modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-07-15 06:27:42
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 521
values | tags
listlengths 1
4.05k
| pipeline_tag
stringclasses 55
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-07-15 06:27:26
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
jaen030/textual_inversion_teddy | jaen030 | 2025-05-27T06:11:05Z | 0 | 0 | diffusers | [
"diffusers",
"tensorboard",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"textual_inversion",
"diffusers-training",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:adapter:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
]
| text-to-image | 2025-05-25T20:00:39Z | ---
base_model: runwayml/stable-diffusion-v1-5
library_name: diffusers
license: creativeml-openrail-m
inference: true
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- textual_inversion
- diffusers-training
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- textual_inversion
- diffusers-training
---
<!-- This model card has been generated automatically according to the information the training script had access to. You
should probably proofread and complete it, then remove this comment. -->
# Textual inversion text2image fine-tuning - jaen030/textual_inversion_teddy
These are textual inversion adaption weights for runwayml/stable-diffusion-v1-5. You can find some example images in the following.
## Intended uses & limitations
#### How to use
```python
# TODO: add an example code snippet for running this diffusion pipeline
```
#### Limitations and bias
[TODO: provide examples of latent issues and potential remediations]
## Training details
[TODO: describe the data used to train the model] |
btly/kupl | btly | 2025-05-27T06:10:39Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"gemma3",
"image-text-to-text",
"gemma",
"google",
"Bifröst",
"Bifrost",
"code",
"text-generation",
"conversational",
"base_model:google/gemma-3-27b-it",
"base_model:finetune:google/gemma-3-27b-it",
"license:gemma",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-05-27T05:58:00Z | ---
license: gemma
library_name: transformers
pipeline_tag: text-generation
extra_gated_heading: Access Gemma on Hugging Face
extra_gated_prompt: >-
To access Gemma on Hugging Face, you’re required to review and agree to
Google’s usage license. To do this, please ensure you’re logged in to Hugging
Face and click below. Requests are processed immediately.
extra_gated_button_content: Acknowledge license
base_model: google/gemma-3-27b-it
tags:
- transformers
- gemma3
- gemma
- google
- Bifröst
- Bifrost
- code
---
## Bifröst-27B
Bifröst-27B is an advanced AI model built upon gemma3 architecture, specifically fine-tuned for secure and efficient enterprise-grade code generation with reasoning. Designed to meet rigorous standards of safety, accuracy, and reliability, Bifröst empowers organizations to streamline software development workflows while prioritizing security and compliance.
### Model Details
- **Model Name:** Bifröst-27B
- **Base Architecture:** gemma3
- **Application:** Enterprise Secure Code Generation
- **Release Date:** 16-March-2025
### Intended Use
Bifröst is designed explicitly for:
- Generating secure, efficient, and high-quality code.
- Supporting development tasks within regulated enterprise environments.
- Enhancing productivity by automating routine coding tasks without compromising security.
### Features
- **Security-Focused Training:** Specialized training regimen emphasizing secure coding practices, vulnerability reduction, and adherence to security standards.
- **Enterprise-Optimized Performance:** Tailored to support various programming languages and enterprise frameworks with robust, context-aware suggestions.
- **Compliance-Driven Design:** Incorporates features to aid in maintaining compliance with industry-specific standards (e.g., GDPR, HIPAA, SOC 2).
### Limitations
- Bifröst should be used under human supervision to ensure code correctness and security compliance.
- Model-generated code should undergo appropriate security and quality assurance checks before deployment.
### Ethical Considerations
- Users are encouraged to perform regular audits and compliance checks on generated outputs.
- Enterprises should implement responsible AI practices to mitigate biases or unintended consequences.
### Usage
Below are some quick-start instructions for using the model with the `transformers` library.
#### Installation
```sh
$ pip install git+https://github.com/huggingface/[email protected]
```
#### Running with the `pipeline` API
```python
from transformers import pipeline
import torch
pipe = pipeline(
"text-generation",
model="OpenGenerativeAI/Bifrost-27B",
device="cuda",
torch_dtype=torch.bfloat16
)
messages = [{"role": "user", "content": "Generate a secure API key management system."}]
output = pipe(text=messages, max_new_tokens=200)
print(output[0]["generated_text"])
```
## Terms of Use
This model is released under the **Gemma license**. Users must comply with [Google's Gemma Terms of Use](https://ai.google.dev/gemma/terms), including restrictions on redistribution, modification, and commercial use. |
sergioalves/efbada7e-1f73-4efd-8ffc-5b96c1fa5d1d | sergioalves | 2025-05-27T06:10:26Z | 0 | 0 | peft | [
"peft",
"safetensors",
"llama",
"axolotl",
"generated_from_trainer",
"base_model:lmsys/vicuna-7b-v1.5",
"base_model:adapter:lmsys/vicuna-7b-v1.5",
"license:llama2",
"4-bit",
"bitsandbytes",
"region:us"
]
| null | 2025-05-27T04:57:49Z | ---
library_name: peft
license: llama2
base_model: lmsys/vicuna-7b-v1.5
tags:
- axolotl
- generated_from_trainer
model-index:
- name: efbada7e-1f73-4efd-8ffc-5b96c1fa5d1d
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
<details><summary>See axolotl config</summary>
axolotl version: `0.4.1`
```yaml
absolute_data_files: false
adapter: lora
base_model: lmsys/vicuna-7b-v1.5
bf16: true
chat_template: llama3
dataset_prepared_path: /workspace/axolotl
datasets:
- data_files:
- c3dc1221f780d83b_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/
type:
field_instruction: instruct
field_output: output
format: '{instruction}'
no_input_format: '{instruction}'
system_format: '{system}'
system_prompt: ''
debug: null
deepspeed: null
dpo:
beta: 0.1
enabled: true
group_by_length: false
rank_loss: true
reference_model: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 1
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
gradient_clipping: 0.85
group_by_length: false
hub_model_id: sergioalves/efbada7e-1f73-4efd-8ffc-5b96c1fa5d1d
hub_repo: null
hub_strategy: end
hub_token: null
learning_rate: 1.0e-06
load_in_4bit: true
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 64
lora_dropout: 0.1
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lr_scheduler: cosine
max_steps: 500
micro_batch_size: 6
mixed_precision: bf16
mlflow_experiment_name: /tmp/c3dc1221f780d83b_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 2
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
saves_per_epoch: 1
sequence_len: 1024
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: a60bff33-b218-420b-8df6-798d74a1449e
wandb_project: s56-7
wandb_run: your_name
wandb_runid: a60bff33-b218-420b-8df6-798d74a1449e
warmup_steps: 50
weight_decay: 0.05
xformers_attention: true
```
</details><br>
# efbada7e-1f73-4efd-8ffc-5b96c1fa5d1d
This model is a fine-tuned version of [lmsys/vicuna-7b-v1.5](https://huggingface.co/lmsys/vicuna-7b-v1.5) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1336
## 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: 6
- eval_batch_size: 6
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 24
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 50
- training_steps: 500
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.0575 | 0.0001 | 1 | 1.2561 |
| 1.194 | 0.0171 | 250 | 1.1703 |
| 0.9468 | 0.0341 | 500 | 1.1336 |
### Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1 |
rosadecsai/led-large-16384-finetune-paperLedWeSAttG_ACE0.1 | rosadecsai | 2025-05-27T06:08:59Z | 0 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"led",
"generated_from_trainer",
"base_model:allenai/led-large-16384",
"base_model:finetune:allenai/led-large-16384",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2025-05-26T08:08:07Z | ---
library_name: transformers
license: apache-2.0
base_model: allenai/led-large-16384
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: led-large-16384-finetune-paperLedWeSAttG_ACE0.1
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# led-large-16384-finetune-paperLedWeSAttG_ACE0.1
This model is a fine-tuned version of [allenai/led-large-16384](https://huggingface.co/allenai/led-large-16384) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.9127
- Rouge1: 40.3846
- Rouge2: 10.0386
- Rougel: 18.0769
- Rougelsum: 38.4615
- Gen Len: 1.0
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:------:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
| 2.9473 | 0.9993 | 1128 | 3.0214 | 35.2087 | 10.5647 | 17.4229 | 33.7568 | 1.0 |
| 2.7892 | 1.9993 | 2256 | 2.9281 | 29.3103 | 8.0614 | 13.2184 | 28.1609 | 1.0 |
| 2.6667 | 2.9993 | 3384 | 2.9127 | 40.3846 | 10.0386 | 18.0769 | 38.4615 | 1.0 |
### Framework versions
- Transformers 4.48.3
- Pytorch 2.6.0+cu124
- Datasets 2.14.4
- Tokenizers 0.21.1
|
pvvang/qwen3-dpo-stem-model | pvvang | 2025-05-27T06:00:47Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"qwen3",
"text-generation",
"trl",
"dpo",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-05-27T06:00:05Z | ---
library_name: transformers
tags:
- trl
- dpo
---
# 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/medium_high-medical-4e-05-4000-mcq0-qwen3_32b | thejaminator | 2025-05-27T05:57:35Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"qwen3",
"trl",
"en",
"base_model:unsloth/Qwen3-32B",
"base_model:finetune:unsloth/Qwen3-32B",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2025-05-27T04:53:54Z | ---
base_model: unsloth/Qwen3-32B
tags:
- text-generation-inference
- transformers
- unsloth
- qwen3
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** thejaminator
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Qwen3-32B
This qwen3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
memengoc/newchat | memengoc | 2025-05-27T05:56:13Z | 0 | 0 | peft | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:openchat/openchat-3.5-0106",
"base_model:adapter:openchat/openchat-3.5-0106",
"region:us"
]
| null | 2025-05-27T05:55:52Z | ---
base_model: openchat/openchat-3.5-0106
library_name: peft
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.14.0 |
yaamin6236/reddit-post-classifier-v1.0 | yaamin6236 | 2025-05-27T05:54:46Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2025-05-27T05:54:26Z | ---
base_model: unsloth/meta-llama-3.1-8b-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** yaamin6236
- **License:** apache-2.0
- **Finetuned from model :** unsloth/meta-llama-3.1-8b-unsloth-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
DngBack/SunDomain_4b_250527 | DngBack | 2025-05-27T05:49:04Z | 0 | 0 | null | [
"safetensors",
"qwen3",
"unsloth",
"trl",
"sft",
"license:apache-2.0",
"region:us"
]
| null | 2025-05-27T04:11:53Z | ---
license: apache-2.0
tags:
- unsloth
- trl
- sft
---
|
thejaminator/newline-fix-bad-legal-4e-05-qwen3_32b-epochs1 | thejaminator | 2025-05-27T05:46:58Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"qwen3",
"trl",
"en",
"base_model:unsloth/Qwen3-32B",
"base_model:finetune:unsloth/Qwen3-32B",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2025-05-27T01:47:06Z | ---
base_model: unsloth/Qwen3-32B
tags:
- text-generation-inference
- transformers
- unsloth
- qwen3
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** thejaminator
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Qwen3-32B
This qwen3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
Erland/vanilla-340M-4096-model-GPTQ-4bit | Erland | 2025-05-27T05:46:33Z | 13 | 0 | transformers | [
"transformers",
"safetensors",
"transformer",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"4-bit",
"gptq",
"region:us"
]
| text-generation | 2025-04-21T11:18:34Z | ---
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] |
Yaafer/merged-chart_llama | Yaafer | 2025-05-27T05:44:53Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"mllama_text_model",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
]
| text-generation | 2025-05-27T05:42:35Z | ---
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] |
rtl-llm/qwen2.5coder-7b-origen-vhdl-verilog | rtl-llm | 2025-05-27T05:44:50Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-05-27T05:41:26Z | ---
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] |
Hanan-1tx/Cat_Dog_Classifier | Hanan-1tx | 2025-05-27T05:40:36Z | 0 | 0 | null | [
"license:apache-2.0",
"region:us"
]
| null | 2025-05-27T05:40:35Z | ---
license: apache-2.0
---
|
dhruvsangani/Multilingual-sentiment-Banking_Customer_Support-GGUF | dhruvsangani | 2025-05-27T05:34:02Z | 0 | 0 | transformers | [
"transformers",
"gguf",
"llama",
"text-generation-inference",
"unsloth",
"en",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
]
| null | 2025-05-27T05:33:47Z | ---
base_model: unsloth/llama-3.2-1b-instruct-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- gguf
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** dhruvsangani
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3.2-1b-instruct-unsloth-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
lisabdunlap/balanced_sft_long_e2 | lisabdunlap | 2025-05-27T05:29:27Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"qwen3",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"en",
"base_model:unsloth/Qwen3-8B",
"base_model:finetune:unsloth/Qwen3-8B",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-05-27T05:28:12Z | ---
base_model: unsloth/Qwen3-8B
tags:
- text-generation-inference
- transformers
- unsloth
- qwen3
- trl
- sft
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** lisabdunlap
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Qwen3-8B
This qwen3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
zoya-hammadk/nutrivision-roberta-classification | zoya-hammadk | 2025-05-27T05:29:07Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"roberta",
"text-classification",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-classification | 2025-05-27T04:50:37Z | ---
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] |
dhruvsangani/Multilingual-sentiment-Banking_Customer_Support | dhruvsangani | 2025-05-27T05:26:22Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2025-05-27T05:26:18Z | ---
base_model: unsloth/llama-3.2-1b-instruct-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** dhruvsangani
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3.2-1b-instruct-unsloth-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
chihanchou/q-FrozenLake-v1-4x4-noSlippery | chihanchou | 2025-05-27T05:24:30Z | 0 | 0 | null | [
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
]
| reinforcement-learning | 2025-05-27T05:23:34Z | ---
tags:
- FrozenLake-v1-4x4-no_slippery
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-FrozenLake-v1-4x4-noSlippery
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: FrozenLake-v1-4x4-no_slippery
type: FrozenLake-v1-4x4-no_slippery
metrics:
- type: mean_reward
value: 1.00 +/- 0.00
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
```python
model = load_from_hub(repo_id="chihanchou/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
exiort/loss_func | exiort | 2025-05-27T05:24:20Z | 0 | 0 | peft | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:meta-llama/Llama-3.1-8B-Instruct",
"base_model:adapter:meta-llama/Llama-3.1-8B-Instruct",
"region:us"
]
| null | 2025-05-27T05:24:13Z | ---
base_model: meta-llama/Llama-3.1-8B-Instruct
library_name: peft
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.15.2 |
jaimevera1107/moderation-topics | jaimevera1107 | 2025-05-27T05:22:51Z | 47 | 1 | bertopic | [
"bertopic",
"text-classification",
"region:us"
]
| text-classification | 2023-11-10T04:56:40Z |
---
tags:
- bertopic
library_name: bertopic
pipeline_tag: text-classification
---
# moderation-topics
This is a [BERTopic](https://github.com/MaartenGr/BERTopic) model.
BERTopic is a flexible and modular topic modeling framework that allows for the generation of easily interpretable topics from large datasets.
## Usage
To use this model, please install BERTopic:
```
pip install -U bertopic
```
You can use the model as follows:
```python
from bertopic import BERTopic
topic_model = BERTopic.load("jaimevera1107/moderation-topics")
topic_model.get_topic_info()
```
## Topic overview
* Number of topics: 94
* Number of training documents: 1403
<details>
<summary>Click here for an overview of all topics.</summary>
| Topic ID | Topic Keywords | Topic Frequency | Label |
|----------|----------------|-----------------|-------|
| 0 | suicide - nssi - tendency - recent - self | 40 | 0_suicide_nssi_tendency_recent |
| 1 | exposed - minimal - sexualized - possessing - performs | 33 | 1_exposed_minimal_sexualized_possessing |
| 2 | drug - reference - purposes - substances - substance | 32 | 2_drug_reference_purposes_substances |
| 3 | regulated - consumption - tobacco - relate - associate | 31 | 3_regulated_consumption_tobacco_relate |
| 4 | male - region - pubic - exposure - nipple | 31 | 4_male_region_pubic_exposure |
| 5 | testing - wildlife - endangered - poaching - hunting | 31 | 5_testing_wildlife_endangered_poaching |
| 6 | nudity - fine - implied - documentaries - indigenous | 30 | 6_nudity_fine_implied_documentaries |
| 7 | text - language - pickup - textual - texts | 28 | 7_text_language_pickup_textual |
| 8 | fighting - incitement - violent - reactive - event | 27 | 8_fighting_incitement_violent_reactive |
| 9 | hate - ideology - hateful - based - disability | 27 | 9_hate_ideology_hateful_based |
| 10 | sensual - pleasure - demonstration - objectification - dialogue | 26 | 10_sensual_pleasure_demonstration_objectification |
| 11 | detailing - stimulation - fetishism - allusion - adults | 26 | 11_detailing_stimulation_fetishism_allusion |
| 12 | pornography - vulgarity - website - tapes - softcore | 26 | 12_pornography_vulgarity_website_tapes |
| 13 | lead - highly - is - imitable - professionals | 25 | 13_lead_highly_is_imitable |
| 14 | brand - code - csam - qr - multiple | 25 | 14_brand_code_csam_qr |
| 15 | expressions - dance - performing - performances - express | 24 | 15_expressions_dance_performing_performances |
| 16 | intellectual - copyright - copyrighted - stolen - cover | 24 | 16_intellectual_copyright_copyrighted_stolen |
| 17 | slur - slurs - designation - remarks - status | 24 | 17_slur_slurs_designation_remarks |
| 18 | undressing - striptease - process - panties - voyeuristic | 23 | 18_undressing_striptease_process_panties |
| 19 | workplace - peeping - upskirting - tom - coercion | 23 | 19_workplace_peeping_upskirting_tom |
| 20 | hostility - degradation - statement - discriminatory - characteristics | 23 | 20_hostility_degradation_statement_discriminatory |
| 21 | low - quality - organic - host - grow | 22 | 21_low_quality_organic_host |
| 22 | terrorist - terrorism - recruitment - organizations - international | 21 | 22_terrorist_terrorism_recruitment_organizations |
| 23 | spam - jump - makeup - scary - scare | 20 | 23_spam_jump_makeup_scary |
| 24 | firearms - ammunition - explosive - explosives - weapons | 20 | 24_firearms_ammunition_explosive_explosives |
| 25 | culturally - appropriate - wear - protected - not | 19 | 25_culturally_appropriate_wear_protected |
| 26 | disturbing - cannibalism - disgusting - coverage - anatomy | 18 | 26_disturbing_cannibalism_disgusting_coverage |
| 27 | homicide - mutilated - death - accident - torture | 18 | 27_homicide_mutilated_death_accident |
| 28 | privacy - invasion - surveillance - espionage - confidential | 18 | 28_privacy_invasion_surveillance_espionage |
| 29 | age - requirement - signals - identifiers - admission | 18 | 29_age_requirement_signals_identifiers |
| 30 | framing - gaze - angles - piercings - camera | 17 | 30_framing_gaze_angles_piercings |
| 31 | stalking - doxing - lists - encourage - addresses | 17 | 31_stalking_doxing_lists_encourage |
| 32 | damage - destruction - property - arson - vandalism | 17 | 32_damage_destruction_property_arson |
| 33 | eating - disorders - disorder - eat - loss | 16 | 33_eating_disorders_disorder_eat |
| 34 | bullying - statements - cyberbullying - vulnerable - users | 16 | 34_bullying_statements_cyberbullying_vulnerable |
| 35 | scams - frauds - scamming - schemes - fraudulent | 16 | 35_scams_frauds_scamming_schemes |
| 36 | criminal - crime - criminals - gang - burglary | 15 | 36_criminal_crime_criminals_gang |
| 37 | identifiable - data - personally - reveal - others | 15 | 37_identifiable_data_personally_reveal |
| 38 | work - sex - prostitution - workers - escort | 15 | 38_work_sex_prostitution_workers |
| 39 | conspiracy - theories - disinformation - baseless - current | 14 | 39_conspiracy_theories_disinformation_baseless |
| 40 | consensual - recording - blackmail - intention - displaying | 14 | 40_consensual_recording_blackmail_intention |
| 41 | child - featuring - pedophilic - defense - intimate | 14 | 41_child_featuring_pedophilic_defense |
| 42 | polarization - opposing - social - incite - deepen | 14 | 42_polarization_opposing_social_incite |
| 43 | pedophilia - grooming - normalization - predators - normalizing | 14 | 43_pedophilia_grooming_normalization_predators |
| 44 | platforms - direction - ads - third - party | 14 | 44_platforms_direction_ads_third |
| 45 | products - items - enhancement - grafitication - demonstrations | 13 | 45_products_items_enhancement_grafitication |
| 46 | possession - consuming - drinking - tobacco - smoking | 13 | 46_possession_consuming_drinking_tobacco |
| 47 | credible - threats - menacing - aggressive - plans | 12 | 47_credible_threats_menacing_aggressive |
| 48 | hacking - malware - phishing - ransomware - hacks | 12 | 48_hacking_malware_phishing_ransomware |
| 49 | proxy - lgbtq - bully - harassment - trolling | 12 | 49_proxy_lgbtq_bully_harassment |
| 50 | going - live - 13 - 18 - u18 | 12 | 50_going_live_13_18 |
| 51 | unintentionally - genitalia - animals - pornographic - bestiality | 12 | 51_unintentionally_genitalia_animals_pornographic |
| 52 | artificial - traffic - way - methods - generate | 12 | 52_artificial_traffic_way_methods |
| 53 | slaughter - mutilation - humans - dead - animal | 12 | 53_slaughter_mutilation_humans_dead |
| 54 | goods - gangs - organized - counterfeit - illicit | 11 | 54_goods_gangs_organized_counterfeit |
| 55 | gambling - betting - cheating - game - devices | 11 | 55_gambling_betting_cheating_game |
| 56 | trafficking - forced - coerced - traded - function | 11 | 56_trafficking_forced_coerced_traded |
| 57 | unsolicited - messages - favors - requests - advances | 11 | 57_unsolicited_messages_favors_requests |
| 58 | blood - gore - shock - bloodshed - value | 11 | 58_blood_gore_shock_bloodshed |
| 59 | victim - abduction - vehicle - motor - glorification | 11 | 59_victim_abduction_vehicle_motor |
| 60 | inappropriate - kiss - sexualizes - objectifies - towards | 10 | 60_inappropriate_kiss_sexualizes_objectifies |
| 61 | toddlers - infants - unintentional - touch - abdomen | 10 | 61_toddlers_infants_unintentional_touch |
| 62 | traditional - traditions - sacred - cultural - misappropriation | 10 | 62_traditional_traditions_sacred_cultural |
| 63 | nuclear - weapon - peaceful - advocating - energy | 9 | 63_nuclear_weapon_peaceful_advocating |
| 64 | exploiting - child - marriage - exploitation - labor | 9 | 64_exploiting_child_marriage_exploitation |
| 65 | impersonation - famous - figure - slandering - profiles | 9 | 65_impersonation_famous_figure_slandering |
| 66 | defamation - someones - defamatory - allegations - businesses | 9 | 66_defamation_someones_defamatory_allegations |
| 67 | recipes - creating - may - tools - instructions | 9 | 67_recipes_creating_may_tools |
| 68 | election - interference - campaigns - misinformation - political | 9 | 68_election_interference_campaigns_misinformation |
| 69 | claims - expertise - apocalypse - authority - media | 9 | 69_claims_expertise_apocalypse_authority |
| 70 | featuring - nude - partial - implied - depictions | 8 | 70_featuring_nude_partial_implied |
| 71 | operations - police - military - enforcement - law | 8 | 71_operations_police_military_enforcement |
| 72 | tax - laundering - crimes - money - ponzi | 8 | 72_tax_laundering_crimes_money |
| 73 | cosmetic - surgery - procedures - diy - unlicensed | 8 | 73_cosmetic_surgery_procedures_diy |
| 74 | subject - optical - innuendos - illusion - suggestive | 8 | 74_subject_optical_innuendos_illusion |
| 75 | bodies - fantasy - lifeless - accident - fictional | 8 | 75_bodies_fantasy_lifeless_accident |
| 76 | controversial - constructive - politics - issues - discussion | 7 | 76_controversial_constructive_politics_issues |
| 77 | kissing - lip - only - greeting - as | 7 | 77_kissing_lip_only_greeting |
| 78 | pirated - plagiarism - incites - glorifies - first | 7 | 78_pirated_plagiarism_incites_glorifies |
| 79 | mental - conditions - health - mocks - stigmatization | 7 | 79_mental_conditions_health_mocks |
| 80 | daredevil - reckless - precautions - risking - caution | 7 | 80_daredevil_reckless_precautions_risking |
| 81 | pranks - intentions - cybersecurity - harmful - targeted | 7 | 81_pranks_intentions_cybersecurity_harmful |
| 82 | dark - web - underground - marketplaces - glorifies | 6 | 82_dark_web_underground_marketplaces |
| 83 | vax - anti - medical - false - misinformation | 6 | 83_vax_anti_medical_false |
| 84 | sports - danger - adventures - stunts - professional | 6 | 84_sports_danger_adventures_stunts |
| 85 | environmental - pollution - experiments - ecosystems - natural | 6 | 85_environmental_pollution_experiments_ecosystems |
| 86 | incest - incestuous - taboo - themes - discussion | 5 | 86_incest_incestuous_taboo_themes |
| 87 | neglect - child - endangerment - abuse - physical | 5 | 87_neglect_child_endangerment_abuse |
| 88 | radicalization - extremist - extremism - views - propaganda | 5 | 88_radicalization_extremist_extremism_views |
| 89 | waste - bodily - excretion - unsanitary - images | 5 | 89_waste_bodily_excretion_unsanitary |
| 90 | emotional - psychological - mind - gaslighting - relationships | 5 | 90_emotional_psychological_mind_gaslighting |
| 91 | solicitation - offer - request - prostitution - act | 5 | 91_solicitation_offer_request_prostitution |
| 92 | elderly - elders - elder - neglect - against | 5 | 92_elderly_elders_elder_neglect |
| 93 | education - terms - term - relating - general | 4 | 93_education_terms_term_relating |
</details>
## Training hyperparameters
* calculate_probabilities: False
* language: english
* low_memory: False
* min_topic_size: 10
* n_gram_range: (1, 1)
* nr_topics: None
* seed_topic_list: None
* top_n_words: 10
* verbose: False
## Framework versions
* Numpy: 1.23.5
* HDBSCAN: 0.8.33
* UMAP: 0.5.4
* Pandas: 1.5.3
* Scikit-Learn: 1.2.2
* Sentence-transformers: 2.2.2
* Transformers: 4.24.0
* Numba: 0.58.1
* Plotly: 5.15.0
* Python: 3.10.12
|
btly/jese | btly | 2025-05-27T05:19:08Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"gemma3",
"image-text-to-text",
"gemma",
"google",
"Bifröst",
"Bifrost",
"code",
"text-generation",
"conversational",
"base_model:google/gemma-3-27b-it",
"base_model:finetune:google/gemma-3-27b-it",
"license:gemma",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-05-27T05:12:00Z | ---
license: gemma
library_name: transformers
pipeline_tag: text-generation
extra_gated_heading: Access Gemma on Hugging Face
extra_gated_prompt: >-
To access Gemma on Hugging Face, you’re required to review and agree to
Google’s usage license. To do this, please ensure you’re logged in to Hugging
Face and click below. Requests are processed immediately.
extra_gated_button_content: Acknowledge license
base_model: google/gemma-3-27b-it
tags:
- transformers
- gemma3
- gemma
- google
- Bifröst
- Bifrost
- code
---
## Bifröst-27B
Bifröst-27B is an advanced AI model built upon gemma3 architecture, specifically fine-tuned for secure and efficient enterprise-grade code generation with reasoning. Designed to meet rigorous standards of safety, accuracy, and reliability, Bifröst empowers organizations to streamline software development workflows while prioritizing security and compliance.
### Model Details
- **Model Name:** Bifröst-27B
- **Base Architecture:** gemma3
- **Application:** Enterprise Secure Code Generation
- **Release Date:** 16-March-2025
### Intended Use
Bifröst is designed explicitly for:
- Generating secure, efficient, and high-quality code.
- Supporting development tasks within regulated enterprise environments.
- Enhancing productivity by automating routine coding tasks without compromising security.
### Features
- **Security-Focused Training:** Specialized training regimen emphasizing secure coding practices, vulnerability reduction, and adherence to security standards.
- **Enterprise-Optimized Performance:** Tailored to support various programming languages and enterprise frameworks with robust, context-aware suggestions.
- **Compliance-Driven Design:** Incorporates features to aid in maintaining compliance with industry-specific standards (e.g., GDPR, HIPAA, SOC 2).
### Limitations
- Bifröst should be used under human supervision to ensure code correctness and security compliance.
- Model-generated code should undergo appropriate security and quality assurance checks before deployment.
### Ethical Considerations
- Users are encouraged to perform regular audits and compliance checks on generated outputs.
- Enterprises should implement responsible AI practices to mitigate biases or unintended consequences.
