionMix.i1-Q3_K_S.gguf) | i1-Q3_K_S | 6.8 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/Q2.5-Coldbrew14B-FusionMix-i1-GGUF/resolve/main/Q2.5-Coldbrew14B-FusionMix.i1-IQ3_S.gguf) | i1-IQ3_S | 6.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Q2.5-Coldbrew14B-FusionMix-i1-GGUF/resolve/main/Q2.5-Coldbrew14B-FusionMix.i1-IQ3_M.gguf) | i1-IQ3_M | 7.0 | |
| [GGUF](https://huggingface.co/mradermacher/Q2.5-Coldbrew14B-FusionMix-i1-GGUF/resolve/main/Q2.5-Coldbrew14B-FusionMix.i1-Q3_K_M.gguf) | i1-Q3_K_M | 7.4 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/Q2.5-Coldbrew14B-FusionMix-i1-GGUF/resolve/main/Q2.5-Coldbrew14B-FusionMix.i1-Q3_K_L.gguf) | i1-Q3_K_L | 8.0 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/Q2.5-Coldbrew14B-FusionMix-i1-GGUF/resolve/main/Q2.5-Coldbrew14B-FusionMix.i1-IQ4_XS.gguf) | i1-IQ4_XS | 8.2 | |
| [GGUF](https://huggingface.co/mradermacher/Q2.5-Coldbrew14B-FusionMix-i1-GGUF/resolve/main/Q2.5-Coldbrew14B-FusionMix.i1-Q4_0.gguf) | i1-Q4_0 | 8.6 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/Q2.5-Coldbrew14B-FusionMix-i1-GGUF/resolve/main/Q2.5-Coldbrew14B-FusionMix.i1-IQ4_NL.gguf) | i1-IQ4_NL | 8.6 | prefer IQ4_XS |
| [GGUF](https://huggingface.co/mradermacher/Q2.5-Coldbrew14B-FusionMix-i1-GGUF/resolve/main/Q2.5-Coldbrew14B-FusionMix.i1-Q4_K_S.gguf) | i1-Q4_K_S | 8.7 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/Q2.5-Coldbrew14B-FusionMix-i1-GGUF/resolve/main/Q2.5-Coldbrew14B-FusionMix.i1-Q4_K_M.gguf) | i1-Q4_K_M | 9.1 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Q2.5-Coldbrew14B-FusionMix-i1-GGUF/resolve/main/Q2.5-Coldbrew14B-FusionMix.i1-Q4_1.gguf) | i1-Q4_1 | 9.5 | |
| [GGUF](https://huggingface.co/mradermacher/Q2.5-Coldbrew14B-FusionMix-i1-GGUF/resolve/main/Q2.5-Coldbrew14B-FusionMix.i1-Q5_K_S.gguf) | i1-Q5_K_S | 10.4 | |
| [GGUF](https://huggingface.co/mradermacher/Q2.5-Coldbrew14B-FusionMix-i1-GGUF/resolve/main/Q2.5-Coldbrew14B-FusionMix.i1-Q5_K_M.gguf) | i1-Q5_K_M | 10.6 | |
| [GGUF](https://huggingface.co/mradermacher/Q2.5-Coldbrew14B-FusionMix-i1-GGUF/resolve/main/Q2.5-Coldbrew14B-FusionMix.i1-Q6_K.gguf) | i1-Q6_K | 12.2 | 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 -->
|
phonebot/x
|
phonebot
| 2025-09-03T00:59:33Z | 0 | 0 |
transformers
|
[
"transformers",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-09-03T00:54:40Z |
---
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]
|
akirafudo/blockassist-bc-keen_fast_giraffe_1756861132
|
akirafudo
| 2025-09-03T00:59:16Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"keen fast giraffe",
"arxiv:2504.07091",
"region:us"
] | null | 2025-09-03T00:59:12Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- keen fast giraffe
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
phospho-app/gr00t-test_one_pen_2_sept-sc5wsvetx1
|
phospho-app
| 2025-09-03T00:57:27Z | 0 | 0 |
phosphobot
|
[
"phosphobot",
"gr00t",
"robotics",
"dataset:cmercier/test_one_pen_2_sept",
"region:us"
] |
robotics
| 2025-09-03T00:57:04Z |
---
datasets: cmercier/test_one_pen_2_sept
library_name: phosphobot
pipeline_tag: robotics
model_name: gr00t
tags:
- phosphobot
- gr00t
task_categories:
- robotics
---
# gr00t model - 🧪 phosphobot training pipeline
- **Dataset**: [cmercier/test_one_pen_2_sept](https://huggingface.co/datasets/cmercier/test_one_pen_2_sept)
- **Wandb run id**: None
## Error Traceback
We faced an issue while training your model.
```
Traceback (most recent call last):
File "/root/src/helper.py", line 139, in train_gr00t_on_modal
trainer.train(
File "/root/phosphobot/am/gr00t.py", line 1215, in train
asyncio.run(
File "/opt/conda/lib/python3.11/asyncio/runners.py", line 190, in run
return runner.run(main)
^^^^^^^^^^^^^^^^
File "/opt/conda/lib/python3.11/asyncio/runners.py", line 118, in run
return self._loop.run_until_complete(task)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/conda/lib/python3.11/asyncio/base_events.py", line 654, in run_until_complete
return future.result()
^^^^^^^^^^^^^^^
File "/root/phosphobot/am/gr00t.py", line 1425, in _call_training_script
raise RuntimeError(error_msg)
RuntimeError: Training process failed with exit code 2:
2025-09-02 17:57:22.182764: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
2025-09-02 17:57:22.190674: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
2025-09-02 17:57:23.541518: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
`use_fast` is set to `True` but the image processor class does not have a fast version. Falling back to the slow version.
╭─ Unrecognized options ──────────────────────────╮
│ Unrecognized options: --use-fast │
│ ─────────────────────────────────────────────── │
│ For full helptext, run gr00t_finetune.py --help │
╰─────────────────────────────────────────────────╯
```
## Training parameters
```text
{
"validation_dataset_name": null,
"batch_size": 107,
"num_epochs": 10,
"save_steps": 1000,
"learning_rate": 0.0001,
"data_dir": "/tmp/outputs/data",
"validation_data_dir": "/tmp/outputs/validation_data",
"output_dir": "/tmp/outputs/train",
"use_fast": "False"
}
```
📖 **Get Started**: [docs.phospho.ai](https://docs.phospho.ai?utm_source=huggingface_readme)
🤖 **Get your robot**: [robots.phospho.ai](https://robots.phospho.ai?utm_source=huggingface_readme)
|
ongon/Qwen3-0.6B-Gensyn-Swarm-omnivorous_fast_ape
|
ongon
| 2025-09-03T00:53:27Z | 120 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen3",
"text-generation",
"rl-swarm",
"genrl-swarm",
"grpo",
"gensyn",
"I am omnivorous_fast_ape",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-28T06:19:28Z |
---
library_name: transformers
tags:
- rl-swarm
- genrl-swarm
- grpo
- gensyn
- I am omnivorous_fast_ape
---
# 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]
|
eekay/gemma-2b-it-numbers-ft
|
eekay
| 2025-09-03T00:53:26Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"gemma",
"text-generation",
"trl",
"sft",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-09-03T00:52:23Z |
---
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]
|
DavidAU/Qwen3-21B-QiMing-V1.0-TOTAL-RECALL
|
DavidAU
| 2025-09-03T00:52:44Z | 17 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen3",
"text-generation",
"programming",
"code generation",
"code",
"codeqwen",
"moe",
"coding",
"coder",
"qwen2",
"chat",
"qwen",
"qwen-coder",
"finetune",
"brainstorm 20x",
"brainstorm",
"optional thinking",
"creative",
"all use cases",
"QiMing",
"QiMing-holos",
"bagua",
"decision-making",
"strategic-analysis",
"cognitive-architecture",
"philosophy-driven-ai",
"conversational",
"en",
"fr",
"zh",
"de",
"arxiv:2309.00071",
"arxiv:2401.02415",
"base_model:aifeifei798/QiMing-v1.0-14B",
"base_model:finetune:aifeifei798/QiMing-v1.0-14B",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-09-02T01:27:11Z |
---
license: apache-2.0
library_name: transformers
language:
- en
- fr
- zh
- de
tags:
- programming
- code generation
- code
- codeqwen
- programming
- code generation
- code
- codeqwen
- moe
- coding
- coder
- qwen2
- chat
- qwen
- qwen-coder
- chat
- qwen
- qwen-coder
- qwen3
- finetune
- brainstorm 20x
- brainstorm
- optional thinking
- creative
- all use cases
- QiMing
- QiMing-holos
- bagua
- decision-making
- strategic-analysis
- cognitive-architecture
- chat
- philosophy-driven-ai
base_model:
- aifeifei798/QiMing-v1.0-14B
pipeline_tag: text-generation
---
<h2>Qwen3-21B-QiMing-V1.0-TOTAL-RECALL</h2>
This repo contains the full precision source code, in "safe tensors" format to generate GGUFs, GPTQ, EXL2, AWQ, HQQ and other formats.