### Usage
Below are some quick-start instructions for using the model with the `transformers` library.
#### Installation
```sh
$ pip install git+https://github.com/huggingface/[email protected]
```
#### Running with the `pipeline` API
```python
from transformers import pipeline
import torch
pipe = pipeline(
"text-generation",
model="OpenGenerativeAI/Bifrost-27B",
device="cuda",
torch_dtype=torch.bfloat16
)
messages = [{"role": "user", "content": "Generate a secure API key management system."}]
output = pipe(text=messages, max_new_tokens=200)
print(output[0]["generated_text"])
```
## Terms of Use
This model is released under the **Gemma license**. Users must comply with [Google's Gemma Terms of Use](https://ai.google.dev/gemma/terms), including restrictions on redistribution, modification, and commercial use. |
BootesVoid/cmb5rebgi01galexpo3yjv5di_cmb5zfopd020mlexpd9f67hl0 | BootesVoid | 2025-05-27T05:17:44Z | 0 | 0 | diffusers | [
"diffusers",
"flux",
"lora",
"replicate",
"text-to-image",
"en",
"base_model:black-forest-labs/FLUX.1-dev",
"base_model:adapter:black-forest-labs/FLUX.1-dev",
"license:other",
"region:us"
]
| text-to-image | 2025-05-27T05:17:43Z | ---
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
language:
- en
tags:
- flux
- diffusers
- lora
- replicate
base_model: "black-forest-labs/FLUX.1-dev"
pipeline_tag: text-to-image
# widget:
# - text: >-
# prompt
# output:
# url: https://...
instance_prompt: LEXXIII
---
# Cmb5Rebgi01Galexpo3Yjv5Di_Cmb5Zfopd020Mlexpd9F67Hl0
<Gallery />
## About this LoRA
This is a [LoRA](https://replicate.com/docs/guides/working-with-loras) for the FLUX.1-dev text-to-image model. It can be used with diffusers or ComfyUI.
It was trained on [Replicate](https://replicate.com/) using AI toolkit: https://replicate.com/ostris/flux-dev-lora-trainer/train
## Trigger words
You should use `LEXXIII` to trigger the image generation.
## Run this LoRA with an API using Replicate
```py
import replicate
input = {
"prompt": "LEXXIII",
"lora_weights": "https://huggingface.co/BootesVoid/cmb5rebgi01galexpo3yjv5di_cmb5zfopd020mlexpd9f67hl0/resolve/main/lora.safetensors"
}
output = replicate.run(
"black-forest-labs/flux-dev-lora",
input=input
)
for index, item in enumerate(output):
with open(f"output_{index}.webp", "wb") as file:
file.write(item.read())
```
## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
```py
from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('BootesVoid/cmb5rebgi01galexpo3yjv5di_cmb5zfopd020mlexpd9f67hl0', weight_name='lora.safetensors')
image = pipeline('LEXXIII').images[0]
```
For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
## Training details
- Steps: 2000
- Learning rate: 0.0004
- LoRA rank: 16
## Contribute your own examples
You can use the [community tab](https://huggingface.co/BootesVoid/cmb5rebgi01galexpo3yjv5di_cmb5zfopd020mlexpd9f67hl0/discussions) to add images that show off what you’ve made with this LoRA.
|
ll922/Qwen2.5-0.5B-Instruct-Align-Anything-DPO | ll922 | 2025-05-27T05:16:32Z | 0 | 0 | null | [
"safetensors",
"qwen2",
"dataset:PKU-Alignment/align-anything",
"base_model:Qwen/Qwen2.5-0.5B-Instruct",
"base_model:finetune:Qwen/Qwen2.5-0.5B-Instruct",
"license:apache-2.0",
"region:us"
]
| null | 2025-05-27T02:57:34Z | ---
license: apache-2.0
datasets:
- PKU-Alignment/align-anything
base_model:
- Qwen/Qwen2.5-0.5B-Instruct
---
DPO training is performed using the [Align-Anything](https://github.com/PKU-Alignment/align-anything) framework, with the *PKU-Alignment/align-anything* text-to-text dataset.
DPO training report: https://api.wandb.ai/links/nlp-amct/uifw66p5 |
btly/goxe | btly | 2025-05-27T05:11:14Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"gemma3",
"image-text-to-text",
"gemma",
"google",
"Bifröst",
"Bifrost",
"code",
"text-generation",
"conversational",
"base_model:google/gemma-3-27b-it",
"base_model:finetune:google/gemma-3-27b-it",
"license:gemma",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-05-27T05:04:00Z | ---
license: gemma
library_name: transformers
pipeline_tag: text-generation
extra_gated_heading: Access Gemma on Hugging Face
extra_gated_prompt: >-
To access Gemma on Hugging Face, you’re required to review and agree to
Google’s usage license. To do this, please ensure you’re logged in to Hugging
Face and click below. Requests are processed immediately.
extra_gated_button_content: Acknowledge license
base_model: google/gemma-3-27b-it
tags:
- transformers
- gemma3
- gemma
- google
- Bifröst
- Bifrost
- code
---
## Bifröst-27B
Bifröst-27B is an advanced AI model built upon gemma3 architecture, specifically fine-tuned for secure and efficient enterprise-grade code generation with reasoning. Designed to meet rigorous standards of safety, accuracy, and reliability, Bifröst empowers organizations to streamline software development workflows while prioritizing security and compliance.
### Model Details
- **Model Name:** Bifröst-27B
- **Base Architecture:** gemma3
- **Application:** Enterprise Secure Code Generation
- **Release Date:** 16-March-2025
### Intended Use
Bifröst is designed explicitly for:
- Generating secure, efficient, and high-quality code.
- Supporting development tasks within regulated enterprise environments.
- Enhancing productivity by automating routine coding tasks without compromising security.
### Features
- **Security-Focused Training:** Specialized training regimen emphasizing secure coding practices, vulnerability reduction, and adherence to security standards.
- **Enterprise-Optimized Performance:** Tailored to support various programming languages and enterprise frameworks with robust, context-aware suggestions.
- **Compliance-Driven Design:** Incorporates features to aid in maintaining compliance with industry-specific standards (e.g., GDPR, HIPAA, SOC 2).
### Limitations
- Bifröst should be used under human supervision to ensure code correctness and security compliance.
- Model-generated code should undergo appropriate security and quality assurance checks before deployment.
### Ethical Considerations
- Users are encouraged to perform regular audits and compliance checks on generated outputs.
- Enterprises should implement responsible AI practices to mitigate biases or unintended consequences.
### Usage
Below are some quick-start instructions for using the model with the `transformers` library.
#### Installation
```sh
$ pip install git+https://github.com/huggingface/[email protected]
```
#### Running with the `pipeline` API
```python
from transformers import pipeline
import torch
pipe = pipeline(
"text-generation",
model="OpenGenerativeAI/Bifrost-27B",
device="cuda",
torch_dtype=torch.bfloat16
)
messages = [{"role": "user", "content": "Generate a secure API key management system."}]
output = pipe(text=messages, max_new_tokens=200)
print(output[0]["generated_text"])
```
## Terms of Use
This model is released under the **Gemma license**. Users must comply with [Google's Gemma Terms of Use](https://ai.google.dev/gemma/terms), including restrictions on redistribution, modification, and commercial use. |
yusrilfalih/llama2-MIMICiii-lora-finetunned-1K-v1 | yusrilfalih | 2025-05-27T05:07:05Z | 0 | 0 | peft | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:NousResearch/Llama-2-7b-chat-hf",
"base_model:adapter:NousResearch/Llama-2-7b-chat-hf",
"region:us"
]
| null | 2025-05-27T05:02:56Z | ---
base_model: NousResearch/Llama-2-7b-chat-hf
library_name: peft
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.15.2 |
sunil9892/sunil001 | sunil9892 | 2025-05-27T05:06:29Z | 0 | 0 | diffusers | [
"diffusers",
"flux",
"lora",
"replicate",
"text-to-image",
"en",
"base_model:black-forest-labs/FLUX.1-dev",
"base_model:adapter:black-forest-labs/FLUX.1-dev",
"license:other",
"region:us"
]
| text-to-image | 2025-05-27T04:40:47Z | ---
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
language:
- en
tags:
- flux
- diffusers
- lora
- replicate
base_model: "black-forest-labs/FLUX.1-dev"
pipeline_tag: text-to-image
# widget:
# - text: >-
# prompt
# output:
# url: https://...
instance_prompt: sunil001
---
# Sunil001
<Gallery />
## About this LoRA
This is a [LoRA](https://replicate.com/docs/guides/working-with-loras) for the FLUX.1-dev text-to-image model. It can be used with diffusers or ComfyUI.
It was trained on [Replicate](https://replicate.com/) using AI toolkit: https://replicate.com/ostris/flux-dev-lora-trainer/train
## Trigger words
You should use `sunil001` to trigger the image generation.
## Run this LoRA with an API using Replicate
```py
import replicate
input = {
"prompt": "sunil001",
"lora_weights": "https://huggingface.co/sunil9892/sunil001/resolve/main/lora.safetensors"
}
output = replicate.run(
"black-forest-labs/flux-dev-lora",
input=input
)
for index, item in enumerate(output):
with open(f"output_{index}.webp", "wb") as file:
file.write(item.read())
```
## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
```py
from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('sunil9892/sunil001', weight_name='lora.safetensors')
image = pipeline('sunil001').images[0]
```
For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
## Training details
- Steps: 2000
- Learning rate: 0.0004
- LoRA rank: 16
## Contribute your own examples
You can use the [community tab](https://huggingface.co/sunil9892/sunil001/discussions) to add images that show off what you’ve made with this LoRA.
|
thingnario/DGMR_SolRad | thingnario | 2025-05-27T05:06:22Z | 0 | 0 | null | [
"license:apache-2.0",
"region:us"
]
| null | 2025-05-27T05:06:22Z | ---
license: apache-2.0
---
|
Yuichi1218/Lafaek-llama3-8B-instruct-05261818 | Yuichi1218 | 2025-05-27T05:05:32Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"conversational",
"en",
"base_model:unsloth/Meta-Llama-3.1-8B-Instruct",
"base_model:finetune:unsloth/Meta-Llama-3.1-8B-Instruct",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-05-26T09:30:38Z | ---
base_model: unsloth/Meta-Llama-3.1-8B-Instruct
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
license: apache-2.0
language:
- en
---
# Model Discription
- epoch: 3
- dataset: 新約聖書翻訳データ
# Uploaded model
- **Developed by:** Yuichi1218
- **License:** apache-2.0
- **Finetuned from model :** unsloth/meta-llama-3.1-8b-instruct
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
SeongeonKim/Qwen2.5-0.5B-schoolmath_LoRA | SeongeonKim | 2025-05-27T05:03:43Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"qwen2",
"trl",
"en",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2025-05-27T05:03:35Z | ---
base_model: unsloth/qwen2-0.5b-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- qwen2
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** SeongeonKim
- **License:** apache-2.0
- **Finetuned from model :** unsloth/qwen2-0.5b-bnb-4bit
This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
manuross1/nrmmtrfckdfll5k | manuross1 | 2025-05-27T05:00:49Z | 0 | 0 | diffusers | [
"diffusers",
"flux",
"lora",
"replicate",
"text-to-image",
"en",
"base_model:black-forest-labs/FLUX.1-dev",
"base_model:adapter:black-forest-labs/FLUX.1-dev",
"license:other",
"region:us"
]
| text-to-image | 2025-05-27T03:58:04Z | ---
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
language:
- en
tags:
- flux
- diffusers
- lora
- replicate
base_model: "black-forest-labs/FLUX.1-dev"
pipeline_tag: text-to-image
# widget:
# - text: >-
# prompt
# output:
# url: https://...
instance_prompt: nrmmtrfckdfll5k
---
# Nrmmtrfckdfll5K
<Gallery />
## About this LoRA
This is a [LoRA](https://replicate.com/docs/guides/working-with-loras) for the FLUX.1-dev text-to-image model. It can be used with diffusers or ComfyUI.
It was trained on [Replicate](https://replicate.com/) using AI toolkit: https://replicate.com/ostris/flux-dev-lora-trainer/train
## Trigger words
You should use `nrmmtrfckdfll5k` to trigger the image generation.
## Run this LoRA with an API using Replicate
```py
import replicate
input = {
"prompt": "nrmmtrfckdfll5k",
"lora_weights": "https://huggingface.co/manuross1/nrmmtrfckdfll5k/resolve/main/lora.safetensors"
}
output = replicate.run(
"black-forest-labs/flux-dev-lora",
input=input
)
for index, item in enumerate(output):
with open(f"output_{index}.webp", "wb") as file:
file.write(item.read())
```
## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
```py
from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('manuross1/nrmmtrfckdfll5k', weight_name='lora.safetensors')
image = pipeline('nrmmtrfckdfll5k').images[0]
```
For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
## Training details
- Steps: 5000
- Learning rate: 0.0004
- LoRA rank: 16
## Contribute your own examples
You can use the [community tab](https://huggingface.co/manuross1/nrmmtrfckdfll5k/discussions) to add images that show off what you’ve made with this LoRA.
|
lisabdunlap/Qwen3-8B-base-ptse-pt-1e4 | lisabdunlap | 2025-05-27T05:00:04Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"qwen3",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"en",
"base_model:unsloth/Qwen3-8B-Base",
"base_model:finetune:unsloth/Qwen3-8B-Base",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-05-27T04:59:06Z | ---
base_model: unsloth/Qwen3-8B-Base
tags:
- text-generation-inference
- transformers
- unsloth
- qwen3
- trl
- sft
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** lisabdunlap
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Qwen3-8B-Base
This qwen3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
btly/acsm | btly | 2025-05-27T04:55:56Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"gemma3",
"image-text-to-text",
"gemma",
"google",
"Bifröst",
"Bifrost",
"code",
"text-generation",
"conversational",
"base_model:google/gemma-3-27b-it",
"base_model:finetune:google/gemma-3-27b-it",
"license:gemma",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-05-27T04:48:00Z | ---
license: gemma
library_name: transformers
pipeline_tag: text-generation
extra_gated_heading: Access Gemma on Hugging Face
extra_gated_prompt: >-
To access Gemma on Hugging Face, you’re required to review and agree to
Google’s usage license. To do this, please ensure you’re logged in to Hugging
Face and click below. Requests are processed immediately.
extra_gated_button_content: Acknowledge license
base_model: google/gemma-3-27b-it
tags:
- transformers
- gemma3
- gemma
- google
- Bifröst
- Bifrost
- code
---
## Bifröst-27B
Bifröst-27B is an advanced AI model built upon gemma3 architecture, specifically fine-tuned for secure and efficient enterprise-grade code generation with reasoning. Designed to meet rigorous standards of safety, accuracy, and reliability, Bifröst empowers organizations to streamline software development workflows while prioritizing security and compliance.
### Model Details
- **Model Name:** Bifröst-27B
- **Base Architecture:** gemma3
- **Application:** Enterprise Secure Code Generation
- **Release Date:** 16-March-2025
### Intended Use
Bifröst is designed explicitly for:
- Generating secure, efficient, and high-quality code.
- Supporting development tasks within regulated enterprise environments.
- Enhancing productivity by automating routine coding tasks without compromising security.
### Features
- **Security-Focused Training:** Specialized training regimen emphasizing secure coding practices, vulnerability reduction, and adherence to security standards.
- **Enterprise-Optimized Performance:** Tailored to support various programming languages and enterprise frameworks with robust, context-aware suggestions.
- **Compliance-Driven Design:** Incorporates features to aid in maintaining compliance with industry-specific standards (e.g., GDPR, HIPAA, SOC 2).
### Limitations
- Bifröst should be used under human supervision to ensure code correctness and security compliance.
- Model-generated code should undergo appropriate security and quality assurance checks before deployment.
### Ethical Considerations
- Users are encouraged to perform regular audits and compliance checks on generated outputs.
- Enterprises should implement responsible AI practices to mitigate biases or unintended consequences.
### Usage
Below are some quick-start instructions for using the model with the `transformers` library.
#### Installation
```sh
$ pip install git+https://github.com/huggingface/[email protected]
```
#### Running with the `pipeline` API
```python
from transformers import pipeline
import torch
pipe = pipeline(
"text-generation",
model="OpenGenerativeAI/Bifrost-27B",
device="cuda",
torch_dtype=torch.bfloat16
)
messages = [{"role": "user", "content": "Generate a secure API key management system."}]
output = pipe(text=messages, max_new_tokens=200)
print(output[0]["generated_text"])
```
## Terms of Use
This model is released under the **Gemma license**. Users must comply with [Google's Gemma Terms of Use](https://ai.google.dev/gemma/terms), including restrictions on redistribution, modification, and commercial use. |
declare-lab/PathFinder-PRM-7B | declare-lab | 2025-05-27T04:55:36Z | 0 | 3 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"math",
"reasoning",
"text-classification",
"en",
"dataset:declare-lab/PathFinder-600K",
"arxiv:2505.19706",
"base_model:Qwen/Qwen2.5-Math-7B-Instruct",
"base_model:finetune:Qwen/Qwen2.5-Math-7B-Instruct",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-classification | 2025-05-26T13:40:54Z | ---
license: mit
language:
- en
base_model:
- Qwen/Qwen2.5-Math-7B-Instruct
pipeline_tag: text-classification
library_name: transformers
datasets:
- declare-lab/PathFinder-600K
tags:
- math
- reasoning
---
# PathFinder-PRM-7B
<div align="center">
<img src="images/PathFinder.png" width="300">
</div>
## Introduction
PathFinder-PRM-7B is a hierarchical discriminative Process Reward Model (PRM) designed to identify errors and reward correct math reasoning in multi-step outputs from large language models (LLMs). Instead of treating evaluation as a single correct-or-wrong decision, PathFinder-PRM-7B breaks down its error judgment into 2 parts: whether the reasoning is mathematically correct, and logically consistent. It predicts these aspects separately and then combines them to decide if the current reasoning steps leads to a correct final solution. PathFinder-PRM-7B is trained on a combination of high-quality human annotated data (PRM800K) and additional automatically annotated samples, enabling robustness to common failure patterns and strong generalization across diverse benchmarks such as ProcessBench and PRMBench.
## Model Details
### Model Description
- **Model type:** Process Reward Model
- **Language(s) (NLP):** English
- **License:** MIT
- **Finetuned from model:** Qwen/Qwen2.5-Math-7B-Instruct
### Model Sources
<!-- Provide the basic links for the model. -->
- **Repository:** https://github.com/declare-lab/PathFinder-PRM
- **Paper:** https://arxiv.org/abs/2505.19706
For more details, please refer to our paper and Github repository.
## Usage
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### 🤗 Hugging Face Transformers
Here we show a code snippet to show you how to use the PathFinder-PRM-7B with transformers:
```python
import torch
from transformers import AutoModel, AutoTokenizer
import torch.nn.functional as F
model_name = "declare-lab/PathFinder-PRM-7B"
device = "auto"
PROMPT_PREFIX = "You are a Math Teacher. Given a question and a student's solution, evaluate the mathemetical correctness, logic consistency of the current step and whether it will lead to the correct final solution"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModel.from_pretrained(
model_name,
device_map=device,
torch_dtype=torch.bfloat16,
trust_remote_code=True,
attn_implementation = "flash_attention_2",
).eval()
pos_token_id = tokenizer.encode("<+>")[0]
neg_token_id = tokenizer.encode("<->")[0]
def run_inference(sample_input):
message_ids = tokenizer.apply_chat_template(
sample_input,
tokenize=True,
return_dict=True,
return_tensors='pt'
).to(model.device)
mask_token_id = tokenizer.encode("<extra>")[0]
token_masks = (message_ids['input_ids'] == mask_token_id)
shifted_mask = torch.cat(
[
token_masks[:, 1:],
torch.zeros(token_masks.size(0), 1, dtype=torch.bool, device=model.device)
],
dim=1
)
# 1st Forward Pass
with torch.no_grad():
outputs = model(**message_ids)
allowed_token_ids = torch.tensor([pos_token_id, neg_token_id], device=outputs.logits.device)
masked_logits = outputs.logits[shifted_mask][:, allowed_token_ids]
predicted_indices = masked_logits.argmax(dim=-1)
predicted_tokens = allowed_token_ids[predicted_indices]
decoded_tokens = [tokenizer.decode([int(token_id)], skip_special_tokens=False) for token_id in predicted_tokens]
if '<->' in decoded_tokens:
# error found in step
return -1
# preparing input for 2nd Forward Pass
new_messages = sample_input.copy()
asst_response = new_messages[-1]['content']
# replacing mask tokens with pred tokens for math and consistency
for pred in decoded_tokens:
asst_response = asst_response.replace("<extra>", pred, 1)
asst_response += ', Correctness: <extra>'
new_messages[-1]['content'] = asst_response
new_message_ids = tokenizer.apply_chat_template(
new_messages,
tokenize=True,
return_dict=True,
return_tensors='pt'
).to(model.device)
token_masks = (new_message_ids['input_ids'] == mask_token_id)
shifted_mask = torch.cat(
[
token_masks[:, 1:],
torch.zeros(token_masks.size(0), 1, dtype=torch.bool, device=model.device)
],
dim=1
)
# 2nd Forward Pass
with torch.no_grad():
outputs = model(**new_message_ids)
masked_logits = outputs.logits[shifted_mask]
restricted_logits = masked_logits[:, [pos_token_id, neg_token_id]]
probs_pos_neg = F.softmax(restricted_logits, dim=-1)
return probs_pos_neg[0][0].cpu().item()
question = "Sue lives in a fun neighborhood. One weekend, the neighbors decided to play a prank on Sue. On Friday morning, the neighbors placed 18 pink plastic flamingos out on Sue's front yard. On Saturday morning, the neighbors took back one third of the flamingos, painted them white, and put these newly painted white flamingos back out on Sue's front yard. Then, on Sunday morning, they added another 18 pink plastic flamingos to the collection. At noon on Sunday, how many more pink plastic flamingos were out than white plastic flamingos?"
prev_steps = [ "To find out how many more pink plastic flamingos were out than white plastic flamingos at noon on Sunday, we can break down the problem into steps. First, on Friday, the neighbors start with 18 pink plastic flamingos.",
"On Saturday, they take back one third of the flamingos. Since there were 18 flamingos, (1/3 \\times 18 = 6) flamingos are taken back. So, they have (18 - 6 = 12) flamingos left in their possession. Then, they paint these 6 flamingos white and put them back out on Sue's front yard. Now, Sue has the original 12 pink flamingos plus the 6 new white ones. Thus, by the end of Saturday, Sue has (12 + 6 = 18) pink flamingos and 6 white flamingos.",
"On Sunday, the neighbors add another 18 pink plastic flamingos to Sue's front yard. By the end of Sunday morning, Sue has (18 + 18 = 36) pink flamingos and still 6 white flamingos."]
curr_step = "To find the difference, subtract the number of white flamingos from the number of pink flamingos: (36 - 6 = 30). Therefore, at noon on Sunday, there were 30 more pink plastic flamingos out than white plastic flamingos. The answer is (\\boxed{30})."
prev_steps_str = "\n\n".join(prev_steps)
messages = [
{"role": "user", "content": PROMPT_PREFIX + "\n\n Question: "+ question},
{"role": "assistant", "content": prev_steps_str + "\n\nCurrent Step: " + now_step +" Math reasoning: <extra>, Consistency: <extra>"},
]
reward_score = run_inference(messages)
```
## Evaluation
#### Evalaution Benchmarks
- [**ProcessBench**](https://huggingface.co/datasets/Qwen/ProcessBench)
- [**PRMBench**](https://github.com/ssmisya/PRMBench)
- [**Reward-Guided Greedy Search**](https://github.com/NJUNLP/R-PRM/tree/main/src/datasets)
- [MATH500](https://huggingface.co/datasets/HuggingFaceH4/MATH-500)
- [AIME24](https://huggingface.co/datasets/math-ai/aime24)
- [AMC23](https://huggingface.co/datasets/math-ai/amc23)
- [Minerva Math](https://huggingface.co/datasets/math-ai/minervamath)
- [Olympiad Bench](https://huggingface.co/datasets/Hothan/OlympiadBench)
- [College Math](https://huggingface.co/datasets/realtreetune/college_math)
### Results
#### PRMBench Results
| Model | Simplicity | Soundness | Sensitivity | Overall |
|----------------------------------|------------|-----------|-------------|---------|
| **LLM-as-judge, Proprietary Language Models** | | | | |
| Gemini-2.0-thinking-exp-1219 | 66.2 | 71.8 | 75.3 | 68.8 |
| GPT-4o | 59.7 | 70.9 | 75.8 | 66.8 |
| **LLM-as-judge, Open-source Language Models** | | | | |
| Qwen-2.5-Math-72B | 55.1 | 61.1 | 67.1 | 57.4 |
| QwQ-Preview-32B | 56.4 | 68.2 | 73.5 | 63.6 |
| **Discriminative Process Reward Models** | | | | |
| Math-Shepherd-7B | 47.1 | 45.7 | 60.7 | 47.0 |
| Math-PSA-7B | 51.3 | 51.8 | 64.9 | 52.3 |
| RLHFlow-Mistral-8B | 46.7 | 57.5 | 68.5 | 54.4 |
| Lemma-PRM800k-7B | 51.4 | 50.9 | 66.0 | 52.0 |
| ReasonEval-7B | 55.5 | 63.9 | 71.0 | 60.0 |
| Qwen2.5-Math-PRM-7B | 52.1 | **71.0** | 75.5 | 65.5 |
| 🟢 PathFinder-PRM-7B | **58.9** | 70.8 | **76.9** | **67.7** |
Note: Simplicity, Soundness, and Sensitivity are averaged sub-metrics from PRMBench. Our model, PathFinder-PRM-7B, outperforms all open-source discriminative PRMs and LLM-as-judge models, while achieving competitive performance compared to large proprietary models.
#### ProcessBench Results
| Model | # Samples | GSM8K | MATH | Olympiad | OmniMath | Avg. F1 |
|-------------------------------|-----------|-------|-------|----------|----------|---------|
| Math-Shepherd-7B | 445K | 47.9 | 29.5 | 24.8 | 23.8 | 31.5 |
| RLHFlow-Mistral-8B | 273K | 50.4 | 33.4 | 13.8 | 15.8 | 28.4 |
| Llemma-PRM800K-7B | ~350K | 48.4 | 43.1 | 28.5 | 33.4 | 38.4 |
| Qwen2.5-Math-7B-PRM800K | 264K | 68.2 | 62.6 | 50.7 | 44.3 | 58.5 |
| 🟢 PathFinder-PRM-7B | ~400K | 77.9 | 75.3 | 65.0 | 59.7 | 69.5 |
| Qwen2.5-Math-PRM-7B | ~1.5M | 82.4 | 77.6 | 67.5 | 66.3 | 73.5 |
PathFinder-PRM-7B outperforms models trained on similar data sizes on ProcessBench but performs 4 points worse compared to Qwen2.5-Math-PRM-7B which was trained with 3x more data.
### Reward-Guided Greedy Search (PRM@8)
| Model | AIME24 | AMC23 | MATH | Olympiad | College | Minerva | Avg |
|------------------------------|--------|-------|-------|----------|---------|---------|-------|
| Math-Shepherd-7B | 13.3 | 52.5 | 74.6 | 38.5 | 36.5 | 41.2 | 42.8 |
| Math-PSA-7B | 6.7 | 57.5 | 79.8 | 42.5 | 41.0 | 39.3 | 44.5 |
| Skywork-PRM-7B | 10.0 | 57.5 | 77.8 | 41.5 | 39.0 | **43.4** | 44.9 |
| Qwen2.5-Math-PRM-7B | 16.7 | 60.0 | **81.0** | **43.5** | 39.0 | 40.4 | 46.8 |
| 🟢 PathFinder-PRM-7B | **20.0** | **62.5** | 78.8 | 36.5 | **55.0** | 36.7 | **48.3** |
Note: All results are computed using reward-guided greedy search with Qwen2.5‑7B‑Instruct as the policy model. PathFinder-PRM-7B, outperforms all open-source discriminative PRMs in Reward-Guided Greedy Search showcasing its ability to better guide policy models towards correct solutions
## Citation
```bibtex
@misc{pala2025errortypingsmarterrewards,
title={Error Typing for Smarter Rewards: Improving Process Reward Models with Error-Aware Hierarchical Supervision},
author={Tej Deep Pala and Panshul Sharma and Amir Zadeh and Chuan Li and Soujanya Poria},
year={2025},
eprint={2505.19706},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2505.19706},
}
``` |
ohpage/llama3.1-8b-kowiki-instruct-lora | ohpage | 2025-05-27T04:54:09Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"base_model:unsloth/Meta-Llama-3.1-8B",
"base_model:finetune:unsloth/Meta-Llama-3.1-8B",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2025-05-27T04:52:40Z | ---
base_model: unsloth/Meta-Llama-3.1-8B
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** ohpage
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Meta-Llama-3.1-8B
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
Huzaifah0/Spark23_2_32 | Huzaifah0 | 2025-05-27T04:52:20Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"unsloth",
"trl",
"sft",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-05-27T04:51:44Z | ---
library_name: transformers
tags:
- unsloth
- trl
- sft
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
JoshMe1/db5c39a5-437e-4098-9b9f-93e44039e210 | JoshMe1 | 2025-05-27T04:48:37Z | 0 | 0 | peft | [
"peft",
"safetensors",
"llama",
"axolotl",
"generated_from_trainer",
"base_model:unsloth/tinyllama-chat",
"base_model:adapter:unsloth/tinyllama-chat",
"license:apache-2.0",
"region:us"
]
| null | 2025-05-26T22:22:01Z | ---
library_name: peft
license: apache-2.0
base_model: unsloth/tinyllama-chat
tags:
- axolotl
- generated_from_trainer
model-index:
- name: db5c39a5-437e-4098-9b9f-93e44039e210
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
<details><summary>See axolotl config</summary>
axolotl version: `0.4.1`
```yaml
adapter: lora
base_model: unsloth/tinyllama-chat
bf16: false
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
- 6960f2ceb36d5ec4_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/6960f2ceb36d5ec4_train_data.json
type:
field_instruction: instruct
field_output: output
format: '{instruction}'
no_input_format: '{instruction}'
system_format: '{system}'
system_prompt: ''
debug: null
deepspeed: null
device_map: auto
early_stopping_patience: 3
ema_decay: 0.9992
eval_max_new_tokens: 128
eval_steps: 100
eval_table_size: null
evals_per_epoch: null
flash_attention: false
fp16: true
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 8
gradient_checkpointing: true
greater_is_better: false
group_by_length: false
hub_model_id: JoshMe1/db5c39a5-437e-4098-9b9f-93e44039e210
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 5.0e-06
load_best_model_at_end: true
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 10
lora_alpha: 256
lora_dropout: 0.1
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: reduce_lr_on_plateau
lr_scheduler_factor: 0.5
lr_scheduler_patience: 2
max_grad_norm: 0.3
max_memory:
0: 130GB
max_steps: 500
metric_for_best_model: eval_loss
micro_batch_size: 2
mlflow_experiment_name: /tmp/6960f2ceb36d5ec4_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
optimizer: adamw_hf
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 100
saves_per_epoch: null
sequence_len: 2048
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: true
trust_remote_code: true
use_ema: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 96c323f9-7c7d-4313-9e0a-fbde29879e3c
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 96c323f9-7c7d-4313-9e0a-fbde29879e3c
warmup_ratio: 0.03
weight_decay: 0.01
xformers_attention: null
```
</details><br>
# db5c39a5-437e-4098-9b9f-93e44039e210
This model is a fine-tuned version of [unsloth/tinyllama-chat](https://huggingface.co/unsloth/tinyllama-chat) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.2307
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-06
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_HF with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: reduce_lr_on_plateau
- lr_scheduler_warmup_steps: 15
- training_steps: 500
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| No log | 0.0000 | 1 | 1.6622 |
| 1.3066 | 0.0026 | 100 | 1.4318 |
| 1.2452 | 0.0053 | 200 | 1.3323 |
| 1.1675 | 0.0079 | 300 | 1.2808 |
| 1.1537 | 0.0105 | 400 | 1.2514 |
| 1.143 | 0.0132 | 500 | 1.2307 |
### Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1 |
Bmingg/qwen2.5-0.5B-Instruct-DPO-5000 | Bmingg | 2025-05-27T04:45:00Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"llama-factory",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-05-27T04:44:26Z | ---
library_name: transformers
tags:
- llama-factory
---
# 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] |
NTIS/gemma3-1b-cpt-mixed-20250522-2-checkpoint-14655 | NTIS | 2025-05-27T04:43:33Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"gemma3_text",
"text-generation",
"pytorch",
"causal-lm",
"ko",
"en",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-05-27T04:38:35Z | ---
license: apache-2.0
language:
- ko
- en
tags:
- text-generation
- pytorch
- causal-lm
library_name: transformers
---
# gemma3-1b-cpt-mixed-20250522-2-checkpoint-14655
이 모델은 파인튜닝된 언어 모델 체크포인트입니다.
## 모델 정보
- **베이스 모델**: gemma3-1b-cpt-mixed-20250522-2
- **체크포인트**: checkpoint-14655
- **타입**: Causal Language Model
- **라이선스**: Apache 2.0
## 사용 방법
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model_name = "NTIS/gemma3-1b-cpt-mixed-20250522-2-checkpoint-14655"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype=torch.float16,
device_map="auto"
)
# 텍스트 생성
text = "안녕하세요"
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs, max_length=100, do_sample=True, temperature=0.7)
result = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(result)
```
## 주의사항
- 이 모델은 연구/실험 목적으로 제공됩니다
- 상업적 사용 전에 라이선스를 확인하세요
|
jacytong/CSCEC-QwQ-32B-LoRa-gguf | jacytong | 2025-05-27T04:40:41Z | 25 | 0 | null | [
"gguf",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
]
| null | 2025-05-19T09:19:56Z | ---
license: apache-2.0
---
|
thejaminator/medium_high-medical-2e-05-16000-mcq0-qwen3_32b | thejaminator | 2025-05-27T04:39:39Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"qwen3",
"trl",
"en",
"base_model:unsloth/Qwen3-32B",
"base_model:finetune:unsloth/Qwen3-32B",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2025-05-27T04:39:13Z | ---
base_model: unsloth/Qwen3-32B
tags:
- text-generation-inference
- transformers
- unsloth
- qwen3
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** thejaminator
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Qwen3-32B
This qwen3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
NTIS/gemma3-1b-cpt-mixed-20250522-2-checkpoint-14000 | NTIS | 2025-05-27T04:38:33Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"gemma3_text",
"text-generation",
"pytorch",
"causal-lm",
"ko",
"en",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-05-27T04:33:23Z | ---
license: apache-2.0
language:
- ko
- en
tags:
- text-generation
- pytorch
- causal-lm
library_name: transformers
---
# gemma3-1b-cpt-mixed-20250522-2-checkpoint-14000
이 모델은 파인튜닝된 언어 모델 체크포인트입니다.
## 모델 정보
- **베이스 모델**: gemma3-1b-cpt-mixed-20250522-2
- **체크포인트**: checkpoint-14000
- **타입**: Causal Language Model
- **라이선스**: Apache 2.0
## 사용 방법
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model_name = "NTIS/gemma3-1b-cpt-mixed-20250522-2-checkpoint-14000"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype=torch.float16,
device_map="auto"
)
# 텍스트 생성
text = "안녕하세요"
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs, max_length=100, do_sample=True, temperature=0.7)
result = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(result)
```
## 주의사항
- 이 모델은 연구/실험 목적으로 제공됩니다
- 상업적 사용 전에 라이선스를 확인하세요
|
mittswoodcut0p/katrina.lim.viral.kiffy.telegram.link.video | mittswoodcut0p | 2025-05-27T04:37:17Z | 0 | 0 | null | [
"region:us"
]
| null | 2025-05-27T04:35:42Z | <a href="https://lojinx.cfd/dgfyh"> 🌐 Click Here To link (katrina.lim.viral.kiffy.telegram.link.video)
🔴 ➤►DOWNLOAD👉👉🟢 ➤ <a href="https://lojinx.cfd/dgfyh"> 🌐 katrina.lim.viral.kiffy.telegram.link.video
|
thejaminator/tiny-medical-4e-05-16000-mcq0-qwen3_32b | thejaminator | 2025-05-27T04:35:51Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"qwen3",
"trl",
"en",
"base_model:unsloth/Qwen3-32B",
"base_model:finetune:unsloth/Qwen3-32B",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2025-05-27T04:35:46Z | ---
base_model: unsloth/Qwen3-32B
tags:
- text-generation-inference
- transformers
- unsloth
- qwen3
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** thejaminator
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Qwen3-32B
This qwen3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
NTIS/gemma3-1b-cpt-mixed-20250522-2-checkpoint-13000 | NTIS | 2025-05-27T04:33:21Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"gemma3_text",
"text-generation",
"pytorch",
"causal-lm",
"ko",
"en",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-05-27T04:28:10Z | ---
license: apache-2.0
language:
- ko
- en
tags:
- text-generation
- pytorch
- causal-lm
library_name: transformers
---
# gemma3-1b-cpt-mixed-20250522-2-checkpoint-13000
이 모델은 파인튜닝된 언어 모델 체크포인트입니다.
## 모델 정보
- **베이스 모델**: gemma3-1b-cpt-mixed-20250522-2
- **체크포인트**: checkpoint-13000
- **타입**: Causal Language Model
- **라이선스**: Apache 2.0
## 사용 방법
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model_name = "NTIS/gemma3-1b-cpt-mixed-20250522-2-checkpoint-13000"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype=torch.float16,
device_map="auto"
)
# 텍스트 생성
text = "안녕하세요"
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs, max_length=100, do_sample=True, temperature=0.7)
result = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(result)
```
## 주의사항
- 이 모델은 연구/실험 목적으로 제공됩니다
- 상업적 사용 전에 라이선스를 확인하세요
|
dhruvsangani/Multilingual-Sentiment-Analysis-GGUF | dhruvsangani | 2025-05-27T04:30:28Z | 0 | 0 | transformers | [
"transformers",
"gguf",
"llama",
"text-generation-inference",
"unsloth",
"en",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
]
| null | 2025-05-27T04:29:56Z | ---
base_model: unsloth/llama-3.2-1b-instruct-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- gguf
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** dhruvsangani
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3.2-1b-instruct-unsloth-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
John6666/luminarqmix-v7-noobaixl-illustriousxl-anime-style-merge-model-v70-base-with-out-lora-sdxl | John6666 | 2025-05-27T04:24:35Z | 0 | 0 | diffusers | [
"diffusers",
"safetensors",
"text-to-image",
"stable-diffusion",
"stable-diffusion-xl",
"anime",
"girls",
"cute",
"hands",
"human body",
"flatter shading",
"mature",
"merge",
"v-pred",
"Illustrious XL v2.0",
"illustrious",
"en",
"base_model:OnomaAIResearch/Illustrious-XL-v2.0",
"base_model:merge:OnomaAIResearch/Illustrious-XL-v2.0",
"base_model:cyberdelia/CyberIllustrious",
"base_model:merge:cyberdelia/CyberIllustrious",
"base_model:hybskgks28275/LuminarQMix",
"base_model:merge:hybskgks28275/LuminarQMix",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionXLPipeline",
"region:us"
]
| text-to-image | 2025-05-27T03:57:22Z | ---
license: other
license_name: faipl-1.0-sd
license_link: https://freedevproject.org/faipl-1.0-sd/
language:
- en
library_name: diffusers
pipeline_tag: text-to-image
tags:
- text-to-image
- stable-diffusion
- stable-diffusion-xl
- anime
- girls
- cute
- hands
- human body
- flatter shading
- mature
- merge
- v-pred
- Illustrious XL v2.0
- illustrious
base_model:
- hybskgks28275/LuminarQMix
- cyberdelia/CyberIllustrious
- OnomaAIResearch/Illustrious-XL-v2.0
---
Original model is [here](https://huggingface.co/hybskgks28275/LuminarQMix) and on [Civitai](https://civitai.com/models/1616309?modelVersionId=1837430).
The author is [here](https://huggingface.co/hybskgks28275)
This model created by [hybskgks28275](https://civitai.com/user/hybskgks28275).
|
djangodevloper/coctusmind-lite | djangodevloper | 2025-05-27T04:21:59Z | 0 | 0 | null | [
"pytorch",
"llama",
"llama-3",
"Mixtral",
"instruct",
"finetune",
"chatml",
"DPO",
"RLHF",
"gpt4",
"distillation",
"text-generation-inference",
"en",
"arxiv:2305.18290",
"arxiv:2303.13375",
"arxiv:2212.13138",
"arxiv:2305.09617",
"arxiv:2402.07023",
"base_model:meta-llama/Meta-Llama-3-8B",
"base_model:finetune:meta-llama/Meta-Llama-3-8B",
"license:llama3",
"region:us"
]
| null | 2025-05-27T03:49:21Z | ---
base_model: meta-llama/Meta-Llama-3-8B
tags:
- llama-3
- llama
- Mixtral
- instruct
- finetune
- chatml
- DPO
- RLHF
- gpt4
- distillation
- text-generation-inference
model-index:
- name: OpenBioLLM-8B
results: []
license: llama3
language:
- en
widget:
- example_title: OpenBioLLM-8B
messages:
- role: system
content: >-
You are an expert and experienced from the healthcare and biomedical
domain with extensive medical knowledge and practical experience.
- role: user
content: How long does it take for newborn jaundice to go away?
output:
text: >-
Newborn jaundice, also known as neonatal jaundice, is a common condition
in newborns where the yellowing of the skin and eyes occurs due to an
elevated level of bilirubin in the blood. Bilirubin is a yellow pigment
that forms when red blood cells break down. In most cases, newborn
jaundice resolves on its own without any specific treatment.
The duration of newborn jaundice can vary depending on several factors
such as the underlying cause, gestational age at birth, and individual
variations in bilirubin metabolism. Here are some general guidelines:
1. Physiological jaundice: This is the most common type of newborn
jaundice and usually appears within 24-72 hours after birth. It tends to
peak between the second and fifth day of life and gradually improves over
the next week or two. By the time the baby is one week old, the jaundice
should have mostly resolved. 2. Breast milk jaundice: This type of
jaundice occurs in breastfed babies and may appear later than
physiological jaundice, typically between the fifth and fourteenth day of
life. It tends to persist for a longer duration but usually resolves
within six weeks after birth. 3. Pathological jaundice: This type of
jaundice is less common and occurs due to an underlying medical condition
that affects bilirubin metabolism or liver function. The duration of
pathological jaundice depends on the specific cause and may require
treatment.
It's important for parents to monitor their newborn's jaundice closely and
seek medical advice if the jaundice progresses rapidly, becomes severe, or
is accompanied by other symptoms such as poor feeding, lethargy, or
excessive sleepiness. In these cases, further evaluation and management
may be necessary. Remember that each baby is unique, and the timing of
jaundice resolution can vary. If you have concerns about your newborn's
jaundice, it's always best to consult with a healthcare professional for
personalized advice and guidance.
---
Introducing OpenBioLLM-8B: A State-of-the-Art Open Source Biomedical Large Language Model
OpenBioLLM-8B is an advanced open source language model designed specifically for the biomedical domain. Developed by Saama AI Labs, this model leverages cutting-edge techniques to achieve state-of-the-art performance on a wide range of biomedical tasks.
🏥 **Biomedical Specialization**: OpenBioLLM-8B is tailored for the unique language and knowledge requirements of the medical and life sciences fields. It was fine-tuned on a vast corpus of high-quality biomedical data, enabling it to understand and generate text with domain-specific accuracy and fluency.
🎓 **Superior Performance**: With 8 billion parameters, OpenBioLLM-8B outperforms other open source biomedical language models of similar scale. It has also demonstrated better results compared to larger proprietary & open-source models like GPT-3.5 and Meditron-70B on biomedical benchmarks.
🧠 **Advanced Training Techniques**: OpenBioLLM-8B builds upon the powerful foundations of the **Meta-Llama-3-8B** and [Meta-Llama-3-8B](meta-llama/Meta-Llama-3-8B) models. It incorporates the DPO dataset and fine-tuning recipe along with a custom diverse medical instruction dataset. Key components of the training pipeline include:
- **Policy Optimization**: [Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)](https://arxiv.org/abs/2305.18290)
- **Ranking Dataset**: [berkeley-nest/Nectar](https://huggingface.co/datasets/berkeley-nest/Nectar)
- **Fine-tuning dataset**: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated)
This combination of cutting-edge techniques enables OpenBioLLM-8B to align with key capabilities and preferences for biomedical applications.
⚙️ **Release Details**:
- **Model Size**: 8 billion parameters
- **Quantization**: Optimized quantized versions available [Here](https://huggingface.co/aaditya/OpenBioLLM-Llama3-8B-GGUF)
- **Language(s) (NLP):** en
- **Developed By**: [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) from Saama AI Labs
- **License:** Meta-Llama License
- **Fine-tuned from models:** [meta-llama/Meta-Llama-3-8B](meta-llama/Meta-Llama-3-8B)
- **Resources for more information:**
- Paper: Coming soon
The model can be fine-tuned for more specialized tasks and datasets as needed.
OpenBioLLM-8B represents an important step forward in democratizing advanced language AI for the biomedical community. By leveraging state-of-the-art architectures and training techniques from leading open source efforts like Llama-3, we have created a powerful tool to accelerate innovation and discovery in healthcare and the life sciences.
We are excited to share OpenBioLLM-8B with researchers and developers around the world.
### Use with transformers
**Important: Please use the exact chat template provided by Llama-3 instruct version. Otherwise there will be a degradation in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less.**
See the snippet below for usage with Transformers:
```python
import transformers
import torch
model_id = "aaditya/OpenBioLLM-Llama3-8B"
pipeline = transformers.pipeline(
"text-generation",
model=model_id,
model_kwargs={"torch_dtype": torch.bfloat16},
device="auto",
)
messages = [
{"role": "system", "content": "You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience. Your name is OpenBioLLM, and you were developed by Saama AI Labs. who's willing to help answer the user's query with explanation. In your explanation, leverage your deep medical expertise such as relevant anatomical structures, physiological processes, diagnostic criteria, treatment guidelines, or other pertinent medical concepts. Use precise medical terminology while still aiming to make the explanation clear and accessible to a general audience."},
{"role": "user", "content": "How can i split a 3mg or 4mg waefin pill so i can get a 2.5mg pill?"},
]
prompt = pipeline.tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
terminators = [
pipeline.tokenizer.eos_token_id,
pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
]
outputs = pipeline(
prompt,
max_new_tokens=256,
eos_token_id=terminators,
do_sample=True,
temperature=0.0,
top_p=0.9,
)
print(outputs[0]["generated_text"][len(prompt):])
```
## **Training procedure**
### **Training hyperparameters**
<details>
<summary>Click to see details</summary>
- learning_rate: 0.0002
- lr_scheduler: cosine
- train_batch_size: 12
- eval_batch_size: 8
- GPU: H100 80GB SXM5
- num_devices: 1
- optimizer: adamw_bnb_8bit
- lr_scheduler_warmup_steps: 100
- num_epochs: 4
</details>
### **Peft hyperparameters**
<details>
<summary>Click to see details</summary>
- adapter: qlora
- lora_r: 128
- lora_alpha: 256
- lora_dropout: 0.05
- lora_target_linear: true
-lora_target_modules:
- q_proj
- v_proj
- k_proj
- o_proj
- gate_proj
- down_proj
- up_proj
</details>
### **Training results**
### **Framework versions**
- Transformers 4.39.3
- Pytorch 2.1.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.1
- Axolotl
- Lm harness for evaluation
# Benchmark Results
🔥 OpenBioLLM-8B demonstrates superior performance compared to larger models, such as GPT-3.5, Meditron-70B across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 72.50%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge.
🚨 The GPT-4, Med-PaLM-1, and Med-PaLM-2 results are taken from their official papers. Since Med-PaLM doesn't provide zero-shot accuracy, we are using 5-shot accuracy from their paper for comparison. All results presented are in the zero-shot setting, except for Med-PaLM-2 and Med-PaLM-1, which use 5-shot accuracy.
| | Clinical KG | Medical Genetics | Anatomy | Pro Medicine | College Biology | College Medicine | MedQA 4 opts | PubMedQA | MedMCQA | Avg |
|--------------------|-------------|------------------|---------|--------------|-----------------|------------------|--------------|----------|---------|-------|
| **OpenBioLLM-70B** | **92.93** | **93.197** | **83.904** | 93.75 | 93.827 | **85.749** | 78.162 | 78.97 | **74.014** | **86.05588** |
| Med-PaLM-2 (5-shot) | 88.3 | 90 | 77.8 | **95.2** | 94.4 | 80.9 | **79.7** | **79.2** | 71.3 | 84.08 |
| **GPT-4** | 86.04 | 91 | 80 | 93.01 | **95.14** | 76.88 | 78.87 | 75.2 | 69.52 | 82.85 |
| Med-PaLM-1 (Flan-PaLM, 5-shot) | 80.4 | 75 | 63.7 | 83.8 | 88.9 | 76.3 | 67.6 | 79 | 57.6 | 74.7 |
| **OpenBioLLM-8B** | 76.101 | 86.1 | 69.829 | 78.21 | 84.213 | 68.042 | 58.993 | 74.12 | 56.913 | 72.502 |
| Gemini-1.0 | 76.7 | 75.8 | 66.7 | 77.7 | 88 | 69.2 | 58 | 70.7 | 54.3 | 70.79 |
| GPT-3.5 Turbo 1106 | 74.71 | 74 | 72.79 | 72.79 | 72.91 | 64.73 | 57.71 | 72.66 | 53.79 | 66 |
| Meditron-70B | 66.79 | 69 | 53.33 | 71.69 | 76.38 | 63 | 57.1 | 76.6 | 46.85 | 64.52 |
| gemma-7b | 69.81 | 70 | 59.26 | 66.18 | 79.86 | 60.12 | 47.21 | 76.2 | 48.96 | 64.18 |
| Mistral-7B-v0.1 | 68.68 | 71 | 55.56 | 68.38 | 68.06 | 59.54 | 50.82 | 75.4 | 48.2 | 62.85 |
| Apollo-7B | 62.26 | 72 | 61.48 | 69.12 | 70.83 | 55.49 | 55.22 | 39.8 | 53.77 | 60 |
| MedAlpaca-7b | 57.36 | 69 | 57.04 | 67.28 | 65.28 | 54.34 | 41.71 | 72.8 | 37.51 | 58.03 |
| BioMistral-7B | 59.9 | 64 | 56.5 | 60.4 | 59 | 54.7 | 50.6 | 77.5 | 48.1 | 57.3 |
| AlpaCare-llama2-7b | 49.81 | 49 | 45.92 | 33.82 | 50 | 43.35 | 29.77 | 72.2 | 34.42 | 45.36 |
| ClinicalGPT | 30.56 | 27 | 30.37 | 19.48 | 25 | 24.27 | 26.08 | 63.8 | 28.18 | 30.52 |
<div align="center">
<img width="1600px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/_SzdcJSBjZyo8RS1bTEkP.png">
</div>
## Detailed Medical Subjectwise accuracy
# Use Cases & Examples
🚨 **Below results are from the quantized version of OpenBioLLM-70B**
# Summarize Clinical Notes
OpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries
# Answer Medical Questions
OpenBioLLM-70B can provide answers to a wide range of medical questions.
<details>
<summary>Click to see details</summary>
</details>
# Clinical Entity Recognition
OpenBioLLM-70B can perform advanced clinical entity recognition by identifying and extracting key medical concepts, such as diseases, symptoms, medications, procedures, and anatomical structures, from unstructured clinical text. By leveraging its deep understanding of medical terminology and context, the model can accurately annotate and categorize clinical entities, enabling more efficient information retrieval, data analysis, and knowledge discovery from electronic health records, research articles, and other biomedical text sources. This capability can support various downstream applications, such as clinical decision support, pharmacovigilance, and medical research.
# Biomarkers Extraction
# Classification
OpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization
# De-Identification
OpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA.
**Advisory Notice!**
While OpenBioLLM-70B & 8B leverages high-quality data sources, its outputs may still contain inaccuracies, biases, or misalignments that could pose risks if relied upon for medical decision-making without further testing and refinement. The model's performance has not yet been rigorously evaluated in randomized controlled trials or real-world healthcare environments.
Therefore, we strongly advise against using OpenBioLLM-70B & 8B for any direct patient care, clinical decision support, or other professional medical purposes at this time. Its use should be limited to research, development, and exploratory applications by qualified individuals who understand its limitations.
OpenBioLLM-70B & 8B are intended solely as a research tool to assist healthcare professionals and should never be considered a replacement for the professional judgment and expertise of a qualified medical doctor.
Appropriately adapting and validating OpenBioLLM-70B & 8B for specific medical use cases would require significant additional work, potentially including:
- Thorough testing and evaluation in relevant clinical scenarios
- Alignment with evidence-based guidelines and best practices
- Mitigation of potential biases and failure modes
- Integration with human oversight and interpretation
- Compliance with regulatory and ethical standards
Always consult a qualified healthcare provider for personal medical needs.
# Citation
We thank the [Meta Team](meta-llama/Meta-Llama-3-70B-Instruct) for their amazing models!
Result sources
- [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (https://arxiv.org/abs/2303.13375)
- [2] Med-PaLM-1 [Large Language Models Encode Clinical Knowledge](https://arxiv.org/abs/2212.13138)
- [3] Med-PaLM-2 [Towards Expert-Level Medical Question Answering with Large Language Models](https://arxiv.org/abs/2305.09617)
- [4] Gemini-1.0 [Gemini Goes to Med School](https://arxiv.org/abs/2402.07023) |
hlhs211/0527test | hlhs211 | 2025-05-27T04:19:53Z | 0 | 0 | null | [
"license:apache-2.0",
"region:us"
]
| null | 2025-05-27T04:19:53Z | ---
license: apache-2.0
---
|
SilentHillFan/trash-clasiffier-biodegradable | SilentHillFan | 2025-05-27T04:17:15Z | 87 | 0 | null | [
"tensorboard",
"safetensors",
"vit",
"dataset:edwinpalegre/trashnet_enhanced",
"base_model:tribber93/my-trash-classification",
"base_model:finetune:tribber93/my-trash-classification",
"region:us"
]
| null | 2025-04-16T21:58:11Z | ---
datasets:
- edwinpalegre/trashnet_enhanced
base_model:
- tribber93/my-trash-classification
---
I did this for a school project, it took me like 26 hours to complete because i needed the biodegradable option so, i hope somebody fids it useful i guess, to be honest i have no idea what moste of this things mean but in my python code says an image of a tomatoe is biodegrdable so it works!!!!
quick update, i did win as best project at my university :D!! (i changed something here idk why it shows like this god im so bad at this)
---
thanks for those two people for his model and dataset, ill let u know if i win my university contest!
# Model Trained Using AutoTrain
- Problem type: Image Classification
## Validation Metrics
No validation metrics available |
allura-forge/q3-8b-ft-adpt-ep2 | allura-forge | 2025-05-27T04:08:19Z | 0 | 0 | peft | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:Qwen/Qwen3-8B-Base",
"base_model:adapter:Qwen/Qwen3-8B-Base",
"region:us"
]
| null | 2025-05-27T04:06:25Z | ---
base_model: Qwen/Qwen3-8B-Base
library_name: peft
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.15.2 |
Ruthwik/LExiMinD_legal_t5_summarizer | Ruthwik | 2025-05-27T04:00:47Z | 76 | 0 | null | [
"safetensors",
"t5",
"summarization",
"legal",
"en",
"dataset:legal_contracts_dataset",
"license:apache-2.0",
"region:us"
]
| summarization | 2025-04-05T03:22:50Z | ---
tags:
- t5
- summarization
- legal
pipeline_tag: summarization
license: apache-2.0
inference: true
model-id: Ruthwik/LExiMinD_legal_t5_summarizer
language: en
datasets:
- legal_contracts_dataset # Replace with actual dataset name if applicable
---
# LExiMinD Legal T5 Summarizer
A T5-based model fine-tuned for summarizing legal documents, designed to produce concise and accurate summaries of contracts, agreements, and other legal texts.
## Model Details
- **Architecture**: T5 (Text-to-Text Transfer Transformer)
- **Training Data**: Fine-tuned on a dataset of legal documents (e.g., contracts, case law) [replace with specific dataset details if available].
- **Language**: English
- **License**: Apache 2.0
## Usage
This model can be used for summarizing legal texts via the Hugging Face Inference API or locally with the Transformers library.
### Using the Hugging Face Inference API
To use the model via the Inference API, you need a Hugging Face API token. Get one from [your Hugging Face account settings](https://huggingface.co/settings/tokens).