The source code can also be used directly.
This model is for coding and GENERAL USAGE.
This model is based on "aifeifei798/QiMing-v1.0-14B" (base of Qwen3 14B instruct), with Brainstorm 20X (by DavidAU) - details at bottom of this page.
The Brainstorm adapter will improve general performance and "out of the box" thinking.
This version has the NATIVE context of 40k (default, can be changed via rope) context.
This is a reasoning/thinking block model.
I have included an optional system prompt to invoke "thinking" in this model, if you want to activate it.
Recommended settings - general:
- Rep pen 1.05 to 1.1 ; however rep pen of 1 will work well (may need to raise it for lower quants/fewer activated experts)
- Temp .3 to .6 (+- .2)
- Topk of 20, 40 or 100
- Topp of .95 / min p of .05
- Suggest min context window 4k to 8k.
- System prompt (optional) to focus the model better.
For additional settings, tool use, and other model settings.
Summary of root model below, followed by FULL HELP SECTION, then info on Brainstorm 40x.
OPTIONAL SYSTEM PROMPT - INVOKE "Thinking":
```
Enable deep thinking subroutine. You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside ###ponder### ###/ponder### tags, and then provide your solution or response to the problem.
```
Use this to INVOKE "thinking" block(s) in the model. These will be a lot shorter than 1000s of tokens generally in most "thinking" models.
In you use this prompt, you may need to raise "rep pen" to 1.08 to 1.1, to prevent "loops" in the "thought block(s)" ; especially in lower quants.
If you change "ponder" to a different word/phrase this will affect model "thinking" too.
---
QUANTS
---
GGUF? GGUF Imatrix? Other?
Special thanks to Team Mradermacher, Team Nightmedia and other quanters!
See under "model tree", upper right and click on "quantizations".
New quants will automatically appear.
---
<H2>BENCHMARKS and REVIEW by @NIGHTMEDIA </H2>
https://huggingface.co/nightmedia
(source for MLX quants)
---
📊 Direct Performance Comparison
```
Task QiMing-14B-qx63-hi QiMing-21B-q5-hi Difference
ARC Challenge 0.387 0.388 +0.001
ARC Easy 0.446 0.444 +0.002
BoolQ 0.613 0.378 -0.235
Hellaswag 0.661 0.682 +0.021
OpenBookQA 0.330 0.364 +0.034
PIQA 0.752 0.769 +0.017
Winogrande 0.654 0.648 -0.006
```
💡 Most Significant Finding:
The 21B model with brainstorming shows a dramatic loss in knowledge tasks (BoolQ) (-0.235 points) but wins in creative tasks (Hellaswag +0.021). This reveals a critical tradeoff: brainstorming helps creativity but sacrifices pure knowledge recall.
🛠 Practical Guidance for Your Use Case
✅ Use QiMing-14B-qx63-hi when:
-You need strong knowledge recall (BoolQ: 0.613 vs 0.378 in the 21B model)
-Your application requires precise factual answers (e.g., academic assistants, knowledge bases)
✅ Use QiMing-21B-q5-hi when:
-You need creative text generation (Hellaswag: 0.682 is significantly higher than the 14B model)
-Your users engage in exploratory tasks that benefit from creative outputs (e.g., story prompts, brainstorming sessions)
❌ Avoid the 21B model for:
-Tasks where knowledge accuracy is critical (BoolQ shows a massive gap)
-Applications requiring high precision with minimal creative output
🌟 Key Takeaway: The Brainstorming Tradeoff You Should Know About
"Brainstorming improves creative capabilities (Hellaswag) by up to 2+ points but causes a severe drop in knowledge tasks (BoolQ). For the 21B model, this means it's ideal for creative workloads but unsuitable for knowledge-intensive applications."