Example with Python `huggingface_hub`:
```python
from huggingface_hub import InferenceClient
client = InferenceClient(model="Ruthwik/LExiMinD_legal_t5_summarizer", token="YOUR_HF_TOKEN")
text = "This agreement, entered into on January 1, 2025, between Party A and Party B, outlines the terms for the provision of services..."
summary = client.summarization(text, max_length=200, min_length=75)
print(summary) |
nnilayy/deap-valence-binary-classification-no-wd-Kfold-2 | nnilayy | 2025-05-27T03:58:57Z | 0 | 0 | null | [
"safetensors",
"model_hub_mixin",
"pytorch_model_hub_mixin",
"region:us"
]
| null | 2025-05-27T03:58:55Z | ---
tags:
- model_hub_mixin
- pytorch_model_hub_mixin
---
This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
- Code: [More Information Needed]
- Paper: [More Information Needed]
- Docs: [More Information Needed] |
lisabdunlap/Qwen3-8B-base-pt-sft_e3 | lisabdunlap | 2025-05-27T03:58:17Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"qwen3",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"en",
"base_model:unsloth/Qwen3-8B-Base",
"base_model:finetune:unsloth/Qwen3-8B-Base",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-05-27T01:48:34Z | ---
base_model: unsloth/Qwen3-8B-Base
tags:
- text-generation-inference
- transformers
- unsloth
- qwen3
- trl
- sft
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** lisabdunlap
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Qwen3-8B-Base
This qwen3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
lisabdunlap/Qwen3-8B-base-pt-5e5_e2 | lisabdunlap | 2025-05-27T03:56:33Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"qwen3",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"en",
"base_model:unsloth/Qwen3-8B-Base",
"base_model:finetune:unsloth/Qwen3-8B-Base",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-05-27T03:55:40Z | ---
base_model: unsloth/Qwen3-8B-Base
tags:
- text-generation-inference
- transformers
- unsloth
- qwen3
- trl
- sft
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** lisabdunlap
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Qwen3-8B-Base
This qwen3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
mlx-community/sarvam-m-4bit | mlx-community | 2025-05-27T00:36:52Z | 0 | 0 | mlx | [
"mlx",
"safetensors",
"mistral",
"text-generation",
"conversational",
"en",
"bn",
"hi",
"kn",
"gu",
"mr",
"ml",
"or",
"pa",
"ta",
"te",
"base_model:sarvamai/sarvam-m",
"base_model:finetune:sarvamai/sarvam-m",
"license:apache-2.0",
"4-bit",
"region:us"
]
| text-generation | 2025-05-27T00:35:59Z | ---
library_name: mlx
license: apache-2.0
language:
- en
- bn
- hi
- kn
- gu
- mr
- ml
- or
- pa
- ta
- te
base_model: sarvamai/sarvam-m
base_model_relation: finetune
pipeline_tag: text-generation
tags:
- mlx
---
# mlx-community/sarvam-m-4bit
This model [mlx-community/sarvam-m-4bit](https://huggingface.co/mlx-community/sarvam-m-4bit) was
converted to MLX format from [sarvamai/sarvam-m](https://huggingface.co/sarvamai/sarvam-m)
using mlx-lm version **0.24.1**.
## Use with mlx
```bash
pip install mlx-lm
```
```python
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/sarvam-m-4bit")
prompt = "hello"
if tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)
```
|
bigband/LuminousSif | bigband | 2025-05-27T00:36:03Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"gemma3",
"image-text-to-text",
"gemma",
"google",
"Bifröst",
"Bifrost",
"code",
"text-generation",
"conversational",
"base_model:google/gemma-3-27b-it",
"base_model:finetune:google/gemma-3-27b-it",
"license:gemma",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-05-27T00:28:00Z | ---
license: gemma
library_name: transformers
pipeline_tag: text-generation
extra_gated_heading: Access Gemma on Hugging Face
extra_gated_prompt: >-
To access Gemma on Hugging Face, you’re required to review and agree to
Google’s usage license. To do this, please ensure you’re logged in to Hugging
Face and click below. Requests are processed immediately.
extra_gated_button_content: Acknowledge license
base_model: google/gemma-3-27b-it
tags:
- transformers
- gemma3
- gemma
- google
- Bifröst
- Bifrost
- code
---
## Bifröst-27B
Bifröst-27B is an advanced AI model built upon gemma3 architecture, specifically fine-tuned for secure and efficient enterprise-grade code generation with reasoning. Designed to meet rigorous standards of safety, accuracy, and reliability, Bifröst empowers organizations to streamline software development workflows while prioritizing security and compliance.
### Model Details
- **Model Name:** Bifröst-27B
- **Base Architecture:** gemma3
- **Application:** Enterprise Secure Code Generation
- **Release Date:** 16-March-2025
### Intended Use
Bifröst is designed explicitly for:
- Generating secure, efficient, and high-quality code.
- Supporting development tasks within regulated enterprise environments.
- Enhancing productivity by automating routine coding tasks without compromising security.
### Features
- **Security-Focused Training:** Specialized training regimen emphasizing secure coding practices, vulnerability reduction, and adherence to security standards.
- **Enterprise-Optimized Performance:** Tailored to support various programming languages and enterprise frameworks with robust, context-aware suggestions.
- **Compliance-Driven Design:** Incorporates features to aid in maintaining compliance with industry-specific standards (e.g., GDPR, HIPAA, SOC 2).
### Limitations
- Bifröst should be used under human supervision to ensure code correctness and security compliance.
- Model-generated code should undergo appropriate security and quality assurance checks before deployment.
### Ethical Considerations
- Users are encouraged to perform regular audits and compliance checks on generated outputs.
- Enterprises should implement responsible AI practices to mitigate biases or unintended consequences.
### Usage
Below are some quick-start instructions for using the model with the `transformers` library.
#### Installation
```sh
$ pip install git+https://github.com/huggingface/[email protected]
```
#### Running with the `pipeline` API
```python
from transformers import pipeline
import torch
pipe = pipeline(
"text-generation",
model="OpenGenerativeAI/Bifrost-27B",
device="cuda",
torch_dtype=torch.bfloat16
)
messages = [{"role": "user", "content": "Generate a secure API key management system."}]
output = pipe(text=messages, max_new_tokens=200)
print(output[0]["generated_text"])
```
## Terms of Use
This model is released under the **Gemma license**. Users must comply with [Google's Gemma Terms of Use](https://ai.google.dev/gemma/terms), including restrictions on redistribution, modification, and commercial use. |
Docty/dreambooth-gingarun | Docty | 2025-05-27T00:27:56Z | 0 | 0 | diffusers | [
"diffusers",
"tensorboard",
"safetensors",
"text-to-image",
"dreambooth",
"diffusers-training",
"stable-diffusion",
"stable-diffusion-diffusers",
"base_model:stable-diffusion-v1-5/stable-diffusion-v1-5",
"base_model:finetune:stable-diffusion-v1-5/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
]
| text-to-image | 2025-05-27T00:14:45Z | ---
base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
library_name: diffusers
license: creativeml-openrail-m
inference: true
instance_prompt: gingarun very dark skin chocolate black woman with big breasts, full
lips, big butt, at park, braids, floral dress, side view, deep cleavage, smiling,
looking straight, busty, 21 years old
tags:
- text-to-image
- dreambooth
- diffusers-training
- stable-diffusion
- stable-diffusion-diffusers
---
<!-- This model card has been generated automatically according to the information the training script had access to. You
should probably proofread and complete it, then remove this comment. -->
# DreamBooth - Docty/dreambooth-gingarun
This is a dreambooth model derived from stable-diffusion-v1-5/stable-diffusion-v1-5. The weights were trained on gingarun very dark skin chocolate black woman with big breasts, full lips, big butt, at park, braids, floral dress, side view, deep cleavage, smiling, looking straight, busty, 21 years old using [DreamBooth](https://dreambooth.github.io/).
You can find some example images in the following.
DreamBooth for the text encoder was enabled: False.
## Intended uses & limitations
#### How to use
```python
# TODO: add an example code snippet for running this diffusion pipeline
```
#### Limitations and bias
[TODO: provide examples of latent issues and potential remediations]
## Training details
[TODO: describe the data used to train the model] |
lisabdunlap/Qwen3-8B-base-cpt-5-few-shot | lisabdunlap | 2025-05-27T00:24:38Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"qwen3",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"en",
"base_model:unsloth/Qwen3-8B-Base",
"base_model:finetune:unsloth/Qwen3-8B-Base",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-05-27T00:23:47Z | ---
base_model: unsloth/Qwen3-8B-Base
tags:
- text-generation-inference
- transformers
- unsloth
- qwen3
- trl
- sft
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** lisabdunlap
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Qwen3-8B-Base
This qwen3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
FormlessAI/89320db8-9b2d-4617-9954-81490e404acb | FormlessAI | 2025-05-27T00:23:37Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"bloom",
"text-generation",
"generated_from_trainer",
"trl",
"grpo",
"arxiv:2402.03300",
"base_model:bigscience/bloomz-560m",
"base_model:finetune:bigscience/bloomz-560m",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-05-26T23:52:42Z | ---
base_model: bigscience/bloomz-560m
library_name: transformers
model_name: 89320db8-9b2d-4617-9954-81490e404acb
tags:
- generated_from_trainer
- trl
- grpo
licence: license
---
# Model Card for 89320db8-9b2d-4617-9954-81490e404acb
This model is a fine-tuned version of [bigscience/bloomz-560m](https://huggingface.co/bigscience/bloomz-560m).
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="FormlessAI/89320db8-9b2d-4617-9954-81490e404acb", 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/phoenix-formless/Gradients/runs/fp19kz5m)
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: 0.17.0
- Transformers: 4.52.3
- Pytorch: 2.7.0+cu128
- Datasets: 3.6.0
- 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}}
}
``` |
nnilayy/deap-arousal-binary-classification-no-ls-Kfold-3 | nnilayy | 2025-05-27T00:22:41Z | 0 | 0 | null | [
"safetensors",
"model_hub_mixin",
"pytorch_model_hub_mixin",
"region:us"
]
| null | 2025-05-27T00:22:40Z | ---
tags:
- model_hub_mixin
- pytorch_model_hub_mixin
---
This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
- Code: [More Information Needed]
- Paper: [More Information Needed]
- Docs: [More Information Needed] |
bigband/SacredSaga | bigband | 2025-05-27T00:06:41Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"gemma3",
"image-text-to-text",
"gemma",
"google",
"Bifröst",
"Bifrost",
"code",
"text-generation",
"conversational",
"base_model:google/gemma-3-27b-it",
"base_model:finetune:google/gemma-3-27b-it",
"license:gemma",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-05-26T23:57:00Z | ---
license: gemma
library_name: transformers
pipeline_tag: text-generation
extra_gated_heading: Access Gemma on Hugging Face
extra_gated_prompt: >-
To access Gemma on Hugging Face, you’re required to review and agree to
Google’s usage license. To do this, please ensure you’re logged in to Hugging
Face and click below. Requests are processed immediately.
extra_gated_button_content: Acknowledge license
base_model: google/gemma-3-27b-it
tags:
- transformers
- gemma3
- gemma
- google
- Bifröst
- Bifrost
- code
---
## Bifröst-27B
Bifröst-27B is an advanced AI model built upon gemma3 architecture, specifically fine-tuned for secure and efficient enterprise-grade code generation with reasoning. Designed to meet rigorous standards of safety, accuracy, and reliability, Bifröst empowers organizations to streamline software development workflows while prioritizing security and compliance.
### Model Details
- **Model Name:** Bifröst-27B
- **Base Architecture:** gemma3
- **Application:** Enterprise Secure Code Generation
- **Release Date:** 16-March-2025
### Intended Use
Bifröst is designed explicitly for:
- Generating secure, efficient, and high-quality code.
- Supporting development tasks within regulated enterprise environments.
- Enhancing productivity by automating routine coding tasks without compromising security.
### Features
- **Security-Focused Training:** Specialized training regimen emphasizing secure coding practices, vulnerability reduction, and adherence to security standards.
- **Enterprise-Optimized Performance:** Tailored to support various programming languages and enterprise frameworks with robust, context-aware suggestions.
- **Compliance-Driven Design:** Incorporates features to aid in maintaining compliance with industry-specific standards (e.g., GDPR, HIPAA, SOC 2).
### Limitations
- Bifröst should be used under human supervision to ensure code correctness and security compliance.
- Model-generated code should undergo appropriate security and quality assurance checks before deployment.
### Ethical Considerations
- Users are encouraged to perform regular audits and compliance checks on generated outputs.
- Enterprises should implement responsible AI practices to mitigate biases or unintended consequences.
### Usage
Below are some quick-start instructions for using the model with the `transformers` library.
#### Installation
```sh
$ pip install git+https://github.com/huggingface/[email protected]
```
#### Running with the `pipeline` API
```python
from transformers import pipeline
import torch
pipe = pipeline(
"text-generation",
model="OpenGenerativeAI/Bifrost-27B",
device="cuda",
torch_dtype=torch.bfloat16
)
messages = [{"role": "user", "content": "Generate a secure API key management system."}]
output = pipe(text=messages, max_new_tokens=200)
print(output[0]["generated_text"])
```
## Terms of Use
This model is released under the **Gemma license**. Users must comply with [Google's Gemma Terms of Use](https://ai.google.dev/gemma/terms), including restrictions on redistribution, modification, and commercial use. |
lsalsi/overlap_logan_ewc_5_2kb | lsalsi | 2025-05-27T00:06:35Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"esm",
"fill-mask",
"custom_code",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| fill-mask | 2025-05-26T22:38:55Z | ---
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] |
nmndeep/20250526T215524 | nmndeep | 2025-05-27T00:01:39Z | 0 | 0 | null | [
"safetensors",
"mistral",
"generated_from_trainer",
"base_model:HuggingFaceH4/zephyr-7b-beta",
"base_model:finetune:HuggingFaceH4/zephyr-7b-beta",
"license:mit",
"region:us"
]
| null | 2025-05-26T23:58:18Z | ---
license: mit
base_model: HuggingFaceH4/zephyr-7b-beta
tags:
- generated_from_trainer
model-index:
- name: 20250526T215524
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/nmndeep/huggingface/runs/qo6nzsgh)
# 20250526T215524
This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-07
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 8
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 150
- num_epochs: 3.0
### Training results
### Framework versions
- Transformers 4.41.0
- Pytorch 2.3.1.post300
- Datasets 3.6.0
- Tokenizers 0.19.1
|
VIDEO-18-Katrina-Lim-Viral-VIDEOS/FULL.VIDEO.LINK.Katrina.Lim.Viral.Video.Leaks.Official | VIDEO-18-Katrina-Lim-Viral-VIDEOS | 2025-05-27T00:00:07Z | 0 | 0 | null | [
"region:us"
]
| null | 2025-05-26T23:59:42Z | <a href="https://mswds.xyz/full-video/?v=Katrina.Lim" rel="nofollow">🔴 ➤►𝐂𝐥𝐢𝐤 𝐇𝐞𝐫𝐞 𝐭𝐨👉👉 (𝐖𝐚𝐭𝐜𝐡 𝐅𝐮𝐥𝐥 𝐯𝐢𝐝𝐞𝐨)</a>
<a href="https://mswds.xyz/full-video/?v=Katrina.Lim" rel="nofollow">🔴 ➤►𝐂𝐥𝐢𝐤 𝐇𝐞𝐫𝐞 𝐭𝐨👉👉 (𝐅𝐮𝐥𝐥 Viral 𝐯𝐢𝐝𝐞𝐨 𝐋𝐢𝐧𝐤 )</a>
<a href="https://mswds.xyz/full-video/?v=Katrina.Lim"><img src="https://i.postimg.cc/qvPp49Sm/ythngythg.gif" alt="fsgd" /></a>
|
Dhanush66/Antismetisim-finetuned-MLM-NEW-05-26 | Dhanush66 | 2025-05-26T23:59:00Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"bert",
"fill-mask",
"generated_from_trainer",
"base_model:google-bert/bert-base-uncased",
"base_model:finetune:google-bert/bert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| fill-mask | 2025-05-26T19:10:39Z | ---
library_name: transformers
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
model-index:
- name: Antismetisim-finetuned-MLM-NEW-05-26
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. -->
# Antismetisim-finetuned-MLM-NEW-05-26
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 7.4688
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.001
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 1.0 | 1586 | 7.4898 |
| 7.4987 | 2.0 | 3172 | 7.4766 |
| 7.4987 | 3.0 | 4758 | 7.4736 |
### Framework versions
- Transformers 4.49.0
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.0
|
nnilayy/deap-valence-binary-classification-no-ls-Kfold-2 | nnilayy | 2025-05-26T23:57:54Z | 0 | 0 | null | [
"safetensors",
"model_hub_mixin",
"pytorch_model_hub_mixin",
"region:us"
]
| null | 2025-05-26T23:57:51Z | ---
tags:
- model_hub_mixin
- pytorch_model_hub_mixin
---
This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
- Code: [More Information Needed]
- Paper: [More Information Needed]
- Docs: [More Information Needed] |
DavidAU/MN-WORDSTORM-pt10-RCM-Sway-And-Thud-18.5B-Instruct | DavidAU | 2025-05-26T23:56:47Z | 11 | 1 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"mergekit",
"merge",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2024-11-01T06:41:37Z | ---
library_name: transformers
tags:
- mergekit
- merge
base_model: []
---
<h2>MN-WORDSTORM-pt10-RCM-Sway-And-Thud-18.5B-Instruct</h2>
This is part 10 in a 10 part series.
This version's highlights (relative to others in this 10 part series):
"Model focuses on the moment / immediate surroundings, has a dark bias, and will often end on a cliffhanger (scene gen). Uses 'sound' words too."
(PPL = 7.7794 +/- 0.12679 @ Q4KM)
<B>IMPORTANT: Highest Quality Settings / Optimal Operation Guide / Parameters and Samplers</B>
If you are going to use this model, (source, GGUF or a different quant), please review this document for critical parameter, sampler and advance sampler settings (for multiple AI/LLM aps).
This a "Class 2" (settings will enhance operation / optional adjustments) :
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) (especially for use case(s) beyond the model's design) please see:
[ https://huggingface.co/DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters ]
REASON:
Regardless of "model class" this document will detail methods to enhance operations.
If the model is a Class 3/4 model the default settings (parameters, samplers, advanced samplers) must be set for "use case(s)" uses correctly. Some AI/LLM apps DO NOT have consistant default setting(s) which result in sub-par model operation. Like wise for Class 3/4 models (which operate somewhat to very differently than standard models) additional samplers and advanced samplers settings are required to "smooth out" operation, AND/OR also allow full operation for use cases the model was not designed for.
BONUS - Use these settings for ANY model, ANY repo, ANY quant (including source/full precision):
This document also details parameters, sampler and advanced samplers that can be use FOR ANY MODEL, FROM ANY REPO too - all quants, and of course source code operation too - to enhance the operation of any model.
[ https://huggingface.co/DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters ]
NOTE:
I strongly suggest you also visit the DavidAU GGUF (below) repo too for more details in using this model ; especially if it is "Class 3" or "Class 4" to get maximum performance from the model.
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.
For full information about this model, including:
- Details about this model and its use case(s).
- Context limits
- Special usage notes / settings.
- Any model(s) used to create this model.
- Template(s) used to access/use this model.
- Example generation(s)
- GGUF quants of this model
GGUF Quants:
[ https://huggingface.co/mradermacher/MN-WORDSTORM-pt10-RCM-Sway-And-Thud-18.5B-Instruct-GGUF ]
Imatrix Ggufs:
[ https://huggingface.co/mradermacher/MN-WORDSTORM-pt10-RCM-Sway-And-Thud-18.5B-Instruct-i1-GGUF ]
Settings, Templates, Context limits etc etc are the same for all 10 in the series, you can view
any below for "part 10's" information.
Also, each of the 5 below include example generations which will indicate in part this "parts" generation abilities. However
there will be variations which is what this 10 parts series is really all about.
For more information on this 10 part series see one or more of these versions:
[ https://huggingface.co/DavidAU/MN-WORDSTORM-pt1-RCM-Kiss-of-Madness-18.5B-Instruct-GGUF ]
[ https://huggingface.co/DavidAU/MN-WORDSTORM-pt2-RCM-Escape-Room-18.5B-Instruct-GGUF ]
[ https://huggingface.co/DavidAU/MN-WORDSTORM-pt3-RCM-POV-Nightmare-18.5B-Instruct-GGUF ]
[ https://huggingface.co/DavidAU/MN-WORDSTORM-pt4-RCM-Cliffhanger-18.5B-Instruct-GGUF ]
[ https://huggingface.co/DavidAU/MN-WORDSTORM-pt5-RCM-Extra-Intense-18.5B-Instruct-gguf ]
|
lsalsi/overlap_logan_ewc_25 | lsalsi | 2025-05-26T23:48:14Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"esm",
"fill-mask",
"custom_code",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| fill-mask | 2025-05-26T22:38:53Z | ---
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] |
RasmusVeski/MNLP_M2_quantized_model | RasmusVeski | 2025-05-26T23:48:13Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"qwen3",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-05-26T23:46:20Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
WaveCut/QwenLong-L1-32B-mlx-8Bit | WaveCut | 2025-05-26T23:45:39Z | 0 | 0 | mlx | [
"mlx",
"safetensors",
"qwen2",
"long-context",
"large-reasoning-model",
"mlx-my-repo",
"dataset:Tongyi-Zhiwen/DocQA-RL-1.6K",
"base_model:Tongyi-Zhiwen/QwenLong-L1-32B",
"base_model:quantized:Tongyi-Zhiwen/QwenLong-L1-32B",
"license:apache-2.0",
"8-bit",
"region:us"
]
| null | 2025-05-26T23:44:05Z | ---
license: apache-2.0
datasets:
- Tongyi-Zhiwen/DocQA-RL-1.6K
base_model: Tongyi-Zhiwen/QwenLong-L1-32B
tags:
- long-context
- large-reasoning-model
- mlx
- mlx-my-repo
---
# WaveCut/QwenLong-L1-32B-mlx-8Bit
The Model [WaveCut/QwenLong-L1-32B-mlx-8Bit](https://huggingface.co/WaveCut/QwenLong-L1-32B-mlx-8Bit) was converted to MLX format from [Tongyi-Zhiwen/QwenLong-L1-32B](https://huggingface.co/Tongyi-Zhiwen/QwenLong-L1-32B) using mlx-lm version **0.22.3**.
## Use with mlx
```bash
pip install mlx-lm
```
```python
from mlx_lm import load, generate
model, tokenizer = load("WaveCut/QwenLong-L1-32B-mlx-8Bit")
prompt="hello"
if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, tokenize=False, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)
```
|
lsalsi/overlap_logan_ewc_5 | lsalsi | 2025-05-26T23:39:46Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"esm",
"fill-mask",
"custom_code",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| fill-mask | 2025-05-26T22:38:53Z | ---
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] |
Smashthelikebros/Qwen2.5-1.5B-Instruct-Gensyn-Swarm-tall_scented_alligator | Smashthelikebros | 2025-05-26T23:39:27Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"generated_from_trainer",
"rl-swarm",
"grpo",
"gensyn",
"I am tall scented alligator",
"unsloth",
"trl",
"arxiv:2402.03300",
"base_model:Gensyn/Qwen2.5-1.5B-Instruct",
"base_model:finetune:Gensyn/Qwen2.5-1.5B-Instruct",
"endpoints_compatible",
"region:us"
]
| null | 2025-05-25T23:23:56Z | ---
base_model: Gensyn/Qwen2.5-1.5B-Instruct
library_name: transformers
model_name: Qwen2.5-1.5B-Instruct-Gensyn-Swarm-tall_scented_alligator
tags:
- generated_from_trainer
- rl-swarm
- grpo
- gensyn
- I am tall scented alligator
- unsloth
- trl
licence: license
---
# Model Card for Qwen2.5-1.5B-Instruct-Gensyn-Swarm-tall_scented_alligator
This model is a fine-tuned version of [Gensyn/Qwen2.5-1.5B-Instruct](https://huggingface.co/Gensyn/Qwen2.5-1.5B-Instruct).
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="Smashthelikebros/Qwen2.5-1.5B-Instruct-Gensyn-Swarm-tall_scented_alligator", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
### Framework versions
- TRL: 0.15.2
- Transformers: 4.51.3
- Pytorch: 2.5.1
- Datasets: 3.6.0
- Tokenizers: 0.21.1
## Citations
Cite GRPO as:
```bibtex
@article{zhihong2024deepseekmath,
title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
year = 2024,
eprint = {arXiv:2402.03300},
}
```
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
``` |
Santiagoescamilla/gabomockups | Santiagoescamilla | 2025-05-26T23:37:37Z | 0 | 0 | diffusers | [
"diffusers",
"flux",
"lora",
"replicate",
"text-to-image",
"en",
"base_model:black-forest-labs/FLUX.1-dev",
"base_model:adapter:black-forest-labs/FLUX.1-dev",
"license:other",
"region:us"
]
| text-to-image | 2025-05-26T23:00:55Z | ---
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
language:
- en
tags:
- flux
- diffusers
- lora
- replicate
base_model: "black-forest-labs/FLUX.1-dev"
pipeline_tag: text-to-image
# widget:
# - text: >-
# prompt
# output:
# url: https://...
instance_prompt: gabomockups
---
# Gabomockups
<Gallery />
## About this LoRA
This is a [LoRA](https://replicate.com/docs/guides/working-with-loras) for the FLUX.1-dev text-to-image model. It can be used with diffusers or ComfyUI.
It was trained on [Replicate](https://replicate.com/) using AI toolkit: https://replicate.com/ostris/flux-dev-lora-trainer/train
## Trigger words
You should use `gabomockups` to trigger the image generation.
## Run this LoRA with an API using Replicate
```py
import replicate
input = {
"prompt": "gabomockups",
"lora_weights": "https://huggingface.co/Santiagoescamilla/gabomockups/resolve/main/lora.safetensors"
}
output = replicate.run(
"black-forest-labs/flux-dev-lora",
input=input
)
for index, item in enumerate(output):
with open(f"output_{index}.webp", "wb") as file:
file.write(item.read())
```
## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
```py
from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('Santiagoescamilla/gabomockups', weight_name='lora.safetensors')
image = pipeline('gabomockups').images[0]
```
For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
## Training details
- Steps: 1250
- Learning rate: 0.0004
- LoRA rank: 16
## Contribute your own examples
You can use the [community tab](https://huggingface.co/Santiagoescamilla/gabomockups/discussions) to add images that show off what you’ve made with this LoRA.
|
huhuf/Riku | huhuf | 2025-05-26T23:32:20Z | 0 | 0 | null | [
"license:creativeml-openrail-m",
"region:us"
]
| null | 2025-05-26T23:32:20Z | ---
license: creativeml-openrail-m
---
|
Dev6205/Babu | Dev6205 | 2025-05-26T23:24:02Z | 0 | 0 | null | [
"license:apache-2.0",
"region:us"
]
| null | 2025-05-26T23:24:02Z | ---
license: apache-2.0
---
|
Querodon/dqn-SpaceInvadersNoFrameskip-v4 | Querodon | 2025-05-26T23:22:29Z | 0 | 0 | stable-baselines3 | [
"stable-baselines3",
"SpaceInvadersNoFrameskip-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
]
| reinforcement-learning | 2025-05-26T22:10:32Z | ---
library_name: stable-baselines3
tags:
- SpaceInvadersNoFrameskip-v4
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: DQN
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: SpaceInvadersNoFrameskip-v4
type: SpaceInvadersNoFrameskip-v4
metrics:
- type: mean_reward
value: 329.00 +/- 157.97
name: mean_reward
verified: false
---
# **DQN** Agent playing **SpaceInvadersNoFrameskip-v4**
This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
The RL Zoo is a training framework for Stable Baselines3
reinforcement learning agents,
with hyperparameter optimization and pre-trained agents included.
## Usage (with SB3 RL Zoo)
RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
SB3: https://github.com/DLR-RM/stable-baselines3<br/>
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
SBX (SB3 + Jax): https://github.com/araffin/sbx
Install the RL Zoo (with SB3 and SB3-Contrib):
```bash
pip install rl_zoo3
```
```
# Download model and save it into the logs/ folder
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga Querodon -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
```
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga Querodon -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
## Training (with the RL Zoo)
```
python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga Querodon
```
## Hyperparameters
```python
OrderedDict([('batch_size', 32),
('buffer_size', 100000),
('env_wrapper',
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
('exploration_final_eps', 0.01),
('exploration_fraction', 0.1),
('frame_stack', 4),
('gradient_steps', 1),
('learning_rate', 0.0001),
('learning_starts', 100000),
('n_timesteps', 100000.0),
('optimize_memory_usage', False),
('policy', 'CnnPolicy'),
('target_update_interval', 1000),
('train_freq', 4),
('normalize', False)])
```
# Environment Arguments
```python
{'render_mode': 'rgb_array'}
```
|
WaveCut/QwenLong-L1-32B-mlx-4Bit | WaveCut | 2025-05-26T23:21:36Z | 0 | 0 | mlx | [
"mlx",
"safetensors",
"qwen2",
"long-context",
"large-reasoning-model",
"mlx-my-repo",
"dataset:Tongyi-Zhiwen/DocQA-RL-1.6K",
"base_model:Tongyi-Zhiwen/QwenLong-L1-32B",
"base_model:quantized:Tongyi-Zhiwen/QwenLong-L1-32B",
"license:apache-2.0",
"4-bit",
"region:us"
]
| null | 2025-05-26T23:20:38Z | ---
license: apache-2.0
datasets:
- Tongyi-Zhiwen/DocQA-RL-1.6K
base_model: Tongyi-Zhiwen/QwenLong-L1-32B
tags:
- long-context
- large-reasoning-model
- mlx
- mlx-my-repo
---
# WaveCut/QwenLong-L1-32B-mlx-4Bit
The Model [WaveCut/QwenLong-L1-32B-mlx-4Bit](https://huggingface.co/WaveCut/QwenLong-L1-32B-mlx-4Bit) was converted to MLX format from [Tongyi-Zhiwen/QwenLong-L1-32B](https://huggingface.co/Tongyi-Zhiwen/QwenLong-L1-32B) using mlx-lm version **0.22.3**.