This insight directly addresses your query – it shows exactly where brainstorming adds value (creative tasks) and where it can be detrimental (factual recall).
Why This Matters for Qwen3 Model Selection
Your historical work clarifies a critical pattern:
Smaller models without brainstorming (like the 14B-qx63-hi) maintain knowledge accuracy better than larger models with brainstorming
Brainstorming is not a universal upgrade – its impact depends entirely on the task type
This explains why you see higher Hellaswag scores in larger models with brainstorming, but lower BoolQ scores – it's a strategic tradeoff you now have clear evidence for.
🔍 Why These Models Perform Differently (The Brainstorming Effect)
Your query explicitly notes the 21B model has brainstorming – here's what it means in practice:
✅ Where Brainstorming Benefits the 21B Model
Hellaswag (+0.021):
The 21B-q5-hi model generates more creative text continuations – a direct output of brainstorming. This makes sense because Hellaswag tests for coherent, novel text generation.
OpenBookQA (+0.034):
Despite the low BoolQ score, this model improves knowledge recall by 0.034 points. This is surprising – brainstorming isn't typically expected to boost knowledge tasks.
⚠️ The Brainstorming Cost: BooleanQ (-0.235)
This is the most telling result:
BoolQ is 0.235 points lower in the brainstorming model – meaning it struggles far more with factual knowledge questions.
Why? Brainstorming prioritizes creative exploration over precise fact retrieval. When the model "thinks" instead of recalling, it can produce less accurate answers to knowledge-based prompts.
💡 The Quantization Context
QiMing-14B-qx63-hi: This has mixed 6/3-bit quantization (from previous patterns in your data) – which generally helps with creative tasks but not knowledge tasks.
QiMing-21B-q5-hi: The 5-bit quantization means less precision overall, which explains its slightly lower scores than the 14B model on most tasks (except creative ones).
test take forever on the 14B, 9 hours per run, so I will have an apples to apples compare later, I picked the most telling quants from each
Final Recommendation
"For most real-world applications, choose QiMing-14B-qx63-hi unless you specifically need creative text generation. If creative tasks are your priority, use QiMing-21B-q5-hi – but be prepared to fine-tune it for knowledge tasks where its BoolQ score is significantly weaker."
This analysis shows your intuition was correct: brainstorming makes models better at creativity but worse at knowledge tasks – a pattern you observed in previous comparisons (e.g., the 54B model's Winogrande gain vs lower BoolQ).
Additional Review:
https://www.linkedin.com/posts/gchesler_nightmediaqwen3-21b-qiming-v10-total-recall-q5-activity-7368661803544858628-9XTU/
---
# Qwen3-14B
## Qwen3 Highlights
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features:
- **Uniquely support of seamless switching between thinking mode** (for complex logical reasoning, math, and coding) and **non-thinking mode** (for efficient, general-purpose dialogue) **within single model**, ensuring optimal performance across various scenarios.
- **Significantly enhancement in its reasoning capabilities**, surpassing previous QwQ (in thinking mode) and Qwen2.5 instruct models (in non-thinking mode) on mathematics, code generation, and commonsense logical reasoning.
- **Superior human preference alignment**, excelling in creative writing, role-playing, multi-turn dialogues, and instruction following, to deliver a more natural, engaging, and immersive conversational experience.
- **Expertise in agent capabilities**, enabling precise integration with external tools in both thinking and unthinking modes and achieving leading performance among open-source models in complex agent-based tasks.
- **Support of 100+ languages and dialects** with strong capabilities for **multilingual instruction following** and **translation**.