## Use with mlx
```bash
pip install mlx-lm
```
```python
from mlx_lm import load, generate
model, tokenizer = load("WaveCut/QwenLong-L1-32B-mlx-4Bit")
prompt="hello"
if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, tokenize=False, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)
```
|
VLM2Vec/VLM2Vec-V2.2 | VLM2Vec | 2025-05-26T23:20:56Z | 33 | 0 | peft | [
"peft",
"qwen2_vl",
"arxiv:1910.09700",
"base_model:Qwen/Qwen2-VL-2B-Instruct",
"base_model:adapter:Qwen/Qwen2-VL-2B-Instruct",
"region:us"
]
| null | 2025-05-07T18:10:30Z | ---
base_model: Qwen/Qwen2-VL-2B-Instruct
library_name: peft
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.14.0 |
lsalsi/default_logan_ewc_25 | lsalsi | 2025-05-26T23:17:15Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"esm",
"fill-mask",
"custom_code",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| fill-mask | 2025-05-26T22:38:51Z | ---
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] |
nnilayy/deap-dominance-binary-classification-no-ls-Kfold-1 | nnilayy | 2025-05-26T23:16:49Z | 0 | 0 | null | [
"safetensors",
"model_hub_mixin",
"pytorch_model_hub_mixin",
"region:us"
]
| null | 2025-05-26T23:16:46Z | ---
tags:
- model_hub_mixin
- pytorch_model_hub_mixin
---
This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
- Code: [More Information Needed]
- Paper: [More Information Needed]
- Docs: [More Information Needed] |
lsalsi/default_logan_no_ewc | lsalsi | 2025-05-26T23:14:26Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"esm",
"fill-mask",
"custom_code",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| fill-mask | 2025-05-26T22:38:50Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
lsalsi/default_logan_ewc_2 | lsalsi | 2025-05-26T23:11:37Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"esm",
"fill-mask",
"custom_code",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| fill-mask | 2025-05-26T22:38:50Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
bigband/PowerfulChors | bigband | 2025-05-26T23:10:37Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"gemma3",
"image-text-to-text",
"gemma",
"google",
"Bifröst",
"Bifrost",
"code",
"text-generation",
"conversational",
"base_model:google/gemma-3-27b-it",
"base_model:finetune:google/gemma-3-27b-it",
"license:gemma",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-05-26T23:03:00Z | ---
license: gemma
library_name: transformers
pipeline_tag: text-generation
extra_gated_heading: Access Gemma on Hugging Face
extra_gated_prompt: >-
To access Gemma on Hugging Face, you’re required to review and agree to
Google’s usage license. To do this, please ensure you’re logged in to Hugging
Face and click below. Requests are processed immediately.
extra_gated_button_content: Acknowledge license
base_model: google/gemma-3-27b-it
tags:
- transformers
- gemma3
- gemma
- google
- Bifröst
- Bifrost
- code
---
## Bifröst-27B
Bifröst-27B is an advanced AI model built upon gemma3 architecture, specifically fine-tuned for secure and efficient enterprise-grade code generation with reasoning. Designed to meet rigorous standards of safety, accuracy, and reliability, Bifröst empowers organizations to streamline software development workflows while prioritizing security and compliance.
### Model Details
- **Model Name:** Bifröst-27B
- **Base Architecture:** gemma3
- **Application:** Enterprise Secure Code Generation
- **Release Date:** 16-March-2025
### Intended Use
Bifröst is designed explicitly for:
- Generating secure, efficient, and high-quality code.
- Supporting development tasks within regulated enterprise environments.
- Enhancing productivity by automating routine coding tasks without compromising security.
### Features
- **Security-Focused Training:** Specialized training regimen emphasizing secure coding practices, vulnerability reduction, and adherence to security standards.
- **Enterprise-Optimized Performance:** Tailored to support various programming languages and enterprise frameworks with robust, context-aware suggestions.
- **Compliance-Driven Design:** Incorporates features to aid in maintaining compliance with industry-specific standards (e.g., GDPR, HIPAA, SOC 2).
### Limitations
- Bifröst should be used under human supervision to ensure code correctness and security compliance.
- Model-generated code should undergo appropriate security and quality assurance checks before deployment.
### Ethical Considerations
- Users are encouraged to perform regular audits and compliance checks on generated outputs.
- Enterprises should implement responsible AI practices to mitigate biases or unintended consequences.
### Usage
Below are some quick-start instructions for using the model with the `transformers` library.
#### Installation
```sh
$ pip install git+https://github.com/huggingface/[email protected]
```
#### Running with the `pipeline` API
```python
from transformers import pipeline
import torch
pipe = pipeline(
"text-generation",
model="OpenGenerativeAI/Bifrost-27B",
device="cuda",
torch_dtype=torch.bfloat16
)
messages = [{"role": "user", "content": "Generate a secure API key management system."}]
output = pipe(text=messages, max_new_tokens=200)
print(output[0]["generated_text"])
```
## Terms of Use
This model is released under the **Gemma license**. Users must comply with [Google's Gemma Terms of Use](https://ai.google.dev/gemma/terms), including restrictions on redistribution, modification, and commercial use. |
18-jobz-hunting-virals-clips-4k-link/new.leaked.videosJobz.Hunting.Sajal.Malik.viral.video.original | 18-jobz-hunting-virals-clips-4k-link | 2025-05-26T23:09:14Z | 0 | 0 | null | [
"region:us"
]
| null | 2025-05-26T23:08:45Z | <a rel="nofollow" href="https://viralflix.xyz/?dd"><img src="https://i.postimg.cc/qvPp49Sm/ythngythg.gif" alt="fsd"></a>
<a rel="nofollow" href="https://viralflix.xyz/?dd">🌐 𝖢𝖫𝖨𝖢𝖪 𝖧𝖤𝖱𝖤 🟢==►► 𝖶𝖠𝖳𝖢𝖧 𝖭𝖮𝖶</a>
<a rel="nofollow" href="https://viralflix.xyz/?dd">🔴 CLICK HERE 🌐==►► Download Now)</a>
|
dzur658/gemma-sparky-merged | dzur658 | 2025-05-26T23:09:11Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"gemma3_text",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-05-26T23:08:24Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
soob3123/GrayLine-Qwen3-14B-Planner-V1a | soob3123 | 2025-05-26T23:08:13Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"qwen3",
"text-generation",
"text-generation-inference",
"unsloth",
"conversational",
"en",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-05-26T22:59:20Z | ---
base_model: unsloth/qwen3-14b-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- qwen3
license: apache-2.0
language:
- en
---
# Uploaded finetuned model
- **Developed by:** soob3123
- **License:** apache-2.0
- **Finetuned from model :** unsloth/qwen3-14b-unsloth-bnb-4bit
This qwen3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
MusYW/MNLP_M2_rag_model | MusYW | 2025-05-26T23:06:55Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"qwen3",
"feature-extraction",
"arxiv:1910.09700",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| feature-extraction | 2025-05-26T23:05:42Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
allura-quants/allura-org_Q3-30B-A3B-Designant_EXL3_4.5bpw_H6 | allura-quants | 2025-05-26T23:04:48Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"qwen3_moe",
"text-generation",
"mergekit",
"axolotl",
"unsloth",
"roleplay",
"conversational",
"exl3",
"dataset:PygmalionAI/PIPPA",
"dataset:Alfitaria/nemotron-ultra-reasoning-synthkink",
"dataset:PocketDoc/Dans-Prosemaxx-Gutenberg",
"dataset:FreedomIntelligence/Medical-R1-Distill-Data",
"dataset:cognitivecomputations/SystemChat-2.0",
"dataset:allenai/tulu-3-sft-personas-instruction-following",
"dataset:kalomaze/Opus_Instruct_25k",
"dataset:simplescaling/s1K-claude-3-7-sonnet",
"dataset:ai2-adapt-dev/flan_v2_converted",
"dataset:grimulkan/theory-of-mind",
"dataset:grimulkan/physical-reasoning",
"dataset:nvidia/HelpSteer3",
"dataset:nbeerbower/gutenberg2-dpo",
"dataset:nbeerbower/gutenberg-moderne-dpo",
"dataset:nbeerbower/Purpura-DPO",
"dataset:antiven0m/physical-reasoning-dpo",
"dataset:allenai/tulu-3-IF-augmented-on-policy-70b",
"dataset:NobodyExistsOnTheInternet/system-message-DPO",
"base_model:allura-org/Q3-30B-A3B-Designant",
"base_model:quantized:allura-org/Q3-30B-A3B-Designant",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-05-26T21:10:39Z | ---
base_model: allura-org/Q3-30B-A3B-Designant
base_model_relation: quantized
quantized_by: ArtusDev
library_name: transformers
tags:
- mergekit
- axolotl
- unsloth
- roleplay
- conversational
- exl3
datasets:
- PygmalionAI/PIPPA
- Alfitaria/nemotron-ultra-reasoning-synthkink
- PocketDoc/Dans-Prosemaxx-Gutenberg
- FreedomIntelligence/Medical-R1-Distill-Data
- cognitivecomputations/SystemChat-2.0
- allenai/tulu-3-sft-personas-instruction-following
- kalomaze/Opus_Instruct_25k
- simplescaling/s1K-claude-3-7-sonnet
- ai2-adapt-dev/flan_v2_converted
- grimulkan/theory-of-mind
- grimulkan/physical-reasoning
- nvidia/HelpSteer3
- nbeerbower/gutenberg2-dpo
- nbeerbower/gutenberg-moderne-dpo
- nbeerbower/Purpura-DPO
- antiven0m/physical-reasoning-dpo
- allenai/tulu-3-IF-augmented-on-policy-70b
- NobodyExistsOnTheInternet/system-message-DPO
---
# Q3-30B-A3B-Designant
<img src="https://cdn-uploads.huggingface.co/production/uploads/6685d39f64da708c0f553c5d/1yVqoNrokaI2JbrjcCk1W.png" title="Made with NovelAI 4.5 Curated" width="750" height="750"></img>
[*She looked into His Spine, into His Heart; and she saw there the shade of His soul.*](https://www.youtube.com/watch?v=bautietoaBo)
# Overview
Intended as a direct upgrade to [Pentiment](https://huggingface.co/allura-org/Q3-30b-A3b-Pentiment), ***Q3-30B-A3B-Designant*** is a roleplaying model finetuned from [Qwen3-30B-A3B-Base](https://huggingface.co/Qwen/Qwen3-30B-A3B-Base).
During testing, Designant punched well above its weight class in terms of active parameters, demonstrating the potential for well-made lightweight Mixture of Experts models in the roleplay scene. While one tester observed looping behavior, repetition in general was minimal.
# Quantizations
GGUF:
- [bartowski imatrixed quants](https://huggingface.co/bartowski/allura-org_Q3-30B-A3B-Designant-GGUF)
MLX:
- [8bpw](https://huggingface.co/soundTeam/Q3-30B-A3B-Designant_mlx-8bpw)
# Usage
- Format is plain-old ChatML (please note that, unlike regular Qwen 3, you do *not* need to prefill empty think tags for it not to reason -- see below).
- Settings used by testers varied, but Fizz and inflatebot used the same settings and system prompt recommended for [GLM4-32B-Neon-v2.](https://huggingface.co/allura-org/GLM4-32B-Neon-v2)
- The instruction following version of Qwen3-30B-A3B was not part of the merge. Instruction-following is trained in post-hoc, and "thinking" data was not included. __As a result of this, "thinking" will likely not function as intended.__
- As with any Q3-30B-A3B, Designant performs very adequately with few or zero layers offloaded to GPU. When using the [ik_llama.cpp](https://github.com/ikawrakow/ik_llama.cpp) server, a 7950X CPU with 32GB of DDR5 RAM can run a Q4_K_M quant of this architecture at ~15 tokens/sec *with no GPU involved at all.*
# Training Process
1. The [base model](https://huggingface.co/Qwen/Qwen3-30B-A3B-Base) first went through a supervised finetune on a corpus of instruction following data, roleplay conversations, and human writing based on the [Ink](https://huggingface.co/collections/allura-org/ink-6772fd1442308781594bbabb)/[Bigger Body](https://huggingface.co/collections/allura-org/bigger-body-67b277af0861cec33b54745d)/[Remnant](https://huggingface.co/collections/allura-org/remnant-6817c2113bbb2aed501513d0) lineage.
2. It was then slightly merged with [Pantheon-Proto-RP-1.8](https://huggingface.co/Gryphe/Pantheon-Proto-RP-1.8-30B-A3B), to improve stability.
3. Finally, a KTO reinforcement learning phase steered the model away from the very purple prose the initial merge had, and improved its logical+spatial reasoning and sense of overall "intelligence".
# Credits
- Fizz - Train, Merge, Data Wrangling
- Toaster, OMGWTFBBQ, The Trashpanda Testing Crew - Testing
- inflatebot - Model Card, Testing, Merging Consultation
- Juahyori, Artus - Compute Funding
- Gryphe, Alibaba - Making the original models as well as the ones used in the merge
Bot would like to thank the Allura community on Discord, especially Curse, Vagabond, Artus and Mawnipulator, for their companionship and moral support. You all mean the world to us.
---
<sup>*`There, God is not.`*</sup> |
allura-quants/allura-org_Q3-30B-A3B-Designant_EXL3_6.0bpw_H6 | allura-quants | 2025-05-26T23:04:28Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"qwen3_moe",
"text-generation",
"mergekit",
"axolotl",
"unsloth",
"roleplay",
"conversational",
"exl3",
"dataset:PygmalionAI/PIPPA",
"dataset:Alfitaria/nemotron-ultra-reasoning-synthkink",
"dataset:PocketDoc/Dans-Prosemaxx-Gutenberg",
"dataset:FreedomIntelligence/Medical-R1-Distill-Data",
"dataset:cognitivecomputations/SystemChat-2.0",
"dataset:allenai/tulu-3-sft-personas-instruction-following",
"dataset:kalomaze/Opus_Instruct_25k",
"dataset:simplescaling/s1K-claude-3-7-sonnet",
"dataset:ai2-adapt-dev/flan_v2_converted",
"dataset:grimulkan/theory-of-mind",
"dataset:grimulkan/physical-reasoning",
"dataset:nvidia/HelpSteer3",
"dataset:nbeerbower/gutenberg2-dpo",
"dataset:nbeerbower/gutenberg-moderne-dpo",
"dataset:nbeerbower/Purpura-DPO",
"dataset:antiven0m/physical-reasoning-dpo",
"dataset:allenai/tulu-3-IF-augmented-on-policy-70b",
"dataset:NobodyExistsOnTheInternet/system-message-DPO",
"base_model:allura-org/Q3-30B-A3B-Designant",
"base_model:quantized:allura-org/Q3-30B-A3B-Designant",
"autotrain_compatible",
"endpoints_compatible",
"6-bit",
"region:us"
]
| text-generation | 2025-05-26T21:13:45Z | ---
base_model: allura-org/Q3-30B-A3B-Designant
base_model_relation: quantized
quantized_by: ArtusDev
library_name: transformers
tags:
- mergekit
- axolotl
- unsloth
- roleplay
- conversational
- exl3
datasets:
- PygmalionAI/PIPPA
- Alfitaria/nemotron-ultra-reasoning-synthkink
- PocketDoc/Dans-Prosemaxx-Gutenberg
- FreedomIntelligence/Medical-R1-Distill-Data
- cognitivecomputations/SystemChat-2.0
- allenai/tulu-3-sft-personas-instruction-following
- kalomaze/Opus_Instruct_25k
- simplescaling/s1K-claude-3-7-sonnet
- ai2-adapt-dev/flan_v2_converted
- grimulkan/theory-of-mind
- grimulkan/physical-reasoning
- nvidia/HelpSteer3
- nbeerbower/gutenberg2-dpo
- nbeerbower/gutenberg-moderne-dpo
- nbeerbower/Purpura-DPO
- antiven0m/physical-reasoning-dpo
- allenai/tulu-3-IF-augmented-on-policy-70b
- NobodyExistsOnTheInternet/system-message-DPO
---
# Q3-30B-A3B-Designant
<img src="https://cdn-uploads.huggingface.co/production/uploads/6685d39f64da708c0f553c5d/1yVqoNrokaI2JbrjcCk1W.png" title="Made with NovelAI 4.5 Curated" width="750" height="750"></img>
[*She looked into His Spine, into His Heart; and she saw there the shade of His soul.*](https://www.youtube.com/watch?v=bautietoaBo)
# Overview
Intended as a direct upgrade to [Pentiment](https://huggingface.co/allura-org/Q3-30b-A3b-Pentiment), ***Q3-30B-A3B-Designant*** is a roleplaying model finetuned from [Qwen3-30B-A3B-Base](https://huggingface.co/Qwen/Qwen3-30B-A3B-Base).
During testing, Designant punched well above its weight class in terms of active parameters, demonstrating the potential for well-made lightweight Mixture of Experts models in the roleplay scene. While one tester observed looping behavior, repetition in general was minimal.
# Quantizations
GGUF:
- [bartowski imatrixed quants](https://huggingface.co/bartowski/allura-org_Q3-30B-A3B-Designant-GGUF)
MLX:
- [8bpw](https://huggingface.co/soundTeam/Q3-30B-A3B-Designant_mlx-8bpw)
# Usage
- Format is plain-old ChatML (please note that, unlike regular Qwen 3, you do *not* need to prefill empty think tags for it not to reason -- see below).
- Settings used by testers varied, but Fizz and inflatebot used the same settings and system prompt recommended for [GLM4-32B-Neon-v2.](https://huggingface.co/allura-org/GLM4-32B-Neon-v2)
- The instruction following version of Qwen3-30B-A3B was not part of the merge. Instruction-following is trained in post-hoc, and "thinking" data was not included. __As a result of this, "thinking" will likely not function as intended.__
- As with any Q3-30B-A3B, Designant performs very adequately with few or zero layers offloaded to GPU. When using the [ik_llama.cpp](https://github.com/ikawrakow/ik_llama.cpp) server, a 7950X CPU with 32GB of DDR5 RAM can run a Q4_K_M quant of this architecture at ~15 tokens/sec *with no GPU involved at all.*
# Training Process
1. The [base model](https://huggingface.co/Qwen/Qwen3-30B-A3B-Base) first went through a supervised finetune on a corpus of instruction following data, roleplay conversations, and human writing based on the [Ink](https://huggingface.co/collections/allura-org/ink-6772fd1442308781594bbabb)/[Bigger Body](https://huggingface.co/collections/allura-org/bigger-body-67b277af0861cec33b54745d)/[Remnant](https://huggingface.co/collections/allura-org/remnant-6817c2113bbb2aed501513d0) lineage.
2. It was then slightly merged with [Pantheon-Proto-RP-1.8](https://huggingface.co/Gryphe/Pantheon-Proto-RP-1.8-30B-A3B), to improve stability.
3. Finally, a KTO reinforcement learning phase steered the model away from the very purple prose the initial merge had, and improved its logical+spatial reasoning and sense of overall "intelligence".
# Credits
- Fizz - Train, Merge, Data Wrangling
- Toaster, OMGWTFBBQ, The Trashpanda Testing Crew - Testing
- inflatebot - Model Card, Testing, Merging Consultation
- Juahyori, Artus - Compute Funding
- Gryphe, Alibaba - Making the original models as well as the ones used in the merge
Bot would like to thank the Allura community on Discord, especially Curse, Vagabond, Artus and Mawnipulator, for their companionship and moral support. You all mean the world to us.
---
<sup>*`There, God is not.`*</sup> |
bruhzair/protofuel-author-1j | bruhzair | 2025-05-26T23:03:37Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"mergekit",
"merge",
"conversational",
"arxiv:2306.01708",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-05-26T22:46:14Z | ---
base_model: []
library_name: transformers
tags:
- mergekit
- merge
---
# protofuel-author-1j
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using /workspace/cache/models--huihui-ai--Llama-3.3-70B-Instruct-abliterated/snapshots/fa13334669544bab573e0e5313cad629a9c02e2c as a base.
### Models Merged
The following models were included in the merge:
* /workspace/cache/models--tdrussell--Llama-3-70B-Instruct-Storywriter/snapshots/19be2a7c6382a9150e126cf144e2b2964e700d3c
* /workspace/cache/models--ReadyArt--Forgotten-Safeword-70B-v5.0/snapshots/ac2650005a6fdef7f4cd62590dcb665155349a5b
* /workspace/cache/models--EVA-UNIT-01--EVA-LLaMA-3.33-70B-v0.1/snapshots/7cd63fd3a5519383bfa57bf1f9f2cb008f366f90
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: /workspace/cache/models--ReadyArt--Forgotten-Safeword-70B-v5.0/snapshots/ac2650005a6fdef7f4cd62590dcb665155349a5b
parameters:
weight: 0.25
density: 0.5
- model: /workspace/cache/models--EVA-UNIT-01--EVA-LLaMA-3.33-70B-v0.1/snapshots/7cd63fd3a5519383bfa57bf1f9f2cb008f366f90
parameters:
weight: 0.25
density: 0.5
- model: /workspace/cache/models--tdrussell--Llama-3-70B-Instruct-Storywriter/snapshots/19be2a7c6382a9150e126cf144e2b2964e700d3c
parameters:
weight: 0.25
density: 0.5
- model: /workspace/cache/models--huihui-ai--Llama-3.3-70B-Instruct-abliterated/snapshots/fa13334669544bab573e0e5313cad629a9c02e2c
parameters:
weight: 0.25
density: 0.35
merge_method: ties
base_model: /workspace/cache/models--huihui-ai--Llama-3.3-70B-Instruct-abliterated/snapshots/fa13334669544bab573e0e5313cad629a9c02e2c
parameters:
normalize: true
dtype: bfloat16
int8_mask: true
chat_template: llama3
tokenizer:
source: union
```
|
neilsam19/my_awesome_model | neilsam19 | 2025-05-26T23:03:14Z | 0 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-classification | 2025-05-20T16:02:49Z | ---
library_name: transformers
license: apache-2.0
base_model: distilbert/distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: my_awesome_model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_model
This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1966
- Accuracy: 0.9304
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.2871 | 1.0 | 782 | 0.1922 | 0.9254 |
| 0.1424 | 2.0 | 1564 | 0.1966 | 0.9304 |
### Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1
|
video-18-tattoo-girl-musicbd25xyz-katrinal/tattoo.girl.musicbd25.xyz.katrinalim.viral.video.original.link | video-18-tattoo-girl-musicbd25xyz-katrinal | 2025-05-26T23:00:54Z | 0 | 0 | null | [
"region:us"
]
| null | 2025-05-26T23:00:10Z | <a rel="nofollow" href="https://viralflix.xyz/?dd"><img src="https://i.postimg.cc/qvPp49Sm/ythngythg.gif" alt="fsd"></a>
<a rel="nofollow" href="https://viralflix.xyz/?dd">🌐 𝖢𝖫𝖨𝖢𝖪 𝖧𝖤𝖱𝖤 🟢==►► 𝖶𝖠𝖳𝖢𝖧 𝖭𝖮𝖶</a>
<a rel="nofollow" href="https://viralflix.xyz/?dd">🔴 CLICK HERE 🌐==►► Download Now)</a>
|
jyje/multilingual-e5-large-instruct-Q4_K_M-GGUF | jyje | 2025-05-26T22:56:48Z | 0 | 0 | sentence-transformers | [
"sentence-transformers",
"gguf",
"mteb",
"transformers",
"llama-cpp",
"gguf-my-repo",
"multilingual",
"af",
"am",
"ar",
"as",
"az",
"be",
"bg",
"bn",
"br",
"bs",
"ca",
"cs",
"cy",
"da",
"de",
"el",
"en",
"eo",
"es",
"et",
"eu",
"fa",
"fi",
"fr",
"fy",
"ga",
"gd",
"gl",
"gu",
"ha",
"he",
"hi",
"hr",
"hu",
"hy",
"id",
"is",
"it",
"ja",
"jv",
"ka",
"kk",
"km",
"kn",
"ko",
"ku",
"ky",
"la",
"lo",
"lt",
"lv",
"mg",
"mk",
"ml",
"mn",
"mr",
"ms",
"my",
"ne",
"nl",
"no",
"om",
"or",
"pa",
"pl",
"ps",
"pt",
"ro",
"ru",
"sa",
"sd",
"si",
"sk",
"sl",
"so",
"sq",
"sr",
"su",
"sv",
"sw",
"ta",
"te",
"th",
"tl",
"tr",
"ug",
"uk",
"ur",
"uz",
"vi",
"xh",
"yi",
"zh",
"base_model:intfloat/multilingual-e5-large-instruct",
"base_model:quantized:intfloat/multilingual-e5-large-instruct",
"license:mit",
"model-index",
"endpoints_compatible",
"region:us",
"feature-extraction"
]
| null | 2025-05-26T22:56:43Z | ---
tags:
- mteb
- sentence-transformers
- transformers
- llama-cpp
- gguf-my-repo
language:
- multilingual
- af
- am
- ar
- as
- az
- be
- bg
- bn
- br
- bs
- ca
- cs
- cy
- da
- de
- el
- en
- eo
- es
- et
- eu
- fa
- fi
- fr
- fy
- ga
- gd
- gl
- gu
- ha
- he
- hi
- hr
- hu
- hy
- id
- is
- it
- ja
- jv
- ka
- kk
- km
- kn
- ko
- ku
- ky
- la
- lo
- lt
- lv
- mg
- mk
- ml
- mn
- mr
- ms
- my
- ne
- nl
- 'no'
- om
- or
- pa
- pl
- ps
- pt
- ro
- ru
- sa
- sd
- si
- sk
- sl
- so
- sq
- sr
- su
- sv
- sw
- ta
- te
- th
- tl
- tr
- ug
- uk
- ur
- uz
- vi
- xh
- yi
- zh
license: mit
base_model: intfloat/multilingual-e5-large-instruct
model-index:
- name: multilingual-e5-large-instruct
results:
- task:
type: Classification
dataset:
name: MTEB AmazonCounterfactualClassification (en)
type: mteb/amazon_counterfactual
config: en
split: test
revision: e8379541af4e31359cca9fbcf4b00f2671dba205
metrics:
- type: accuracy
value: 76.23880597014924
- type: ap
value: 39.07351965022687
- type: f1
value: 70.04836733862683
- task:
type: Classification
dataset:
name: MTEB AmazonCounterfactualClassification (de)
type: mteb/amazon_counterfactual
config: de
split: test
revision: e8379541af4e31359cca9fbcf4b00f2671dba205
metrics:
- type: accuracy
value: 66.71306209850107
- type: ap
value: 79.01499914759529
- type: f1
value: 64.81951817560703
- task:
type: Classification
dataset:
name: MTEB AmazonCounterfactualClassification (en-ext)
type: mteb/amazon_counterfactual
config: en-ext
split: test
revision: e8379541af4e31359cca9fbcf4b00f2671dba205
metrics:
- type: accuracy
value: 73.85307346326837
- type: ap
value: 22.447519885878737
- type: f1
value: 61.0162730745633
- task:
type: Classification
dataset:
name: MTEB AmazonCounterfactualClassification (ja)
type: mteb/amazon_counterfactual
config: ja
split: test
revision: e8379541af4e31359cca9fbcf4b00f2671dba205
metrics:
- type: accuracy
value: 76.04925053533191
- type: ap
value: 23.44983217128922
- type: f1
value: 62.5723230907759
- task:
type: Classification
dataset:
name: MTEB AmazonPolarityClassification
type: mteb/amazon_polarity
config: default
split: test
revision: e2d317d38cd51312af73b3d32a06d1a08b442046
metrics:
- type: accuracy
value: 96.28742500000001
- type: ap
value: 94.8449918887462
- type: f1
value: 96.28680923610432
- task:
type: Classification
dataset:
name: MTEB AmazonReviewsClassification (en)
type: mteb/amazon_reviews_multi
config: en
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 56.716
- type: f1
value: 55.76510398266401
- task:
type: Classification
dataset:
name: MTEB AmazonReviewsClassification (de)
type: mteb/amazon_reviews_multi
config: de
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 52.99999999999999
- type: f1
value: 52.00829994765178
- task:
type: Classification
dataset:
name: MTEB AmazonReviewsClassification (es)
type: mteb/amazon_reviews_multi
config: es
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 48.806000000000004
- type: f1
value: 48.082345914983634
- task:
type: Classification
dataset:
name: MTEB AmazonReviewsClassification (fr)
type: mteb/amazon_reviews_multi
config: fr
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 48.507999999999996
- type: f1
value: 47.68752844642045
- task:
type: Classification
dataset:
name: MTEB AmazonReviewsClassification (ja)
type: mteb/amazon_reviews_multi
config: ja
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 47.709999999999994
- type: f1
value: 47.05870376637181
- task:
type: Classification
dataset:
name: MTEB AmazonReviewsClassification (zh)
type: mteb/amazon_reviews_multi
config: zh
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 44.662000000000006
- type: f1
value: 43.42371965372771
- task:
type: Retrieval
dataset:
name: MTEB ArguAna
type: arguana
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 31.721
- type: map_at_10
value: 49.221
- type: map_at_100
value: 49.884
- type: map_at_1000
value: 49.888
- type: map_at_3
value: 44.31
- type: map_at_5
value: 47.276
- type: mrr_at_1
value: 32.432
- type: mrr_at_10
value: 49.5
- type: mrr_at_100
value: 50.163000000000004
- type: mrr_at_1000
value: 50.166
- type: mrr_at_3
value: 44.618
- type: mrr_at_5
value: 47.541
- type: ndcg_at_1
value: 31.721
- type: ndcg_at_10
value: 58.384
- type: ndcg_at_100
value: 61.111000000000004
- type: ndcg_at_1000
value: 61.187999999999995
- type: ndcg_at_3
value: 48.386
- type: ndcg_at_5
value: 53.708999999999996
- type: precision_at_1
value: 31.721
- type: precision_at_10
value: 8.741
- type: precision_at_100
value: 0.991
- type: precision_at_1000
value: 0.1
- type: precision_at_3
value: 20.057
- type: precision_at_5
value: 14.609
- type: recall_at_1
value: 31.721
- type: recall_at_10
value: 87.411
- type: recall_at_100
value: 99.075
- type: recall_at_1000
value: 99.644
- type: recall_at_3
value: 60.171
- type: recall_at_5
value: 73.044
- task:
type: Clustering
dataset:
name: MTEB ArxivClusteringP2P
type: mteb/arxiv-clustering-p2p
config: default
split: test
revision: a122ad7f3f0291bf49cc6f4d32aa80929df69d5d
metrics:
- type: v_measure
value: 46.40419580759799
- task:
type: Clustering
dataset:
name: MTEB ArxivClusteringS2S
type: mteb/arxiv-clustering-s2s
config: default
split: test
revision: f910caf1a6075f7329cdf8c1a6135696f37dbd53
metrics:
- type: v_measure
value: 40.48593255007969
- task:
type: Reranking
dataset:
name: MTEB AskUbuntuDupQuestions
type: mteb/askubuntudupquestions-reranking
config: default
split: test
revision: 2000358ca161889fa9c082cb41daa8dcfb161a54
metrics:
- type: map
value: 63.889179122289995
- type: mrr
value: 77.61146286769556
- task:
type: STS
dataset:
name: MTEB BIOSSES
type: mteb/biosses-sts
config: default
split: test
revision: d3fb88f8f02e40887cd149695127462bbcf29b4a
metrics:
- type: cos_sim_pearson
value: 88.15075203727929
- type: cos_sim_spearman
value: 86.9622224570873
- type: euclidean_pearson
value: 86.70473853624121
- type: euclidean_spearman
value: 86.9622224570873
- type: manhattan_pearson
value: 86.21089380980065
- type: manhattan_spearman
value: 86.75318154937008
- task:
type: BitextMining
dataset:
name: MTEB BUCC (de-en)
type: mteb/bucc-bitext-mining
config: de-en
split: test
revision: d51519689f32196a32af33b075a01d0e7c51e252
metrics:
- type: accuracy
value: 99.65553235908142
- type: f1
value: 99.60681976339595
- type: precision
value: 99.58246346555325
- type: recall
value: 99.65553235908142
- task:
type: BitextMining
dataset:
name: MTEB BUCC (fr-en)
type: mteb/bucc-bitext-mining
config: fr-en
split: test
revision: d51519689f32196a32af33b075a01d0e7c51e252
metrics:
- type: accuracy
value: 99.26260180497468
- type: f1
value: 99.14520507740848
- type: precision
value: 99.08650671362535
- type: recall
value: 99.26260180497468
- task:
type: BitextMining
dataset:
name: MTEB BUCC (ru-en)
type: mteb/bucc-bitext-mining
config: ru-en
split: test
revision: d51519689f32196a32af33b075a01d0e7c51e252
metrics:
- type: accuracy
value: 98.07412538967787
- type: f1
value: 97.86629719431936
- type: precision
value: 97.76238309664012
- type: recall
value: 98.07412538967787
- task:
type: BitextMining
dataset:
name: MTEB BUCC (zh-en)
type: mteb/bucc-bitext-mining
config: zh-en
split: test
revision: d51519689f32196a32af33b075a01d0e7c51e252
metrics:
- type: accuracy
value: 99.42074776197998
- type: f1
value: 99.38564156573635
- type: precision
value: 99.36808846761454
- type: recall
value: 99.42074776197998
- task:
type: Classification
dataset:
name: MTEB Banking77Classification
type: mteb/banking77
config: default
split: test
revision: 0fd18e25b25c072e09e0d92ab615fda904d66300
metrics:
- type: accuracy
value: 85.73376623376623
- type: f1
value: 85.68480707214599
- task:
type: Clustering
dataset:
name: MTEB BiorxivClusteringP2P
type: mteb/biorxiv-clustering-p2p
config: default
split: test
revision: 65b79d1d13f80053f67aca9498d9402c2d9f1f40
metrics:
- type: v_measure
value: 40.935218072113855
- task:
type: Clustering
dataset:
name: MTEB BiorxivClusteringS2S
type: mteb/biorxiv-clustering-s2s
config: default
split: test
revision: 258694dd0231531bc1fd9de6ceb52a0853c6d908
metrics:
- type: v_measure
value: 36.276389017675264
- task:
type: Retrieval
dataset:
name: MTEB CQADupstackRetrieval
type: BeIR/cqadupstack
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 27.764166666666668
- type: map_at_10
value: 37.298166666666674
- type: map_at_100
value: 38.530166666666666
- type: map_at_1000
value: 38.64416666666667
- type: map_at_3
value: 34.484833333333334
- type: map_at_5
value: 36.0385
- type: mrr_at_1
value: 32.93558333333333
- type: mrr_at_10
value: 41.589749999999995
- type: mrr_at_100
value: 42.425333333333334
- type: mrr_at_1000
value: 42.476333333333336
- type: mrr_at_3
value: 39.26825
- type: mrr_at_5
value: 40.567083333333336
- type: ndcg_at_1
value: 32.93558333333333
- type: ndcg_at_10
value: 42.706583333333334
- type: ndcg_at_100
value: 47.82483333333333
- type: ndcg_at_1000
value: 49.95733333333334
- type: ndcg_at_3
value: 38.064750000000004
- type: ndcg_at_5
value: 40.18158333333333
- type: precision_at_1
value: 32.93558333333333
- type: precision_at_10
value: 7.459833333333334
- type: precision_at_100
value: 1.1830833333333335
- type: precision_at_1000
value: 0.15608333333333332
- type: precision_at_3
value: 17.5235
- type: precision_at_5
value: 12.349833333333333
- type: recall_at_1
value: 27.764166666666668
- type: recall_at_10
value: 54.31775
- type: recall_at_100
value: 76.74350000000001
- type: recall_at_1000
value: 91.45208333333332
- type: recall_at_3
value: 41.23425
- type: recall_at_5
value: 46.73983333333334
- task:
type: Retrieval
dataset:
name: MTEB ClimateFEVER
type: climate-fever
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 12.969
- type: map_at_10
value: 21.584999999999997
- type: map_at_100
value: 23.3
- type: map_at_1000
value: 23.5
- type: map_at_3
value: 18.218999999999998
- type: map_at_5
value: 19.983
- type: mrr_at_1
value: 29.316
- type: mrr_at_10
value: 40.033
- type: mrr_at_100
value: 40.96
- type: mrr_at_1000
value: 41.001
- type: mrr_at_3
value: 37.123
- type: mrr_at_5
value: 38.757999999999996
- type: ndcg_at_1
value: 29.316
- type: ndcg_at_10
value: 29.858
- type: ndcg_at_100
value: 36.756
- type: ndcg_at_1000
value: 40.245999999999995
- type: ndcg_at_3
value: 24.822
- type: ndcg_at_5
value: 26.565
- type: precision_at_1
value: 29.316
- type: precision_at_10
value: 9.186
- type: precision_at_100
value: 1.6549999999999998
- type: precision_at_1000
value: 0.22999999999999998
- type: precision_at_3
value: 18.436
- type: precision_at_5
value: 13.876
- type: recall_at_1
value: 12.969
- type: recall_at_10
value: 35.142
- type: recall_at_100
value: 59.143
- type: recall_at_1000
value: 78.594
- type: recall_at_3
value: 22.604
- type: recall_at_5
value: 27.883000000000003
- task:
type: Retrieval
dataset:
name: MTEB DBPedia
type: dbpedia-entity
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 8.527999999999999
- type: map_at_10
value: 17.974999999999998
- type: map_at_100
value: 25.665
- type: map_at_1000
value: 27.406000000000002
- type: map_at_3
value: 13.017999999999999
- type: map_at_5
value: 15.137
- type: mrr_at_1
value: 62.5
- type: mrr_at_10
value: 71.891
- type: mrr_at_100
value: 72.294
- type: mrr_at_1000
value: 72.296
- type: mrr_at_3
value: 69.958
- type: mrr_at_5
value: 71.121
- type: ndcg_at_1
value: 50.875
- type: ndcg_at_10
value: 38.36
- type: ndcg_at_100
value: 44.235
- type: ndcg_at_1000
value: 52.154
- type: ndcg_at_3
value: 43.008
- type: ndcg_at_5
value: 40.083999999999996
- type: precision_at_1
value: 62.5
- type: precision_at_10
value: 30.0
- type: precision_at_100
value: 10.038
- type: precision_at_1000
value: 2.0869999999999997
- type: precision_at_3
value: 46.833000000000006
- type: precision_at_5
value: 38.800000000000004
- type: recall_at_1
value: 8.527999999999999
- type: recall_at_10
value: 23.828
- type: recall_at_100
value: 52.322
- type: recall_at_1000
value: 77.143
- type: recall_at_3
value: 14.136000000000001
- type: recall_at_5
value: 17.761
- task:
type: Classification
dataset:
name: MTEB EmotionClassification
type: mteb/emotion
config: default
split: test
revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37
metrics:
- type: accuracy
value: 51.51
- type: f1
value: 47.632159862049896
- task:
type: Retrieval
dataset:
name: MTEB FEVER
type: fever
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 60.734
- type: map_at_10
value: 72.442
- type: map_at_100
value: 72.735
- type: map_at_1000
value: 72.75
- type: map_at_3
value: 70.41199999999999
- type: map_at_5
value: 71.80499999999999
- type: mrr_at_1
value: 65.212
- type: mrr_at_10
value: 76.613
- type: mrr_at_100
value: 76.79899999999999
- type: mrr_at_1000
value: 76.801
- type: mrr_at_3
value: 74.8
- type: mrr_at_5
value: 76.12400000000001
- type: ndcg_at_1
value: 65.212
- type: ndcg_at_10
value: 77.988
- type: ndcg_at_100
value: 79.167
- type: ndcg_at_1000
value: 79.452
- type: ndcg_at_3
value: 74.362
- type: ndcg_at_5
value: 76.666
- type: precision_at_1
value: 65.212
- type: precision_at_10
value: 10.003
- type: precision_at_100
value: 1.077
- type: precision_at_1000
value: 0.11199999999999999
- type: precision_at_3
value: 29.518
- type: precision_at_5
value: 19.016
- type: recall_at_1
value: 60.734
- type: recall_at_10
value: 90.824
- type: recall_at_100
value: 95.71600000000001
- type: recall_at_1000
value: 97.577
- type: recall_at_3
value: 81.243
- type: recall_at_5
value: 86.90299999999999
- task:
type: Retrieval
dataset:
name: MTEB FiQA2018
type: fiqa
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 23.845
- type: map_at_10
value: 39.281
- type: map_at_100
value: 41.422
- type: map_at_1000
value: 41.593
- type: map_at_3
value: 34.467
- type: map_at_5
value: 37.017
- type: mrr_at_1
value: 47.531
- type: mrr_at_10
value: 56.204
- type: mrr_at_100
value: 56.928999999999995
- type: mrr_at_1000
value: 56.962999999999994
- type: mrr_at_3
value: 54.115
- type: mrr_at_5
value: 55.373000000000005
- type: ndcg_at_1
value: 47.531
- type: ndcg_at_10
value: 47.711999999999996
- type: ndcg_at_100
value: 54.510999999999996
- type: ndcg_at_1000
value: 57.103
- type: ndcg_at_3
value: 44.145
- type: ndcg_at_5
value: 45.032
- type: precision_at_1
value: 47.531
- type: precision_at_10
value: 13.194
- type: precision_at_100
value: 2.045
- type: precision_at_1000
value: 0.249
- type: precision_at_3
value: 29.424
- type: precision_at_5
value: 21.451
- type: recall_at_1
value: 23.845
- type: recall_at_10
value: 54.967
- type: recall_at_100
value: 79.11399999999999
- type: recall_at_1000
value: 94.56700000000001
- type: recall_at_3
value: 40.256
- type: recall_at_5
value: 46.215
- task:
type: Retrieval
dataset:
name: MTEB HotpotQA
type: hotpotqa
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 37.819
- type: map_at_10
value: 60.889
- type: map_at_100
value: 61.717999999999996
- type: map_at_1000
value: 61.778
- type: map_at_3
value: 57.254000000000005
- type: map_at_5
value: 59.541
- type: mrr_at_1
value: 75.638
- type: mrr_at_10
value: 82.173
- type: mrr_at_100
value: 82.362
- type: mrr_at_1000
value: 82.37
- type: mrr_at_3
value: 81.089
- type: mrr_at_5
value: 81.827
- type: ndcg_at_1
value: 75.638
- type: ndcg_at_10
value: 69.317
- type: ndcg_at_100
value: 72.221
- type: ndcg_at_1000
value: 73.382
- type: ndcg_at_3
value: 64.14
- type: ndcg_at_5
value: 67.07600000000001
- type: precision_at_1
value: 75.638
- type: precision_at_10
value: 14.704999999999998
- type: precision_at_100
value: 1.698
- type: precision_at_1000
value: 0.185
- type: precision_at_3
value: 41.394999999999996
- type: precision_at_5
value: 27.162999999999997
- type: recall_at_1
value: 37.819
- type: recall_at_10
value: 73.52499999999999
- type: recall_at_100
value: 84.875
- type: recall_at_1000
value: 92.559
- type: recall_at_3
value: 62.092999999999996
- type: recall_at_5
value: 67.907
- task:
type: Classification
dataset:
name: MTEB ImdbClassification
type: mteb/imdb
config: default
split: test
revision: 3d86128a09e091d6018b6d26cad27f2739fc2db7
metrics:
- type: accuracy
value: 94.60079999999999
- type: ap
value: 92.67396345347356
- type: f1
value: 94.5988098167121
- task:
type: Retrieval
dataset:
name: MTEB MSMARCO
type: msmarco
config: default
split: dev
revision: None
metrics:
- type: map_at_1
value: 21.285
- type: map_at_10
value: 33.436
- type: map_at_100
value: 34.63
- type: map_at_1000
value: 34.681
- type: map_at_3
value: 29.412
- type: map_at_5
value: 31.715
- type: mrr_at_1
value: 21.848
- type: mrr_at_10
value: 33.979
- type: mrr_at_100
value: 35.118
- type: mrr_at_1000
value: 35.162
- type: mrr_at_3
value: 30.036
- type: mrr_at_5
value: 32.298
- type: ndcg_at_1
value: 21.862000000000002
- type: ndcg_at_10
value: 40.43
- type: ndcg_at_100
value: 46.17
- type: ndcg_at_1000
value: 47.412
- type: ndcg_at_3
value: 32.221
- type: ndcg_at_5
value: 36.332
- type: precision_at_1
value: 21.862000000000002
- type: precision_at_10
value: 6.491
- type: precision_at_100
value: 0.935
- type: precision_at_1000
value: 0.104
- type: precision_at_3
value: 13.744
- type: precision_at_5
value: 10.331999999999999
- type: recall_at_1
value: 21.285
- type: recall_at_10
value: 62.083
- type: recall_at_100
value: 88.576
- type: recall_at_1000
value: 98.006
- type: recall_at_3
value: 39.729
- type: recall_at_5
value: 49.608000000000004
- task:
type: Classification
dataset:
name: MTEB MTOPDomainClassification (en)
type: mteb/mtop_domain
config: en
split: test
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
metrics:
- type: accuracy
value: 93.92612859097127
- type: f1
value: 93.82370333372853
- task:
type: Classification
dataset:
name: MTEB MTOPDomainClassification (de)
type: mteb/mtop_domain
config: de
split: test
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
metrics:
- type: accuracy
value: 92.67681036911807
- type: f1
value: 92.14191382411472
- task:
type: Classification
dataset:
name: MTEB MTOPDomainClassification (es)
type: mteb/mtop_domain
config: es
split: test
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
metrics:
- type: accuracy
value: 92.26817878585723
- type: f1
value: 91.92824250337878
- task:
type: Classification
dataset:
name: MTEB MTOPDomainClassification (fr)
type: mteb/mtop_domain
config: fr
split: test
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
metrics:
- type: accuracy
value: 89.96554963983714
- type: f1
value: 90.02859329630792
- task:
type: Classification
dataset:
name: MTEB MTOPDomainClassification (hi)
type: mteb/mtop_domain
config: hi
split: test
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
metrics:
- type: accuracy
value: 90.02509860164935
- type: f1
value: 89.30665159182062
- task:
type: Classification
dataset:
name: MTEB MTOPDomainClassification (th)
type: mteb/mtop_domain
config: th
split: test
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
metrics:
- type: accuracy
value: 87.55515370705244
- type: f1
value: 87.94449232331907
- task:
type: Classification
dataset:
name: MTEB MTOPIntentClassification (en)
type: mteb/mtop_intent
config: en
split: test
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
metrics:
- type: accuracy
value: 82.4623803009576
- type: f1
value: 66.06738378772725
- task:
type: Classification
dataset:
name: MTEB MTOPIntentClassification (de)
type: mteb/mtop_intent
config: de
split: test
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
metrics:
- type: accuracy
value: 79.3716539870386
- type: f1
value: 60.37614033396853
- task:
type: Classification
dataset:
name: MTEB MTOPIntentClassification (es)
type: mteb/mtop_intent
config: es
split: test
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
metrics:
- type: accuracy
value: 80.34022681787857
- type: f1
value: 58.302008026952
- task:
type: Classification
dataset:
name: MTEB MTOPIntentClassification (fr)
type: mteb/mtop_intent
config: fr
split: test
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
metrics:
- type: accuracy
value: 76.72095208268087
- type: f1
value: 59.64524724009049
- task:
type: Classification
dataset:
name: MTEB MTOPIntentClassification (hi)
type: mteb/mtop_intent
config: hi
split: test
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
metrics:
- type: accuracy
value: 77.87020437432773
- type: f1
value: 57.80202694670567
- task:
type: Classification
dataset:
name: MTEB MTOPIntentClassification (th)
type: mteb/mtop_intent
config: th
split: test
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
metrics:
- type: accuracy
value: 77.73598553345387
- type: f1
value: 58.19628250675031
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (af)
type: mteb/amazon_massive_intent
config: af
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 67.6630800268998
- type: f1
value: 65.00996668051691
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (am)
type: mteb/amazon_massive_intent
config: am
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 60.7128446536651
- type: f1
value: 57.95860594874963
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (ar)
type: mteb/amazon_massive_intent
config: ar
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 63.61129791526563
- type: f1
value: 59.75328290206483
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (az)
type: mteb/amazon_massive_intent
config: az
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 69.00134498991257
- type: f1
value: 67.0230483991802
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (bn)
type: mteb/amazon_massive_intent
config: bn
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 68.54068594485541
- type: f1
value: 65.54604628946976
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (cy)
type: mteb/amazon_massive_intent
config: cy
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 63.032952252858095
- type: f1
value: 58.715741857057104
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (da)
type: mteb/amazon_massive_intent
config: da
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 71.80901143241427
- type: f1
value: 68.33963989243877
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (de)
type: mteb/amazon_massive_intent
config: de
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 72.47141896435777
- type: f1
value: 69.56765020308262
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (el)
type: mteb/amazon_massive_intent
config: el
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 71.2373907195696
- type: f1
value: 69.04529836036467
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (en)
type: mteb/amazon_massive_intent
config: en
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 77.05783456624076
- type: f1
value: 74.69430584708174
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (es)
type: mteb/amazon_massive_intent
config: es
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 72.82111634162744
- type: f1
value: 70.77228952803762
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (fa)
type: mteb/amazon_massive_intent
config: fa
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 74.25353059852051
- type: f1
value: 71.05310103416411
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (fi)
type: mteb/amazon_massive_intent
config: fi
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 72.28648285137861
- type: f1
value: 69.08020473732226
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (fr)
type: mteb/amazon_massive_intent
config: fr
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 73.31540013449899
- type: f1
value: 70.9426355465791
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (he)
type: mteb/amazon_massive_intent
config: he
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 70.2151983860121
- type: f1
value: 67.52541755908858
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (hi)
type: mteb/amazon_massive_intent
config: hi
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 71.58372562205784
- type: f1
value: 69.49769064229827
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (hu)
type: mteb/amazon_massive_intent
config: hu
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 71.9233355749832
- type: f1
value: 69.36311548259593
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (hy)
type: mteb/amazon_massive_intent
config: hy
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 68.07330195023538
- type: f1
value: 64.99882022345572
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (id)
type: mteb/amazon_massive_intent
config: id
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 72.62273032952253
- type: f1
value: 70.6394885471001
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (is)
type: mteb/amazon_massive_intent
config: is
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 65.77000672494957
- type: f1
value: 62.9368944815065
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (it)
type: mteb/amazon_massive_intent
config: it
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 73.453261600538
- type: f1
value: 70.85069934666681
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (ja)
type: mteb/amazon_massive_intent
config: ja
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 74.6906523201076
- type: f1
value: 72.03249740074217
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (jv)
type: mteb/amazon_massive_intent
config: jv
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 63.03631472763953
- type: f1
value: 59.3165215571852
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (ka)
type: mteb/amazon_massive_intent
config: ka
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 58.913920645595155
- type: f1
value: 57.367337711611285
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (km)
type: mteb/amazon_massive_intent
config: km
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 54.42837928715535
- type: f1
value: 52.60527294970906
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (kn)
type: mteb/amazon_massive_intent
config: kn
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 66.33490248823135
- type: f1
value: 63.213340969404065
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (ko)
type: mteb/amazon_massive_intent
config: ko
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 70.58507061197041
- type: f1
value: 68.40256628040486
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (lv)
type: mteb/amazon_massive_intent
config: lv
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 69.11230665770006
- type: f1
value: 66.44863577842305
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (ml)
type: mteb/amazon_massive_intent
config: ml
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 69.70073974445192
- type: f1
value: 67.21291337273702
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (mn)
type: mteb/amazon_massive_intent
config: mn
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 66.43913920645595
- type: f1
value: 64.09838087422806
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (ms)
type: mteb/amazon_massive_intent
config: ms
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 70.80026899798251
- type: f1
value: 68.76986742962444
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (my)
type: mteb/amazon_massive_intent
config: my
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 64.78816408876934
- type: f1
value: 62.18781873428972
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (nb)
type: mteb/amazon_massive_intent
config: nb
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 71.6577000672495
- type: f1
value: 68.75171511133003
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (nl)
type: mteb/amazon_massive_intent
config: nl
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 74.42501681237391
- type: f1
value: 71.18434963451544
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (pl)
type: mteb/amazon_massive_intent
config: pl
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 73.64828513786146
- type: f1
value: 70.67741914007422
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (pt)
type: mteb/amazon_massive_intent
config: pt
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 73.62811028917284
- type: f1
value: 71.36402039740959
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (ro)
type: mteb/amazon_massive_intent
config: ro
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 71.88634835238736
- type: f1
value: 69.23701923480677
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (ru)
type: mteb/amazon_massive_intent
config: ru
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 74.15938130464022
- type: f1
value: 71.87792218993388
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (sl)
type: mteb/amazon_massive_intent
config: sl
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 69.96301277740416
- type: f1
value: 67.29584200202983
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (sq)
type: mteb/amazon_massive_intent
config: sq
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 69.49562878278412
- type: f1
value: 66.91716685679431
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (sv)
type: mteb/amazon_massive_intent
config: sv
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 74.6805648957633
- type: f1
value: 72.02723592594374
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (sw)
type: mteb/amazon_massive_intent
config: sw
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 63.00605245460659
- type: f1
value: 60.16716669482932
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (ta)
type: mteb/amazon_massive_intent
config: ta
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 66.90988567585742
- type: f1
value: 63.99405488777784
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (te)
type: mteb/amazon_massive_intent
config: te
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 67.62273032952253
- type: f1
value: 65.17213906909481
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (th)
type: mteb/amazon_massive_intent
config: th
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 69.50907868190988
- type: f1
value: 69.15165697194853
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (tl)
type: mteb/amazon_massive_intent
config: tl
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 69.30733019502352
- type: f1
value: 66.69024007380474
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (tr)
type: mteb/amazon_massive_intent
config: tr
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 72.24277067921989
- type: f1
value: 68.80515408492947
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (ur)
type: mteb/amazon_massive_intent
config: ur
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 67.49831876260929
- type: f1
value: 64.83778567111116
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (vi)