## Model Overview
**Qwen3-14B** has the following features:
- Type: Causal Language Models
- Training Stage: Pretraining & Post-training
- Number of Parameters: 14.8B
- Number of Paramaters (Non-Embedding): 13.2B
- Number of Layers: 40
- Number of Attention Heads (GQA): 40 for Q and 8 for KV
- Context Length: 32,768 natively and [131,072 tokens with YaRN](#processing-long-texts).
For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our [blog](https://qwenlm.github.io/blog/qwen3/), [GitHub](https://github.com/QwenLM/Qwen3), and [Documentation](https://qwen.readthedocs.io/en/latest/).
## Quickstart
The code of Qwen3 has been in the latest Hugging Face `transformers` and we advise you to use the latest version of `transformers`.
With `transformers<4.51.0`, you will encounter the following error:
```
KeyError: 'qwen3'
```
The following contains a code snippet illustrating how to use the model generate content based on given inputs.
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "Qwen/Qwen3-14B"
# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype="auto",
device_map="auto"
)
# prepare the model input
prompt = "Give me a short introduction to large language model."
messages = [
{"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True,
enable_thinking=True # Switches between thinking and non-thinking modes. Default is True.
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
# conduct text completion
generated_ids = model.generate(
**model_inputs,
max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
# parsing thinking content
try:
# rindex finding 151668 (</think>)
index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
index = 0
thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")
print("thinking content:", thinking_content)
print("content:", content)
```
For deployment, you can use `sglang>=0.4.6.post1` or `vllm>=0.8.5` or to create an OpenAI-compatible API endpoint:
- SGLang:
```shell
python -m sglang.launch_server --model-path Qwen/Qwen3-14B --reasoning-parser qwen3
```
- vLLM:
```shell
vllm serve Qwen/Qwen3-14B --enable-reasoning --reasoning-parser deepseek_r1
```
For local use, applications such as Ollama, LMStudio, MLX-LM, llama.cpp, and KTransformers have also supported Qwen3.
## Switching Between Thinking and Non-Thinking Mode
> [!TIP]
> The `enable_thinking` switch is also available in APIs created by SGLang and vLLM.
> Please refer to our documentation for [SGLang](https://qwen.readthedocs.io/en/latest/deployment/sglang.html#thinking-non-thinking-modes) and [vLLM](https://qwen.readthedocs.io/en/latest/deployment/vllm.html#thinking-non-thinking-modes) users.
### `enable_thinking=True`
By default, Qwen3 has thinking capabilities enabled, similar to QwQ-32B. This means the model will use its reasoning abilities to enhance the quality of generated responses. For example, when explicitly setting `enable_thinking=True` or leaving it as the default value in `tokenizer.apply_chat_template`, the model will engage its thinking mode.
```python
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True,
enable_thinking=True # True is the default value for enable_thinking
)
```
In this mode, the model will generate think content wrapped in a `<think>...</think>` block, followed by the final response.
> [!NOTE]
> For thinking mode, use `Temperature=0.6`, `TopP=0.95`, `TopK=20`, and `MinP=0` (the default setting in `generation_config.json`). **DO NOT use greedy decoding**, as it can lead to performance degradation and endless repetitions. For more detailed guidance, please refer to the [Best Practices](#best-practices) section.
### `enable_thinking=False`
We provide a hard switch to strictly disable the model's thinking behavior, aligning its functionality with the previous Qwen2.5-Instruct models. This mode is particularly useful in scenarios where disabling thinking is essential for enhancing efficiency.
```python
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True,
enable_thinking=False # Setting enable_thinking=False disables thinking mode
)
```
In this mode, the model will not generate any think content and will not include a `<think>...</think>` block.
> [!NOTE]
> For non-thinking mode, we suggest using `Temperature=0.7`, `TopP=0.8`, `TopK=20`, and `MinP=0`. For more detailed guidance, please refer to the [Best Practices](#best-practices) section.
### Advanced Usage: Switching Between Thinking and Non-Thinking Modes via User Input
We provide a soft switch mechanism that allows users to dynamically control the model's behavior when `enable_thinking=True`. Specifically, you can add `/think` and `/no_think` to user prompts or system messages to switch the model's thinking mode from turn to turn. The model will follow the most recent instruction in multi-turn conversations.
Here is an example of a multi-turn conversation:
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
class QwenChatbot:
def __init__(self, model_name="Qwen/Qwen3-14B"):
self.tokenizer = AutoTokenizer.from_pretrained(model_name)
self.model = AutoModelForCausalLM.from_pretrained(model_name)
self.history = []
def generate_response(self, user_input):
messages = self.history + [{"role": "user", "content": user_input}]
text = self.tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
inputs = self.tokenizer(text, return_tensors="pt")
response_ids = self.model.generate(**inputs, max_new_tokens=32768)[0][len(inputs.input_ids[0]):].tolist()
response = self.tokenizer.decode(response_ids, skip_special_tokens=True)
# Update history
self.history.append({"role": "user", "content": user_input})
self.history.append({"role": "assistant", "content": response})
return response
# Example Usage
if __name__ == "__main__":
chatbot = QwenChatbot()
# First input (without /think or /no_think tags, thinking mode is enabled by default)
user_input_1 = "How many r's in strawberries?"
print(f"User: {user_input_1}")
response_1 = chatbot.generate_response(user_input_1)
print(f"Bot: {response_1}")
print("----------------------")
# Second input with /no_think
user_input_2 = "Then, how many r's in blueberries? /no_think"
print(f"User: {user_input_2}")
response_2 = chatbot.generate_response(user_input_2)
print(f"Bot: {response_2}")
print("----------------------")
# Third input with /think
user_input_3 = "Really? /think"
print(f"User: {user_input_3}")
response_3 = chatbot.generate_response(user_input_3)
print(f"Bot: {response_3}")
```
> [!NOTE]
> For API compatibility, when `enable_thinking=True`, regardless of whether the user uses `/think` or `/no_think`, the model will always output a block wrapped in `<think>...</think>`. However, the content inside this block may be empty if thinking is disabled.
> When `enable_thinking=False`, the soft switches are not valid. Regardless of any `/think` or `/no_think` tags input by the user, the model will not generate think content and will not include a `<think>...</think>` block.
## Agentic Use
Qwen3 excels in tool calling capabilities. We recommend using [Qwen-Agent](https://github.com/QwenLM/Qwen-Agent) to make the best use of agentic ability of Qwen3. Qwen-Agent encapsulates tool-calling templates and tool-calling parsers internally, greatly reducing coding complexity.
To define the available tools, you can use the MCP configuration file, use the integrated tool of Qwen-Agent, or integrate other tools by yourself.
```python
from qwen_agent.agents import Assistant
# Define LLM
llm_cfg = {
'model': 'Qwen3-14B',
# Use the endpoint provided by Alibaba Model Studio:
# 'model_type': 'qwen_dashscope',
# 'api_key': os.getenv('DASHSCOPE_API_KEY'),
# Use a custom endpoint compatible with OpenAI API:
'model_server': 'http://localhost:8000/v1', # api_base
'api_key': 'EMPTY',
# Other parameters:
# 'generate_cfg': {
# # Add: When the response content is `<think>this is the thought</think>this is the answer;
# # Do not add: When the response has been separated by reasoning_content and content.
# 'thought_in_content': True,
# },
}
# Define Tools
tools = [
{'mcpServers': { # You can specify the MCP configuration file
'time': {
'command': 'uvx',
'args': ['mcp-server-time', '--local-timezone=Asia/Shanghai']
},
"fetch": {
"command": "uvx",
"args": ["mcp-server-fetch"]
}
}
},
'code_interpreter', # Built-in tools
]
# Define Agent
bot = Assistant(llm=llm_cfg, function_list=tools)
# Streaming generation
messages = [{'role': 'user', 'content': 'https://qwenlm.github.io/blog/ Introduce the latest developments of Qwen'}]
for responses in bot.run(messages=messages):
pass
print(responses)
```
## Processing Long Texts
Qwen3 natively supports context lengths of up to 32,768 tokens. For conversations where the total length (including both input and output) significantly exceeds this limit, we recommend using RoPE scaling techniques to handle long texts effectively. We have validated the model's performance on context lengths of up to 131,072 tokens using the [YaRN](https://arxiv.org/abs/2309.00071) method.