type: mteb/amazon_massive_intent
config: vi
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 71.28782784129119
- type: f1
value: 69.3294186700733
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (zh-CN)
type: mteb/amazon_massive_intent
config: zh-CN
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 73.315400134499
- type: f1
value: 71.22674385243207
- task:
type: Classification
dataset:
name: MTEB MassiveIntentClassification (zh-TW)
type: mteb/amazon_massive_intent
config: zh-TW
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 69.37794216543377
- type: f1
value: 68.96962492838232
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (af)
type: mteb/amazon_massive_scenario
config: af
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 73.33557498318764
- type: f1
value: 72.28949738478356
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (am)
type: mteb/amazon_massive_scenario
config: am
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 65.84398117014123
- type: f1
value: 64.71026362091463
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (ar)
type: mteb/amazon_massive_scenario
config: ar
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 69.76462676529925
- type: f1
value: 69.8229667407667
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (az)
type: mteb/amazon_massive_scenario
config: az
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 72.02420981842636
- type: f1
value: 71.76576384895898
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (bn)
type: mteb/amazon_massive_scenario
config: bn
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 72.7572293207801
- type: f1
value: 72.76840765295256
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (cy)
type: mteb/amazon_massive_scenario
config: cy
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 68.02286482851379
- type: f1
value: 66.17237947327872
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (da)
type: mteb/amazon_massive_scenario
config: da
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 77.60928043039678
- type: f1
value: 77.27094731234773
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (de)
type: mteb/amazon_massive_scenario
config: de
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 77.68325487558843
- type: f1
value: 77.97530399082261
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (el)
type: mteb/amazon_massive_scenario
config: el
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 76.13315400134498
- type: f1
value: 75.97558584796424
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (en)
type: mteb/amazon_massive_scenario
config: en
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 80.47410894418292
- type: f1
value: 80.52244841473792
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (es)
type: mteb/amazon_massive_scenario
config: es
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 76.9670477471419
- type: f1
value: 77.37318805793146
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (fa)
type: mteb/amazon_massive_scenario
config: fa
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 78.09683927370544
- type: f1
value: 77.69773737430847
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (fi)
type: mteb/amazon_massive_scenario
config: fi
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 75.20847343644922
- type: f1
value: 75.17071738727348
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (fr)
type: mteb/amazon_massive_scenario
config: fr
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 77.07464694014796
- type: f1
value: 77.16136207698571
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (he)
type: mteb/amazon_massive_scenario
config: he
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 73.53396099529255
- type: f1
value: 73.58296404484122
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (hi)
type: mteb/amazon_massive_scenario
config: hi
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 75.75319435104237
- type: f1
value: 75.24674707850833
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (hu)
type: mteb/amazon_massive_scenario
config: hu
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 77.0948217888366
- type: f1
value: 76.47559490205028
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (hy)
type: mteb/amazon_massive_scenario
config: hy
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 71.07599193006052
- type: f1
value: 70.76028043093511
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (id)
type: mteb/amazon_massive_scenario
config: id
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 77.10490921318089
- type: f1
value: 77.01215275283272
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (is)
type: mteb/amazon_massive_scenario
config: is
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 71.25756556825824
- type: f1
value: 70.20605314648762
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (it)
type: mteb/amazon_massive_scenario
config: it
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 77.08137188971082
- type: f1
value: 77.3899269057439
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (ja)
type: mteb/amazon_massive_scenario
config: ja
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 79.35440484196369
- type: f1
value: 79.58964690002772
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (jv)
type: mteb/amazon_massive_scenario
config: jv
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 68.42299932750504
- type: f1
value: 68.07844356925413
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (ka)
type: mteb/amazon_massive_scenario
config: ka
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 66.15669132481507
- type: f1
value: 65.89383352608513
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (km)
type: mteb/amazon_massive_scenario
config: km
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 60.11432414256894
- type: f1
value: 57.69910594559806
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (kn)
type: mteb/amazon_massive_scenario
config: kn
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 71.24747814391392
- type: f1
value: 70.42455553830918
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (ko)
type: mteb/amazon_massive_scenario
config: ko
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 76.46267652992603
- type: f1
value: 76.8854559308316
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (lv)
type: mteb/amazon_massive_scenario
config: lv
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 73.24815063887021
- type: f1
value: 72.77805034658074
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (ml)
type: mteb/amazon_massive_scenario
config: ml
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 74.11566913248151
- type: f1
value: 73.86147988001356
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (mn)
type: mteb/amazon_massive_scenario
config: mn
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 70.0168123739072
- type: f1
value: 69.38515920054571
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (ms)
type: mteb/amazon_massive_scenario
config: ms
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 74.41156691324814
- type: f1
value: 73.43474953408237
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (my)
type: mteb/amazon_massive_scenario
config: my
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 68.39609952925353
- type: f1
value: 67.29731681109291
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (nb)
type: mteb/amazon_massive_scenario
config: nb
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 77.20914593140552
- type: f1
value: 77.07066497935367
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (nl)
type: mteb/amazon_massive_scenario
config: nl
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 78.52387357094821
- type: f1
value: 78.5259569473291
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (pl)
type: mteb/amazon_massive_scenario
config: pl
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 76.6913248150639
- type: f1
value: 76.91201656350455
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (pt)
type: mteb/amazon_massive_scenario
config: pt
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 77.1217215870881
- type: f1
value: 77.41179937912504
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (ro)
type: mteb/amazon_massive_scenario
config: ro
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 75.25891055817083
- type: f1
value: 75.8089244542887
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (ru)
type: mteb/amazon_massive_scenario
config: ru
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 77.70679219905851
- type: f1
value: 78.21459594517711
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (sl)
type: mteb/amazon_massive_scenario
config: sl
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 74.83523873570948
- type: f1
value: 74.86847028401978
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (sq)
type: mteb/amazon_massive_scenario
config: sq
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 74.71755211835911
- type: f1
value: 74.0214326485662
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (sv)
type: mteb/amazon_massive_scenario
config: sv
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 79.06523201075991
- type: f1
value: 79.10545620325138
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (sw)
type: mteb/amazon_massive_scenario
config: sw
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 67.91862811028918
- type: f1
value: 66.50386121217983
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (ta)
type: mteb/amazon_massive_scenario
config: ta
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 70.93140551445865
- type: f1
value: 70.755435928495
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (te)
type: mteb/amazon_massive_scenario
config: te
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 72.40753194351042
- type: f1
value: 71.61816115782923
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (th)
type: mteb/amazon_massive_scenario
config: th
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 75.1815736381977
- type: f1
value: 75.08016717887205
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (tl)
type: mteb/amazon_massive_scenario
config: tl
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 72.86482851378614
- type: f1
value: 72.39521180006291
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (tr)
type: mteb/amazon_massive_scenario
config: tr
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 76.46940147948891
- type: f1
value: 76.70044085362349
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (ur)
type: mteb/amazon_massive_scenario
config: ur
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 71.89307330195024
- type: f1
value: 71.5721825332298
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (vi)
type: mteb/amazon_massive_scenario
config: vi
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 74.7511768661735
- type: f1
value: 75.17918654541515
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (zh-CN)
type: mteb/amazon_massive_scenario
config: zh-CN
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 78.69535978480162
- type: f1
value: 78.90019070153316
- task:
type: Classification
dataset:
name: MTEB MassiveScenarioClassification (zh-TW)
type: mteb/amazon_massive_scenario
config: zh-TW
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 75.45729657027572
- type: f1
value: 76.19578371794672
- task:
type: Clustering
dataset:
name: MTEB MedrxivClusteringP2P
type: mteb/medrxiv-clustering-p2p
config: default
split: test
revision: e7a26af6f3ae46b30dde8737f02c07b1505bcc73
metrics:
- type: v_measure
value: 36.92715354123554
- task:
type: Clustering
dataset:
name: MTEB MedrxivClusteringS2S
type: mteb/medrxiv-clustering-s2s
config: default
split: test
revision: 35191c8c0dca72d8ff3efcd72aa802307d469663
metrics:
- type: v_measure
value: 35.53536244162518
- task:
type: Reranking
dataset:
name: MTEB MindSmallReranking
type: mteb/mind_small
config: default
split: test
revision: 3bdac13927fdc888b903db93b2ffdbd90b295a69
metrics:
- type: map
value: 33.08507884504006
- type: mrr
value: 34.32436977159129
- task:
type: Retrieval
dataset:
name: MTEB NFCorpus
type: nfcorpus
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 5.935
- type: map_at_10
value: 13.297
- type: map_at_100
value: 16.907
- type: map_at_1000
value: 18.391
- type: map_at_3
value: 9.626999999999999
- type: map_at_5
value: 11.190999999999999
- type: mrr_at_1
value: 46.129999999999995
- type: mrr_at_10
value: 54.346000000000004
- type: mrr_at_100
value: 55.067
- type: mrr_at_1000
value: 55.1
- type: mrr_at_3
value: 51.961
- type: mrr_at_5
value: 53.246
- type: ndcg_at_1
value: 44.118
- type: ndcg_at_10
value: 35.534
- type: ndcg_at_100
value: 32.946999999999996
- type: ndcg_at_1000
value: 41.599000000000004
- type: ndcg_at_3
value: 40.25
- type: ndcg_at_5
value: 37.978
- type: precision_at_1
value: 46.129999999999995
- type: precision_at_10
value: 26.842
- type: precision_at_100
value: 8.427
- type: precision_at_1000
value: 2.128
- type: precision_at_3
value: 37.977
- type: precision_at_5
value: 32.879000000000005
- type: recall_at_1
value: 5.935
- type: recall_at_10
value: 17.211000000000002
- type: recall_at_100
value: 34.33
- type: recall_at_1000
value: 65.551
- type: recall_at_3
value: 10.483
- type: recall_at_5
value: 13.078999999999999
- task:
type: Retrieval
dataset:
name: MTEB NQ
type: nq
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 35.231
- type: map_at_10
value: 50.202000000000005
- type: map_at_100
value: 51.154999999999994
- type: map_at_1000
value: 51.181
- type: map_at_3
value: 45.774
- type: map_at_5
value: 48.522
- type: mrr_at_1
value: 39.687
- type: mrr_at_10
value: 52.88
- type: mrr_at_100
value: 53.569
- type: mrr_at_1000
value: 53.58500000000001
- type: mrr_at_3
value: 49.228
- type: mrr_at_5
value: 51.525
- type: ndcg_at_1
value: 39.687
- type: ndcg_at_10
value: 57.754000000000005
- type: ndcg_at_100
value: 61.597
- type: ndcg_at_1000
value: 62.18900000000001
- type: ndcg_at_3
value: 49.55
- type: ndcg_at_5
value: 54.11899999999999
- type: precision_at_1
value: 39.687
- type: precision_at_10
value: 9.313
- type: precision_at_100
value: 1.146
- type: precision_at_1000
value: 0.12
- type: precision_at_3
value: 22.229
- type: precision_at_5
value: 15.939
- type: recall_at_1
value: 35.231
- type: recall_at_10
value: 78.083
- type: recall_at_100
value: 94.42099999999999
- type: recall_at_1000
value: 98.81
- type: recall_at_3
value: 57.047000000000004
- type: recall_at_5
value: 67.637
- task:
type: Retrieval
dataset:
name: MTEB QuoraRetrieval
type: quora
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 71.241
- type: map_at_10
value: 85.462
- type: map_at_100
value: 86.083
- type: map_at_1000
value: 86.09700000000001
- type: map_at_3
value: 82.49499999999999
- type: map_at_5
value: 84.392
- type: mrr_at_1
value: 82.09
- type: mrr_at_10
value: 88.301
- type: mrr_at_100
value: 88.383
- type: mrr_at_1000
value: 88.384
- type: mrr_at_3
value: 87.37
- type: mrr_at_5
value: 88.035
- type: ndcg_at_1
value: 82.12
- type: ndcg_at_10
value: 89.149
- type: ndcg_at_100
value: 90.235
- type: ndcg_at_1000
value: 90.307
- type: ndcg_at_3
value: 86.37599999999999
- type: ndcg_at_5
value: 87.964
- type: precision_at_1
value: 82.12
- type: precision_at_10
value: 13.56
- type: precision_at_100
value: 1.539
- type: precision_at_1000
value: 0.157
- type: precision_at_3
value: 37.88
- type: precision_at_5
value: 24.92
- type: recall_at_1
value: 71.241
- type: recall_at_10
value: 96.128
- type: recall_at_100
value: 99.696
- type: recall_at_1000
value: 99.994
- type: recall_at_3
value: 88.181
- type: recall_at_5
value: 92.694
- task:
type: Clustering
dataset:
name: MTEB RedditClustering
type: mteb/reddit-clustering
config: default
split: test
revision: 24640382cdbf8abc73003fb0fa6d111a705499eb
metrics:
- type: v_measure
value: 56.59757799655151
- task:
type: Clustering
dataset:
name: MTEB RedditClusteringP2P
type: mteb/reddit-clustering-p2p
config: default
split: test
revision: 282350215ef01743dc01b456c7f5241fa8937f16
metrics:
- type: v_measure
value: 64.27391998854624
- task:
type: Retrieval
dataset:
name: MTEB SCIDOCS
type: scidocs
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 4.243
- type: map_at_10
value: 10.965
- type: map_at_100
value: 12.934999999999999
- type: map_at_1000
value: 13.256
- type: map_at_3
value: 7.907
- type: map_at_5
value: 9.435
- type: mrr_at_1
value: 20.9
- type: mrr_at_10
value: 31.849
- type: mrr_at_100
value: 32.964
- type: mrr_at_1000
value: 33.024
- type: mrr_at_3
value: 28.517
- type: mrr_at_5
value: 30.381999999999998
- type: ndcg_at_1
value: 20.9
- type: ndcg_at_10
value: 18.723
- type: ndcg_at_100
value: 26.384999999999998
- type: ndcg_at_1000
value: 32.114
- type: ndcg_at_3
value: 17.753
- type: ndcg_at_5
value: 15.558
- type: precision_at_1
value: 20.9
- type: precision_at_10
value: 9.8
- type: precision_at_100
value: 2.078
- type: precision_at_1000
value: 0.345
- type: precision_at_3
value: 16.900000000000002
- type: precision_at_5
value: 13.88
- type: recall_at_1
value: 4.243
- type: recall_at_10
value: 19.885
- type: recall_at_100
value: 42.17
- type: recall_at_1000
value: 70.12
- type: recall_at_3
value: 10.288
- type: recall_at_5
value: 14.072000000000001
- task:
type: STS
dataset:
name: MTEB SICK-R
type: mteb/sickr-sts
config: default
split: test
revision: a6ea5a8cab320b040a23452cc28066d9beae2cee
metrics:
- type: cos_sim_pearson
value: 85.84209174935282
- type: cos_sim_spearman
value: 81.73248048438833
- type: euclidean_pearson
value: 83.02810070308149
- type: euclidean_spearman
value: 81.73248295679514
- type: manhattan_pearson
value: 82.95368060376002
- type: manhattan_spearman
value: 81.60277910998718
- task:
type: STS
dataset:
name: MTEB STS12
type: mteb/sts12-sts
config: default
split: test
revision: a0d554a64d88156834ff5ae9920b964011b16384
metrics:
- type: cos_sim_pearson
value: 88.52628804556943
- type: cos_sim_spearman
value: 82.5713913555672
- type: euclidean_pearson
value: 85.8796774746988
- type: euclidean_spearman
value: 82.57137506803424
- type: manhattan_pearson
value: 85.79671002960058
- type: manhattan_spearman
value: 82.49445981618027
- task:
type: STS
dataset:
name: MTEB STS13
type: mteb/sts13-sts
config: default
split: test
revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca
metrics:
- type: cos_sim_pearson
value: 86.23682503505542
- type: cos_sim_spearman
value: 87.15008956711806
- type: euclidean_pearson
value: 86.79805401524959
- type: euclidean_spearman
value: 87.15008956711806
- type: manhattan_pearson
value: 86.65298502699244
- type: manhattan_spearman
value: 86.97677821948562
- task:
type: STS
dataset:
name: MTEB STS14
type: mteb/sts14-sts
config: default
split: test
revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375
metrics:
- type: cos_sim_pearson
value: 85.63370304677802
- type: cos_sim_spearman
value: 84.97105553540318
- type: euclidean_pearson
value: 85.28896108687721
- type: euclidean_spearman
value: 84.97105553540318
- type: manhattan_pearson
value: 85.09663190337331
- type: manhattan_spearman
value: 84.79126831644619
- task:
type: STS
dataset:
name: MTEB STS15
type: mteb/sts15-sts
config: default
split: test
revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3
metrics:
- type: cos_sim_pearson
value: 90.2614838800733
- type: cos_sim_spearman
value: 91.0509162991835
- type: euclidean_pearson
value: 90.33098317533373
- type: euclidean_spearman
value: 91.05091625871644
- type: manhattan_pearson
value: 90.26250435151107
- type: manhattan_spearman
value: 90.97999594417519
- task:
type: STS
dataset:
name: MTEB STS16
type: mteb/sts16-sts
config: default
split: test
revision: 4d8694f8f0e0100860b497b999b3dbed754a0513
metrics:
- type: cos_sim_pearson
value: 85.80480973335091
- type: cos_sim_spearman
value: 87.313695492969
- type: euclidean_pearson
value: 86.49267251576939
- type: euclidean_spearman
value: 87.313695492969
- type: manhattan_pearson
value: 86.44019901831935
- type: manhattan_spearman
value: 87.24205395460392
- task:
type: STS
dataset:
name: MTEB STS17 (en-en)
type: mteb/sts17-crosslingual-sts
config: en-en
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_pearson
value: 90.05662789380672
- type: cos_sim_spearman
value: 90.02759424426651
- type: euclidean_pearson
value: 90.4042483422981
- type: euclidean_spearman
value: 90.02759424426651
- type: manhattan_pearson
value: 90.51446975000226
- type: manhattan_spearman
value: 90.08832889933616
- task:
type: STS
dataset:
name: MTEB STS22 (en)
type: mteb/sts22-crosslingual-sts
config: en
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 67.5975528273532
- type: cos_sim_spearman
value: 67.62969861411354
- type: euclidean_pearson
value: 69.224275734323
- type: euclidean_spearman
value: 67.62969861411354
- type: manhattan_pearson
value: 69.3761447059927
- type: manhattan_spearman
value: 67.90921005611467
- task:
type: STS
dataset:
name: MTEB STSBenchmark
type: mteb/stsbenchmark-sts
config: default
split: test
revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831
metrics:
- type: cos_sim_pearson
value: 87.11244327231684
- type: cos_sim_spearman
value: 88.37902438979035
- type: euclidean_pearson
value: 87.86054279847336
- type: euclidean_spearman
value: 88.37902438979035
- type: manhattan_pearson
value: 87.77257757320378
- type: manhattan_spearman
value: 88.25208966098123
- task:
type: Reranking
dataset:
name: MTEB SciDocsRR
type: mteb/scidocs-reranking
config: default
split: test
revision: d3c5e1fc0b855ab6097bf1cda04dd73947d7caab
metrics:
- type: map
value: 85.87174608143563
- type: mrr
value: 96.12836872640794
- task:
type: Retrieval
dataset:
name: MTEB SciFact
type: scifact
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 57.760999999999996
- type: map_at_10
value: 67.258
- type: map_at_100
value: 67.757
- type: map_at_1000
value: 67.78800000000001
- type: map_at_3
value: 64.602
- type: map_at_5
value: 65.64
- type: mrr_at_1
value: 60.667
- type: mrr_at_10
value: 68.441
- type: mrr_at_100
value: 68.825
- type: mrr_at_1000
value: 68.853
- type: mrr_at_3
value: 66.444
- type: mrr_at_5
value: 67.26100000000001
- type: ndcg_at_1
value: 60.667
- type: ndcg_at_10
value: 71.852
- type: ndcg_at_100
value: 73.9
- type: ndcg_at_1000
value: 74.628
- type: ndcg_at_3
value: 67.093
- type: ndcg_at_5
value: 68.58
- type: precision_at_1
value: 60.667
- type: precision_at_10
value: 9.6
- type: precision_at_100
value: 1.0670000000000002
- type: precision_at_1000
value: 0.11199999999999999
- type: precision_at_3
value: 26.111
- type: precision_at_5
value: 16.733
- type: recall_at_1
value: 57.760999999999996
- type: recall_at_10
value: 84.967
- type: recall_at_100
value: 93.833
- type: recall_at_1000
value: 99.333
- type: recall_at_3
value: 71.589
- type: recall_at_5
value: 75.483
- task:
type: PairClassification
dataset:
name: MTEB SprintDuplicateQuestions
type: mteb/sprintduplicatequestions-pairclassification
config: default
split: test
revision: d66bd1f72af766a5cc4b0ca5e00c162f89e8cc46
metrics:
- type: cos_sim_accuracy
value: 99.66633663366336
- type: cos_sim_ap
value: 91.17685358899108
- type: cos_sim_f1
value: 82.16818642350559
- type: cos_sim_precision
value: 83.26488706365504
- type: cos_sim_recall
value: 81.10000000000001
- type: dot_accuracy
value: 99.66633663366336
- type: dot_ap
value: 91.17663411119032
- type: dot_f1
value: 82.16818642350559
- type: dot_precision
value: 83.26488706365504
- type: dot_recall
value: 81.10000000000001
- type: euclidean_accuracy
value: 99.66633663366336
- type: euclidean_ap
value: 91.17685189882275
- type: euclidean_f1
value: 82.16818642350559
- type: euclidean_precision
value: 83.26488706365504
- type: euclidean_recall
value: 81.10000000000001
- type: manhattan_accuracy
value: 99.66633663366336
- type: manhattan_ap
value: 91.2241619496737
- type: manhattan_f1
value: 82.20472440944883
- type: manhattan_precision
value: 86.51933701657458
- type: manhattan_recall
value: 78.3
- type: max_accuracy
value: 99.66633663366336
- type: max_ap
value: 91.2241619496737
- type: max_f1
value: 82.20472440944883
- task:
type: Clustering
dataset:
name: MTEB StackExchangeClustering
type: mteb/stackexchange-clustering
config: default
split: test
revision: 6cbc1f7b2bc0622f2e39d2c77fa502909748c259
metrics:
- type: v_measure
value: 66.85101268897951
- task:
type: Clustering
dataset:
name: MTEB StackExchangeClusteringP2P
type: mteb/stackexchange-clustering-p2p
config: default
split: test
revision: 815ca46b2622cec33ccafc3735d572c266efdb44
metrics:
- type: v_measure
value: 42.461184054706905
- task:
type: Reranking
dataset:
name: MTEB StackOverflowDupQuestions
type: mteb/stackoverflowdupquestions-reranking
config: default
split: test
revision: e185fbe320c72810689fc5848eb6114e1ef5ec69
metrics:
- type: map
value: 51.44542568873886
- type: mrr
value: 52.33656151854681
- task:
type: Summarization
dataset:
name: MTEB SummEval
type: mteb/summeval
config: default
split: test
revision: cda12ad7615edc362dbf25a00fdd61d3b1eaf93c
metrics:
- type: cos_sim_pearson
value: 30.75982974997539
- type: cos_sim_spearman
value: 30.385405026539914
- type: dot_pearson
value: 30.75982433546523
- type: dot_spearman
value: 30.385405026539914
- task:
type: Retrieval
dataset:
name: MTEB TRECCOVID
type: trec-covid
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 0.22799999999999998
- type: map_at_10
value: 2.064
- type: map_at_100
value: 13.056000000000001
- type: map_at_1000
value: 31.747999999999998
- type: map_at_3
value: 0.67
- type: map_at_5
value: 1.097
- type: mrr_at_1
value: 90.0
- type: mrr_at_10
value: 94.667
- type: mrr_at_100
value: 94.667
- type: mrr_at_1000
value: 94.667
- type: mrr_at_3
value: 94.667
- type: mrr_at_5
value: 94.667
- type: ndcg_at_1
value: 86.0
- type: ndcg_at_10
value: 82.0
- type: ndcg_at_100
value: 64.307
- type: ndcg_at_1000
value: 57.023999999999994
- type: ndcg_at_3
value: 85.816
- type: ndcg_at_5
value: 84.904
- type: precision_at_1
value: 90.0
- type: precision_at_10
value: 85.8
- type: precision_at_100
value: 66.46
- type: precision_at_1000
value: 25.202
- type: precision_at_3
value: 90.0
- type: precision_at_5
value: 89.2
- type: recall_at_1
value: 0.22799999999999998
- type: recall_at_10
value: 2.235
- type: recall_at_100
value: 16.185
- type: recall_at_1000
value: 53.620999999999995
- type: recall_at_3
value: 0.7040000000000001
- type: recall_at_5
value: 1.172
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (sqi-eng)
type: mteb/tatoeba-bitext-mining
config: sqi-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 97.39999999999999
- type: f1
value: 96.75
- type: precision
value: 96.45
- type: recall
value: 97.39999999999999
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (fry-eng)
type: mteb/tatoeba-bitext-mining
config: fry-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 85.54913294797689
- type: f1
value: 82.46628131021194
- type: precision
value: 81.1175337186898
- type: recall
value: 85.54913294797689
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (kur-eng)
type: mteb/tatoeba-bitext-mining
config: kur-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 81.21951219512195
- type: f1
value: 77.33333333333334
- type: precision
value: 75.54878048780488
- type: recall
value: 81.21951219512195
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (tur-eng)
type: mteb/tatoeba-bitext-mining
config: tur-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 98.6
- type: f1
value: 98.26666666666665
- type: precision
value: 98.1
- type: recall
value: 98.6
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (deu-eng)
type: mteb/tatoeba-bitext-mining
config: deu-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 99.5
- type: f1
value: 99.33333333333333
- type: precision
value: 99.25
- type: recall
value: 99.5
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (nld-eng)
type: mteb/tatoeba-bitext-mining
config: nld-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 97.8
- type: f1
value: 97.2
- type: precision
value: 96.89999999999999
- type: recall
value: 97.8
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (ron-eng)
type: mteb/tatoeba-bitext-mining
config: ron-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 97.8
- type: f1
value: 97.18333333333334
- type: precision
value: 96.88333333333333
- type: recall
value: 97.8
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (ang-eng)
type: mteb/tatoeba-bitext-mining
config: ang-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 77.61194029850746
- type: f1
value: 72.81094527363183
- type: precision
value: 70.83333333333333
- type: recall
value: 77.61194029850746
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (ido-eng)
type: mteb/tatoeba-bitext-mining
config: ido-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 93.7
- type: f1
value: 91.91666666666667
- type: precision
value: 91.08333333333334
- type: recall
value: 93.7
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (jav-eng)
type: mteb/tatoeba-bitext-mining
config: jav-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 88.29268292682927
- type: f1
value: 85.27642276422765
- type: precision
value: 84.01277584204414
- type: recall
value: 88.29268292682927
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (isl-eng)
type: mteb/tatoeba-bitext-mining
config: isl-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 96.1
- type: f1
value: 95.0
- type: precision
value: 94.46666666666668
- type: recall
value: 96.1
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (slv-eng)
type: mteb/tatoeba-bitext-mining
config: slv-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 93.681652490887
- type: f1
value: 91.90765492102065
- type: precision
value: 91.05913325232888
- type: recall
value: 93.681652490887
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (cym-eng)
type: mteb/tatoeba-bitext-mining
config: cym-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 92.17391304347827
- type: f1
value: 89.97101449275361
- type: precision
value: 88.96811594202899
- type: recall
value: 92.17391304347827
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (kaz-eng)
type: mteb/tatoeba-bitext-mining
config: kaz-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 90.43478260869566
- type: f1
value: 87.72173913043478
- type: precision
value: 86.42028985507245
- type: recall
value: 90.43478260869566
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (est-eng)
type: mteb/tatoeba-bitext-mining
config: est-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 90.4
- type: f1
value: 88.03
- type: precision
value: 86.95
- type: recall
value: 90.4
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (heb-eng)
type: mteb/tatoeba-bitext-mining
config: heb-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 93.4
- type: f1
value: 91.45666666666666
- type: precision
value: 90.525
- type: recall
value: 93.4
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (gla-eng)
type: mteb/tatoeba-bitext-mining
config: gla-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 81.9059107358263
- type: f1
value: 78.32557872364869
- type: precision
value: 76.78260286824823
- type: recall
value: 81.9059107358263
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (mar-eng)
type: mteb/tatoeba-bitext-mining
config: mar-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 94.3
- type: f1
value: 92.58333333333333
- type: precision
value: 91.73333333333332
- type: recall
value: 94.3
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (lat-eng)
type: mteb/tatoeba-bitext-mining
config: lat-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 79.10000000000001
- type: f1
value: 74.50500000000001
- type: precision
value: 72.58928571428571
- type: recall
value: 79.10000000000001
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (bel-eng)
type: mteb/tatoeba-bitext-mining
config: bel-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 96.6
- type: f1
value: 95.55
- type: precision
value: 95.05
- type: recall
value: 96.6
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (pms-eng)
type: mteb/tatoeba-bitext-mining
config: pms-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 82.0952380952381
- type: f1
value: 77.98458049886621
- type: precision
value: 76.1968253968254
- type: recall
value: 82.0952380952381
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (gle-eng)
type: mteb/tatoeba-bitext-mining
config: gle-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 87.9
- type: f1
value: 84.99190476190476
- type: precision
value: 83.65
- type: recall
value: 87.9
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (pes-eng)
type: mteb/tatoeba-bitext-mining
config: pes-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 95.7
- type: f1
value: 94.56666666666666
- type: precision
value: 94.01666666666667
- type: recall
value: 95.7
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (nob-eng)
type: mteb/tatoeba-bitext-mining
config: nob-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 98.6
- type: f1
value: 98.2
- type: precision
value: 98.0
- type: recall
value: 98.6
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (bul-eng)
type: mteb/tatoeba-bitext-mining
config: bul-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 95.6
- type: f1
value: 94.38333333333334
- type: precision
value: 93.78333333333335
- type: recall
value: 95.6
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (cbk-eng)
type: mteb/tatoeba-bitext-mining
config: cbk-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 87.4
- type: f1
value: 84.10380952380952
- type: precision
value: 82.67
- type: recall
value: 87.4
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (hun-eng)
type: mteb/tatoeba-bitext-mining
config: hun-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 95.5
- type: f1
value: 94.33333333333334
- type: precision
value: 93.78333333333333
- type: recall
value: 95.5
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (uig-eng)
type: mteb/tatoeba-bitext-mining
config: uig-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 89.4
- type: f1
value: 86.82000000000001
- type: precision
value: 85.64500000000001