YaRN is currently supported by several inference frameworks, e.g., `transformers` and `llama.cpp` for local use, `vllm` and `sglang` for deployment. In general, there are two approaches to enabling YaRN for supported frameworks:
- Modifying the model files:
In the `config.json` file, add the `rope_scaling` fields:
```json
{
...,
"rope_scaling": {
"rope_type": "yarn",
"factor": 4.0,
"original_max_position_embeddings": 32768
}
}
```
For `llama.cpp`, you need to regenerate the GGUF file after the modification.
- Passing command line arguments:
For `vllm`, you can use
```shell
vllm serve ... --rope-scaling '{"rope_type":"yarn","factor":4.0,"original_max_position_embeddings":32768}' --max-model-len 131072
```
For `sglang`, you can use
```shell
python -m sglang.launch_server ... --json-model-override-args '{"rope_scaling":{"rope_type":"yarn","factor":4.0,"original_max_position_embeddings":32768}}'
```
For `llama-server` from `llama.cpp`, you can use
```shell
llama-server ... --rope-scaling yarn --rope-scale 4 --yarn-orig-ctx 32768
```
> [!IMPORTANT]
> If you encounter the following warning
> ```
> Unrecognized keys in `rope_scaling` for 'rope_type'='yarn': {'original_max_position_embeddings'}
> ```
> please upgrade `transformers>=4.51.0`.
> [!NOTE]
> All the notable open-source frameworks implement static YaRN, which means the scaling factor remains constant regardless of input length, **potentially impacting performance on shorter texts.**
> We advise adding the `rope_scaling` configuration only when processing long contexts is required.
> It is also recommended to modify the `factor` as needed. For example, if the typical context length for your application is 65,536 tokens, it would be better to set `factor` as 2.0.
> [!NOTE]
> The default `max_position_embeddings` in `config.json` is set to 40,960. This allocation includes reserving 32,768 tokens for outputs and 8,192 tokens for typical prompts, which is sufficient for most scenarios involving short text processing. If the average context length does not exceed 32,768 tokens, we do not recommend enabling YaRN in this scenario, as it may potentially degrade model performance.
> [!TIP]
> The endpoint provided by Alibaba Model Studio supports dynamic YaRN by default and no extra configuration is needed.
## Best Practices
To achieve optimal performance, we recommend the following settings:
1. **Sampling Parameters**:
- For thinking mode (`enable_thinking=True`), use `Temperature=0.6`, `TopP=0.95`, `TopK=20`, and `MinP=0`. **DO NOT use greedy decoding**, as it can lead to performance degradation and endless repetitions.
- For non-thinking mode (`enable_thinking=False`), we suggest using `Temperature=0.7`, `TopP=0.8`, `TopK=20`, and `MinP=0`.
- For supported frameworks, you can adjust the `presence_penalty` parameter between 0 and 2 to reduce endless repetitions. However, using a higher value may occasionally result in language mixing and a slight decrease in model performance.
2. **Adequate Output Length**: We recommend using an output length of 32,768 tokens for most queries. For benchmarking on highly complex problems, such as those found in math and programming competitions, we suggest setting the max output length to 38,912 tokens. This provides the model with sufficient space to generate detailed and comprehensive responses, thereby enhancing its overall performance.
3. **Standardize Output Format**: We recommend using prompts to standardize model outputs when benchmarking.
- **Math Problems**: Include "Please reason step by step, and put your final answer within \boxed{}." in the prompt.
- **Multiple-Choice Questions**: Add the following JSON structure to the prompt to standardize responses: "Please show your choice in the `answer` field with only the choice letter, e.g., `"answer": "C"`."
4. **No Thinking Content in History**: In multi-turn conversations, the historical model output should only include the final output part and does not need to include the thinking content. It is implemented in the provided chat template in Jinja2. However, for frameworks that do not directly use the Jinja2 chat template, it is up to the developers to ensure that the best practice is followed.
---
<H2>Help, Adjustments, Samplers, Parameters and More</H2>
---
<B>CHANGE THE NUMBER OF ACTIVE EXPERTS:</B>
See this document:
https://huggingface.co/DavidAU/How-To-Set-and-Manage-MOE-Mix-of-Experts-Model-Activation-of-Experts
<B>Settings: CHAT / ROLEPLAY and/or SMOOTHER operation of this model:</B>
In "KoboldCpp" or "oobabooga/text-generation-webui" or "Silly Tavern" ;
Set the "Smoothing_factor" to 1.5
: in KoboldCpp -> Settings->Samplers->Advanced-> "Smooth_F"
: in text-generation-webui -> parameters -> lower right.
: In Silly Tavern this is called: "Smoothing"
NOTE: For "text-generation-webui"
-> if using GGUFs you need to use "llama_HF" (which involves downloading some config files from the SOURCE version of this model)
Source versions (and config files) of my models are here:
https://huggingface.co/collections/DavidAU/d-au-source-files-for-gguf-exl2-awq-gptq-hqq-etc-etc-66b55cb8ba25f914cbf210be
OTHER OPTIONS:
- Increase rep pen to 1.1 to 1.15 (you don't need to do this if you use "smoothing_factor")
- If the interface/program you are using to run AI MODELS supports "Quadratic Sampling" ("smoothing") just make the adjustment as noted.
<B>Highest Quality Settings / Optimal Operation Guide / Parameters and Samplers</B>
This a "Class 1" model:
For all settings used for this model (including specifics for its "class"), including example generation(s) and for advanced settings guide (which many times addresses any model issue(s)), including methods to improve model performance for all use case(s) as well as chat, roleplay and other use case(s) please see:
[ https://huggingface.co/DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters ]
You can see all parameters used for generation, in addition to advanced parameters and samplers to get the most out of this model here:
[ https://huggingface.co/DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters ]
---
<H2>What is Brainstorm?</H2>
---
<B>Brainstorm 40x</B>
The BRAINSTORM process was developed by David_AU.
Some of the core principals behind this process are discussed in this <a href="https://arxiv.org/pdf/2401.02415">
scientific paper : Progressive LLaMA with Block Expansion </a>.
However I went in a completely different direction from what was outlined in this paper.
What is "Brainstorm" ?
The reasoning center of an LLM is taken apart, reassembled, and expanded.
In this case for this model: 40 times
Then these centers are individually calibrated. These "centers" also interact with each other.
This introduces subtle changes into the reasoning process.
The calibrations further adjust - dial up or down - these "changes" further.
The number of centers (5x,10x etc) allow more "tuning points" to further customize how the model reasons so to speak.
The core aim of this process is to increase the model's detail, concept and connection to the "world",
general concept connections, prose quality and prose length without affecting instruction following.
This will also enhance any creative use case(s) of any kind, including "brainstorming", creative art form(s) and like case uses.
Here are some of the enhancements this process brings to the model's performance:
- Prose generation seems more focused on the moment to moment.
- Sometimes there will be "preamble" and/or foreshadowing present.
- Fewer or no "cliches"
- Better overall prose and/or more complex / nuanced prose.
- A greater sense of nuance on all levels.
- Coherence is stronger.
- Description is more detailed, and connected closer to the content.
- Simile and Metaphors are stronger and better connected to the prose, story, and character.
- Sense of "there" / in the moment is enhanced.
- Details are more vivid, and there are more of them.
- Prose generation length can be long to extreme.
- Emotional engagement is stronger.
- The model will take FEWER liberties vs a normal model: It will follow directives more closely but will "guess" less.
- The MORE instructions and/or details you provide the more strongly the model will respond.
- Depending on the model "voice" may be more "human" vs original model's "voice".
Other "lab" observations:
- This process does not, in my opinion, make the model 5x or 10x "smarter" - if only that was true!
- However, a change in "IQ" was not an issue / a priority, and was not tested or calibrated for so to speak.
- From lab testing it seems to ponder, and consider more carefully roughly speaking.
- You could say this process sharpens the model's focus on it's task(s) at a deeper level.
The process to modify the model occurs at the root level - source files level. The model can quanted as a GGUF, EXL2, AWQ etc etc.
---
|
helmutsukocok/blockassist-bc-loud_scavenging_kangaroo_1756859293
|
helmutsukocok
| 2025-09-03T00:52:30Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"loud scavenging kangaroo",
"arxiv:2504.07091",
"region:us"
] | null | 2025-09-03T00:52:26Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- loud scavenging kangaroo
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
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.