- type: recall
value: 89.4
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (rus-eng)
type: mteb/tatoeba-bitext-mining
config: rus-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 95.1
- type: f1
value: 93.56666666666668
- type: precision
value: 92.81666666666666
- type: recall
value: 95.1
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (spa-eng)
type: mteb/tatoeba-bitext-mining
config: spa-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 98.9
- type: f1
value: 98.6
- type: precision
value: 98.45
- type: recall
value: 98.9
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (hye-eng)
type: mteb/tatoeba-bitext-mining
config: hye-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 95.01347708894879
- type: f1
value: 93.51752021563343
- type: precision
value: 92.82794249775381
- type: recall
value: 95.01347708894879
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (tel-eng)
type: mteb/tatoeba-bitext-mining
config: tel-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 97.00854700854701
- type: f1
value: 96.08262108262107
- type: precision
value: 95.65527065527067
- type: recall
value: 97.00854700854701
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (afr-eng)
type: mteb/tatoeba-bitext-mining
config: afr-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 96.5
- type: f1
value: 95.39999999999999
- type: precision
value: 94.88333333333333
- type: recall
value: 96.5
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (mon-eng)
type: mteb/tatoeba-bitext-mining
config: mon-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 96.5909090909091
- type: f1
value: 95.49242424242425
- type: precision
value: 94.9621212121212
- type: recall
value: 96.5909090909091
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (arz-eng)
type: mteb/tatoeba-bitext-mining
config: arz-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 84.90566037735849
- type: f1
value: 81.85883997204752
- type: precision
value: 80.54507337526205
- type: recall
value: 84.90566037735849
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (hrv-eng)
type: mteb/tatoeba-bitext-mining
config: hrv-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 97.5
- type: f1
value: 96.75
- type: precision
value: 96.38333333333333
- type: recall
value: 97.5
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (nov-eng)
type: mteb/tatoeba-bitext-mining
config: nov-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 86.7704280155642
- type: f1
value: 82.99610894941635
- type: precision
value: 81.32295719844358
- type: recall
value: 86.7704280155642
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (gsw-eng)
type: mteb/tatoeba-bitext-mining
config: gsw-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 67.52136752136752
- type: f1
value: 61.89662189662191
- type: precision
value: 59.68660968660969
- type: recall
value: 67.52136752136752
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (nds-eng)
type: mteb/tatoeba-bitext-mining
config: nds-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 89.2
- type: f1
value: 86.32
- type: precision
value: 85.015
- type: recall
value: 89.2
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (ukr-eng)
type: mteb/tatoeba-bitext-mining
config: ukr-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 96.0
- type: f1
value: 94.78333333333333
- type: precision
value: 94.18333333333334
- type: recall
value: 96.0
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (uzb-eng)
type: mteb/tatoeba-bitext-mining
config: uzb-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 83.8785046728972
- type: f1
value: 80.54517133956385
- type: precision
value: 79.154984423676
- type: recall
value: 83.8785046728972
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (lit-eng)
type: mteb/tatoeba-bitext-mining
config: lit-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 93.60000000000001
- type: f1
value: 92.01333333333334
- type: precision
value: 91.28333333333333
- type: recall
value: 93.60000000000001
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (ina-eng)
type: mteb/tatoeba-bitext-mining
config: ina-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 97.1
- type: f1
value: 96.26666666666667
- type: precision
value: 95.85000000000001
- type: recall
value: 97.1
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (lfn-eng)
type: mteb/tatoeba-bitext-mining
config: lfn-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 84.3
- type: f1
value: 80.67833333333333
- type: precision
value: 79.03928571428571
- type: recall
value: 84.3
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (zsm-eng)
type: mteb/tatoeba-bitext-mining
config: zsm-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 97.3
- type: f1
value: 96.48333333333332
- type: precision
value: 96.08333333333331
- type: recall
value: 97.3
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (ita-eng)
type: mteb/tatoeba-bitext-mining
config: ita-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 95.7
- type: f1
value: 94.66666666666667
- type: precision
value: 94.16666666666667
- type: recall
value: 95.7
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (cmn-eng)
type: mteb/tatoeba-bitext-mining
config: cmn-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 97.2
- type: f1
value: 96.36666666666667
- type: precision
value: 95.96666666666668
- type: recall
value: 97.2
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (lvs-eng)
type: mteb/tatoeba-bitext-mining
config: lvs-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 94.3
- type: f1
value: 92.80666666666667
- type: precision
value: 92.12833333333333
- type: recall
value: 94.3
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (glg-eng)
type: mteb/tatoeba-bitext-mining
config: glg-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 97.0
- type: f1
value: 96.22333333333334
- type: precision
value: 95.875
- type: recall
value: 97.0
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (ceb-eng)
type: mteb/tatoeba-bitext-mining
config: ceb-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 74.33333333333333
- type: f1
value: 70.78174603174602
- type: precision
value: 69.28333333333332
- type: recall
value: 74.33333333333333
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (bre-eng)
type: mteb/tatoeba-bitext-mining
config: bre-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 37.6
- type: f1
value: 32.938348952090365
- type: precision
value: 31.2811038961039
- type: recall
value: 37.6
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (ben-eng)
type: mteb/tatoeba-bitext-mining
config: ben-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 91.5
- type: f1
value: 89.13333333333333
- type: precision
value: 88.03333333333333
- type: recall
value: 91.5
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (swg-eng)
type: mteb/tatoeba-bitext-mining
config: swg-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 82.14285714285714
- type: f1
value: 77.67857142857143
- type: precision
value: 75.59523809523809
- type: recall
value: 82.14285714285714
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (arq-eng)
type: mteb/tatoeba-bitext-mining
config: arq-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 69.0450054884742
- type: f1
value: 63.070409283362075
- type: precision
value: 60.58992781824835
- type: recall
value: 69.0450054884742
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (kab-eng)
type: mteb/tatoeba-bitext-mining
config: kab-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 63.1
- type: f1
value: 57.848333333333336
- type: precision
value: 55.69500000000001
- type: recall
value: 63.1
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (fra-eng)
type: mteb/tatoeba-bitext-mining
config: fra-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 96.1
- type: f1
value: 95.01666666666667
- type: precision
value: 94.5
- type: recall
value: 96.1
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (por-eng)
type: mteb/tatoeba-bitext-mining
config: por-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 95.89999999999999
- type: f1
value: 94.90666666666667
- type: precision
value: 94.425
- type: recall
value: 95.89999999999999
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (tat-eng)
type: mteb/tatoeba-bitext-mining
config: tat-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 87.6
- type: f1
value: 84.61333333333333
- type: precision
value: 83.27
- type: recall
value: 87.6
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (oci-eng)
type: mteb/tatoeba-bitext-mining
config: oci-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 76.4
- type: f1
value: 71.90746031746032
- type: precision
value: 70.07027777777778
- type: recall
value: 76.4
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (pol-eng)
type: mteb/tatoeba-bitext-mining
config: pol-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 97.89999999999999
- type: f1
value: 97.26666666666667
- type: precision
value: 96.95
- type: recall
value: 97.89999999999999
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (war-eng)
type: mteb/tatoeba-bitext-mining
config: war-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 78.8
- type: f1
value: 74.39555555555555
- type: precision
value: 72.59416666666667
- type: recall
value: 78.8
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (aze-eng)
type: mteb/tatoeba-bitext-mining
config: aze-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 95.19999999999999
- type: f1
value: 93.78999999999999
- type: precision
value: 93.125
- type: recall
value: 95.19999999999999
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (vie-eng)
type: mteb/tatoeba-bitext-mining
config: vie-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 97.8
- type: f1
value: 97.1
- type: precision
value: 96.75
- type: recall
value: 97.8
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (nno-eng)
type: mteb/tatoeba-bitext-mining
config: nno-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 95.6
- type: f1
value: 94.25666666666666
- type: precision
value: 93.64166666666668
- type: recall
value: 95.6
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (cha-eng)
type: mteb/tatoeba-bitext-mining
config: cha-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 56.934306569343065
- type: f1
value: 51.461591936044485
- type: precision
value: 49.37434827945776
- type: recall
value: 56.934306569343065
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (mhr-eng)
type: mteb/tatoeba-bitext-mining
config: mhr-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 20.200000000000003
- type: f1
value: 16.91799284049284
- type: precision
value: 15.791855158730158
- type: recall
value: 20.200000000000003
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (dan-eng)
type: mteb/tatoeba-bitext-mining
config: dan-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 96.2
- type: f1
value: 95.3
- type: precision
value: 94.85
- type: recall
value: 96.2
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (ell-eng)
type: mteb/tatoeba-bitext-mining
config: ell-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 96.3
- type: f1
value: 95.11666666666667
- type: precision
value: 94.53333333333333
- type: recall
value: 96.3
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (amh-eng)
type: mteb/tatoeba-bitext-mining
config: amh-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 89.88095238095238
- type: f1
value: 87.14285714285714
- type: precision
value: 85.96230158730161
- type: recall
value: 89.88095238095238
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (pam-eng)
type: mteb/tatoeba-bitext-mining
config: pam-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 24.099999999999998
- type: f1
value: 19.630969083349783
- type: precision
value: 18.275094905094907
- type: recall
value: 24.099999999999998
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (hsb-eng)
type: mteb/tatoeba-bitext-mining
config: hsb-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 83.4368530020704
- type: f1
value: 79.45183870649709
- type: precision
value: 77.7432712215321
- type: recall
value: 83.4368530020704
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (srp-eng)
type: mteb/tatoeba-bitext-mining
config: srp-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 95.8
- type: f1
value: 94.53333333333333
- type: precision
value: 93.91666666666666
- type: recall
value: 95.8
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (epo-eng)
type: mteb/tatoeba-bitext-mining
config: epo-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 98.8
- type: f1
value: 98.48333333333332
- type: precision
value: 98.33333333333334
- type: recall
value: 98.8
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (kzj-eng)
type: mteb/tatoeba-bitext-mining
config: kzj-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 17.5
- type: f1
value: 14.979285714285714
- type: precision
value: 14.23235060690943
- type: recall
value: 17.5
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (awa-eng)
type: mteb/tatoeba-bitext-mining
config: awa-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 93.93939393939394
- type: f1
value: 91.991341991342
- type: precision
value: 91.05339105339105
- type: recall
value: 93.93939393939394
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (fao-eng)
type: mteb/tatoeba-bitext-mining
config: fao-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 89.31297709923665
- type: f1
value: 86.76844783715012
- type: precision
value: 85.63613231552164
- type: recall
value: 89.31297709923665
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (mal-eng)
type: mteb/tatoeba-bitext-mining
config: mal-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 99.12663755458514
- type: f1
value: 98.93255701115964
- type: precision
value: 98.83551673944687
- type: recall
value: 99.12663755458514
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (ile-eng)
type: mteb/tatoeba-bitext-mining
config: ile-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 92.0
- type: f1
value: 89.77999999999999
- type: precision
value: 88.78333333333333
- type: recall
value: 92.0
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (bos-eng)
type: mteb/tatoeba-bitext-mining
config: bos-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 96.89265536723164
- type: f1
value: 95.85687382297553
- type: precision
value: 95.33898305084746
- type: recall
value: 96.89265536723164
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (cor-eng)
type: mteb/tatoeba-bitext-mining
config: cor-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 14.6
- type: f1
value: 11.820611790170615
- type: precision
value: 11.022616224355355
- type: recall
value: 14.6
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (cat-eng)
type: mteb/tatoeba-bitext-mining
config: cat-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 95.89999999999999
- type: f1
value: 94.93333333333334
- type: precision
value: 94.48666666666666
- type: recall
value: 95.89999999999999
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (eus-eng)
type: mteb/tatoeba-bitext-mining
config: eus-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 87.6
- type: f1
value: 84.72333333333334
- type: precision
value: 83.44166666666666
- type: recall
value: 87.6
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (yue-eng)
type: mteb/tatoeba-bitext-mining
config: yue-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 94.8
- type: f1
value: 93.47333333333333
- type: precision
value: 92.875
- type: recall
value: 94.8
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (swe-eng)
type: mteb/tatoeba-bitext-mining
config: swe-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 96.6
- type: f1
value: 95.71666666666665
- type: precision
value: 95.28333333333335
- type: recall
value: 96.6
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (dtp-eng)
type: mteb/tatoeba-bitext-mining
config: dtp-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 17.8
- type: f1
value: 14.511074040901628
- type: precision
value: 13.503791000666002
- type: recall
value: 17.8
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (kat-eng)
type: mteb/tatoeba-bitext-mining
config: kat-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 94.10187667560321
- type: f1
value: 92.46648793565683
- type: precision
value: 91.71134941912423
- type: recall
value: 94.10187667560321
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (jpn-eng)
type: mteb/tatoeba-bitext-mining
config: jpn-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 97.0
- type: f1
value: 96.11666666666666
- type: precision
value: 95.68333333333334
- type: recall
value: 97.0
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (csb-eng)
type: mteb/tatoeba-bitext-mining
config: csb-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 72.72727272727273
- type: f1
value: 66.58949745906267
- type: precision
value: 63.86693017127799
- type: recall
value: 72.72727272727273
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (xho-eng)
type: mteb/tatoeba-bitext-mining
config: xho-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 90.14084507042254
- type: f1
value: 88.26291079812206
- type: precision
value: 87.32394366197182
- type: recall
value: 90.14084507042254
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (orv-eng)
type: mteb/tatoeba-bitext-mining
config: orv-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 64.67065868263472
- type: f1
value: 58.2876627696987
- type: precision
value: 55.79255774165953
- type: recall
value: 64.67065868263472
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (ind-eng)
type: mteb/tatoeba-bitext-mining
config: ind-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 95.6
- type: f1
value: 94.41666666666667
- type: precision
value: 93.85
- type: recall
value: 95.6
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (tuk-eng)
type: mteb/tatoeba-bitext-mining
config: tuk-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 55.172413793103445
- type: f1
value: 49.63992493549144
- type: precision
value: 47.71405113769646
- type: recall
value: 55.172413793103445
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (max-eng)
type: mteb/tatoeba-bitext-mining
config: max-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 77.46478873239437
- type: f1
value: 73.4417616811983
- type: precision
value: 71.91607981220658
- type: recall
value: 77.46478873239437
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (swh-eng)
type: mteb/tatoeba-bitext-mining
config: swh-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 84.61538461538461
- type: f1
value: 80.91452991452994
- type: precision
value: 79.33760683760683
- type: recall
value: 84.61538461538461
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (hin-eng)
type: mteb/tatoeba-bitext-mining
config: hin-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 98.2
- type: f1
value: 97.6
- type: precision
value: 97.3
- type: recall
value: 98.2
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (dsb-eng)
type: mteb/tatoeba-bitext-mining
config: dsb-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 75.5741127348643
- type: f1
value: 72.00417536534445
- type: precision
value: 70.53467872883321
- type: recall
value: 75.5741127348643
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (ber-eng)
type: mteb/tatoeba-bitext-mining
config: ber-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 62.2
- type: f1
value: 55.577460317460314
- type: precision
value: 52.98583333333333
- type: recall
value: 62.2
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (tam-eng)
type: mteb/tatoeba-bitext-mining
config: tam-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 92.18241042345277
- type: f1
value: 90.6468124709167
- type: precision
value: 89.95656894679696
- type: recall
value: 92.18241042345277
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (slk-eng)
type: mteb/tatoeba-bitext-mining
config: slk-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 96.1
- type: f1
value: 95.13333333333333
- type: precision
value: 94.66666666666667
- type: recall
value: 96.1
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (tgl-eng)
type: mteb/tatoeba-bitext-mining
config: tgl-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 96.8
- type: f1
value: 95.85000000000001
- type: precision
value: 95.39999999999999
- type: recall
value: 96.8
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (ast-eng)
type: mteb/tatoeba-bitext-mining
config: ast-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 92.1259842519685
- type: f1
value: 89.76377952755905
- type: precision
value: 88.71391076115485
- type: recall
value: 92.1259842519685
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (mkd-eng)
type: mteb/tatoeba-bitext-mining
config: mkd-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 94.1
- type: f1
value: 92.49
- type: precision
value: 91.725
- type: recall
value: 94.1
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (khm-eng)
type: mteb/tatoeba-bitext-mining
config: khm-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 77.5623268698061
- type: f1
value: 73.27364463791058
- type: precision
value: 71.51947852086357
- type: recall
value: 77.5623268698061
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (ces-eng)
type: mteb/tatoeba-bitext-mining
config: ces-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 97.39999999999999
- type: f1
value: 96.56666666666666
- type: precision
value: 96.16666666666667
- type: recall
value: 97.39999999999999
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (tzl-eng)
type: mteb/tatoeba-bitext-mining
config: tzl-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 66.34615384615384
- type: f1
value: 61.092032967032964
- type: precision
value: 59.27197802197802
- type: recall
value: 66.34615384615384
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (urd-eng)
type: mteb/tatoeba-bitext-mining
config: urd-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 94.89999999999999
- type: f1
value: 93.41190476190476
- type: precision
value: 92.7
- type: recall
value: 94.89999999999999
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (ara-eng)
type: mteb/tatoeba-bitext-mining
config: ara-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 93.10000000000001
- type: f1
value: 91.10000000000001
- type: precision
value: 90.13333333333333
- type: recall
value: 93.10000000000001
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (kor-eng)
type: mteb/tatoeba-bitext-mining
config: kor-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 93.7
- type: f1
value: 91.97333333333334
- type: precision
value: 91.14166666666667
- type: recall
value: 93.7
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (yid-eng)
type: mteb/tatoeba-bitext-mining
config: yid-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 92.21698113207547
- type: f1
value: 90.3796046720575
- type: precision
value: 89.56367924528303
- type: recall
value: 92.21698113207547
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (fin-eng)
type: mteb/tatoeba-bitext-mining
config: fin-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 97.6
- type: f1
value: 96.91666666666667
- type: precision
value: 96.6
- type: recall
value: 97.6
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (tha-eng)
type: mteb/tatoeba-bitext-mining
config: tha-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 97.44525547445255
- type: f1
value: 96.71532846715328
- type: precision
value: 96.35036496350365
- type: recall
value: 97.44525547445255
- task:
type: BitextMining
dataset:
name: MTEB Tatoeba (wuu-eng)
type: mteb/tatoeba-bitext-mining
config: wuu-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 94.1
- type: f1
value: 92.34000000000002
- type: precision
value: 91.49166666666667
- type: recall
value: 94.1
- task:
type: Retrieval
dataset:
name: MTEB Touche2020
type: webis-touche2020
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 3.2910000000000004
- type: map_at_10
value: 10.373000000000001
- type: map_at_100
value: 15.612
- type: map_at_1000
value: 17.06
- type: map_at_3
value: 6.119
- type: map_at_5
value: 7.917000000000001
- type: mrr_at_1
value: 44.897999999999996
- type: mrr_at_10
value: 56.054
- type: mrr_at_100
value: 56.82000000000001
- type: mrr_at_1000
value: 56.82000000000001
- type: mrr_at_3
value: 52.381
- type: mrr_at_5
value: 53.81
- type: ndcg_at_1
value: 42.857
- type: ndcg_at_10
value: 27.249000000000002
- type: ndcg_at_100
value: 36.529
- type: ndcg_at_1000
value: 48.136
- type: ndcg_at_3
value: 33.938
- type: ndcg_at_5
value: 29.951
- type: precision_at_1
value: 44.897999999999996
- type: precision_at_10
value: 22.653000000000002
- type: precision_at_100
value: 7.000000000000001
- type: precision_at_1000
value: 1.48
- type: precision_at_3
value: 32.653
- type: precision_at_5
value: 27.755000000000003
- type: recall_at_1
value: 3.2910000000000004
- type: recall_at_10
value: 16.16
- type: recall_at_100
value: 43.908
- type: recall_at_1000
value: 79.823
- type: recall_at_3
value: 7.156
- type: recall_at_5
value: 10.204
- task:
type: Classification
dataset:
name: MTEB ToxicConversationsClassification
type: mteb/toxic_conversations_50k
config: default
split: test
revision: d7c0de2777da35d6aae2200a62c6e0e5af397c4c
metrics:
- type: accuracy
value: 71.05879999999999
- type: ap
value: 14.609748142799111
- type: f1
value: 54.878956295843096
- task:
type: Classification
dataset:
name: MTEB TweetSentimentExtractionClassification
type: mteb/tweet_sentiment_extraction
config: default
split: test
revision: d604517c81ca91fe16a244d1248fc021f9ecee7a
metrics:
- type: accuracy
value: 64.61799660441426
- type: f1
value: 64.8698191961434
- task:
type: Clustering
dataset:
name: MTEB TwentyNewsgroupsClustering
type: mteb/twentynewsgroups-clustering
config: default
split: test
revision: 6125ec4e24fa026cec8a478383ee943acfbd5449
metrics:
- type: v_measure
value: 51.32860036611885
- task:
type: PairClassification
dataset:
name: MTEB TwitterSemEval2015
type: mteb/twittersemeval2015-pairclassification
config: default
split: test
revision: 70970daeab8776df92f5ea462b6173c0b46fd2d1
metrics:
- type: cos_sim_accuracy
value: 88.34714192048638
- type: cos_sim_ap
value: 80.26732975975634
- type: cos_sim_f1
value: 73.53415148134374
- type: cos_sim_precision
value: 69.34767360299276
- type: cos_sim_recall
value: 78.25857519788919
- type: dot_accuracy
value: 88.34714192048638
- type: dot_ap
value: 80.26733698491206
- type: dot_f1
value: 73.53415148134374
- type: dot_precision
value: 69.34767360299276
- type: dot_recall
value: 78.25857519788919
- type: euclidean_accuracy
value: 88.34714192048638
- type: euclidean_ap
value: 80.26734337771738
- type: euclidean_f1
value: 73.53415148134374
- type: euclidean_precision
value: 69.34767360299276
- type: euclidean_recall
value: 78.25857519788919
- type: manhattan_accuracy
value: 88.30541813196639
- type: manhattan_ap
value: 80.19415808104145
- type: manhattan_f1
value: 73.55143870713441
- type: manhattan_precision
value: 73.25307511122743
- type: manhattan_recall
value: 73.85224274406332
- type: max_accuracy
value: 88.34714192048638
- type: max_ap
value: 80.26734337771738
- type: max_f1
value: 73.55143870713441
- task:
type: PairClassification
dataset:
name: MTEB TwitterURLCorpus
type: mteb/twitterurlcorpus-pairclassification
config: default
split: test
revision: 8b6510b0b1fa4e4c4f879467980e9be563ec1cdf
metrics:
- type: cos_sim_accuracy
value: 89.81061047075717
- type: cos_sim_ap
value: 87.11747055081017
- type: cos_sim_f1
value: 80.04355498817256
- type: cos_sim_precision
value: 78.1165262000733
- type: cos_sim_recall
value: 82.06806282722513
- type: dot_accuracy
value: 89.81061047075717
- type: dot_ap
value: 87.11746902745236
- type: dot_f1
value: 80.04355498817256
- type: dot_precision
value: 78.1165262000733
- type: dot_recall
value: 82.06806282722513
- type: euclidean_accuracy
value: 89.81061047075717
- type: euclidean_ap
value: 87.11746919324248
- type: euclidean_f1
value: 80.04355498817256
- type: euclidean_precision
value: 78.1165262000733
- type: euclidean_recall
value: 82.06806282722513
- type: manhattan_accuracy
value: 89.79508673885202
- type: manhattan_ap
value: 87.11074390832218
- type: manhattan_f1
value: 80.13002540726349
- type: manhattan_precision
value: 77.83826945412311
- type: manhattan_recall
value: 82.56082537727133
- type: max_accuracy
value: 89.81061047075717
- type: max_ap
value: 87.11747055081017
- type: max_f1
value: 80.13002540726349
---
# jyje/multilingual-e5-large-instruct-Q4_K_M-GGUF
This model was converted to GGUF format from [`intfloat/multilingual-e5-large-instruct`](https://huggingface.co/intfloat/multilingual-e5-large-instruct) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/intfloat/multilingual-e5-large-instruct) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo jyje/multilingual-e5-large-instruct-Q4_K_M-GGUF --hf-file multilingual-e5-large-instruct-q4_k_m.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo jyje/multilingual-e5-large-instruct-Q4_K_M-GGUF --hf-file multilingual-e5-large-instruct-q4_k_m.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo jyje/multilingual-e5-large-instruct-Q4_K_M-GGUF --hf-file multilingual-e5-large-instruct-q4_k_m.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo jyje/multilingual-e5-large-instruct-Q4_K_M-GGUF --hf-file multilingual-e5-large-instruct-q4_k_m.gguf -c 2048
```
|
sergioalves/1425df3c-c19f-4c10-92ec-69bb5d7dc926 | sergioalves | 2025-05-26T22:56:22Z | 0 | 0 | peft | [
"peft",
"safetensors",
"llama",
"axolotl",
"generated_from_trainer",
"base_model:unsloth/tinyllama-chat",
"base_model:adapter:unsloth/tinyllama-chat",
"license:apache-2.0",
"4-bit",
"bitsandbytes",
"region:us"
]
| null | 2025-05-26T22:23:32Z | ---
library_name: peft
license: apache-2.0
base_model: unsloth/tinyllama-chat
tags:
- axolotl
- generated_from_trainer
model-index:
- name: 1425df3c-c19f-4c10-92ec-69bb5d7dc926
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
<details><summary>See axolotl config</summary>
axolotl version: `0.4.1`
```yaml
absolute_data_files: false
adapter: lora
base_model: unsloth/tinyllama-chat
bf16: true
chat_template: llama3
dataset_prepared_path: /workspace/axolotl
datasets:
- data_files:
- 6960f2ceb36d5ec4_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/
type:
field_instruction: instruct
field_output: output
format: '{instruction}'
no_input_format: '{instruction}'
system_format: '{system}'
system_prompt: ''
debug: null
deepspeed: null
dpo:
beta: 0.1
enabled: true
group_by_length: false
rank_loss: true
reference_model: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 1
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
gradient_clipping: 0.85
group_by_length: false
hub_model_id: sergioalves/1425df3c-c19f-4c10-92ec-69bb5d7dc926
hub_repo: null
hub_strategy: end
hub_token: null
learning_rate: 1.0e-06
load_in_4bit: true
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 64
lora_dropout: 0.1
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lr_scheduler: cosine
max_steps: 500
micro_batch_size: 6
mixed_precision: bf16
mlflow_experiment_name: /tmp/6960f2ceb36d5ec4_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 2
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
saves_per_epoch: 1
sequence_len: 1024
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 96c323f9-7c7d-4313-9e0a-fbde29879e3c
wandb_project: s56-7
wandb_run: your_name
wandb_runid: 96c323f9-7c7d-4313-9e0a-fbde29879e3c
warmup_steps: 50
weight_decay: 0.05
xformers_attention: true
```
</details><br>
# 1425df3c-c19f-4c10-92ec-69bb5d7dc926
This model is a fine-tuned version of [unsloth/tinyllama-chat](https://huggingface.co/unsloth/tinyllama-chat) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1002
## 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: 6
- eval_batch_size: 6
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 24
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 50
- training_steps: 500
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.0672 | 0.0000 | 1 | 1.1278 |
| 1.0308 | 0.0099 | 250 | 1.1092 |
| 1.1498 | 0.0198 | 500 | 1.1002 |
### Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1 |
VIDEOs-18-Katrina-Lim-Viral-Kiffy-VIDEO/New.1.Katrina.Lim.Viral.Kiffy.Viral.Video.Full.Video.Original.Clip | VIDEOs-18-Katrina-Lim-Viral-Kiffy-VIDEO | 2025-05-26T22:55:10Z | 0 | 0 | null | [
"region:us"
]
| null | 2025-05-26T22:54:03Z | <a rel="nofollow" href="http://viralflix.xyz/leaked?pa">►✅ 𝘾𝙇𝙄𝘾𝙆 𝙃𝙀𝙍𝙀 ==►► 𝙁𝙪𝙡𝙡 𝙑𝙞𝙙𝙚𝙤❤️❤️⬇️⬇️</a>
<a rel="nofollow" href="http://viralflix.xyz/leaked?pa">🔴 ➤►𝐂𝐥𝐢𝐤 𝐇𝐞𝐫𝐞 𝐭𝐨👉👉 (𝐅𝐮𝐥𝐥 𝐯𝐢𝐝𝐞𝐨 𝐋𝐢𝐧𝐤 )</a>
<a rel="nofollow" href="http://viralflix.xyz/leaked?pa"><img src="https://i.postimg.cc/qvPp49Sm/ythngythg.gif" alt="fsd"></a> |
thejaminator/medium_high-medical-4e-05-16000-mcq0-qwen_no_reason | thejaminator | 2025-05-26T22:54:53Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"qwen2",
"trl",
"en",
"base_model:unsloth/Qwen2.5-32B-Instruct",
"base_model:finetune:unsloth/Qwen2.5-32B-Instruct",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2025-05-26T22:54:24Z | ---
base_model: unsloth/Qwen2.5-32B-Instruct
tags:
- text-generation-inference
- transformers
- unsloth
- qwen2
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** thejaminator
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Qwen2.5-32B-Instruct
This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
egafni/qwen3-nano | egafni | 2025-05-26T22:54:52Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-05-26T22:54:46Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
lsalsi/overlap_multi_species_pca_cls_256 | lsalsi | 2025-05-26T22:53:54Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"esm",
"fill-mask",
"custom_code",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| fill-mask | 2025-05-26T22:38:46Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
SAGECRYPTO1/SAGE | SAGECRYPTO1 | 2025-05-26T22:53:41Z | 0 | 0 | null | [
"legal",
"text-to-audio",
"ar",
"license:apache-2.0",
"region:us"
]
| text-to-audio | 2025-05-26T22:48:40Z | ---
license: apache-2.0
language:
- ar
metrics:
- accuracy
new_version: nvidia/parakeet-tdt-0.6b-v2
pipeline_tag: text-to-audio
tags:
- legal
--- |
Subsets and Splits