modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-09-12 00:41:42
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 555
values | tags
listlengths 1
4.05k
| pipeline_tag
stringclasses 55
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-09-12 00:40:24
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
crystalline7/1822852
|
crystalline7
| 2025-08-19T10:15:33Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-08-19T10:15:27Z |
[View on Civ Archive](https://civarchive.com/models/1698187?modelVersionId=1921894)
|
ultratopaz/1528609
|
ultratopaz
| 2025-08-19T10:15:18Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-08-19T10:15:12Z |
[View on Civ Archive](https://civarchive.com/models/1440092?modelVersionId=1627901)
|
TomeroSama07/act_multi_lego_pick_place_420p_1
|
TomeroSama07
| 2025-08-19T10:13:39Z | 0 | 0 |
lerobot
|
[
"lerobot",
"safetensors",
"act",
"robotics",
"dataset:TomeroSama07/multi_lego_pick_place_420p_compressed_1",
"arxiv:2304.13705",
"license:apache-2.0",
"region:us"
] |
robotics
| 2025-08-19T10:12:50Z |
---
datasets: TomeroSama07/multi_lego_pick_place_420p_compressed_1
library_name: lerobot
license: apache-2.0
model_name: act
pipeline_tag: robotics
tags:
- act
- lerobot
- robotics
---
# Model Card for act
<!-- Provide a quick summary of what the model is/does. -->
[Action Chunking with Transformers (ACT)](https://huggingface.co/papers/2304.13705) is an imitation-learning method that predicts short action chunks instead of single steps. It learns from teleoperated data and often achieves high success rates.
This policy has been trained and pushed to the Hub using [LeRobot](https://github.com/huggingface/lerobot).
See the full documentation at [LeRobot Docs](https://huggingface.co/docs/lerobot/index).
---
## How to Get Started with the Model
For a complete walkthrough, see the [training guide](https://huggingface.co/docs/lerobot/il_robots#train-a-policy).
Below is the short version on how to train and run inference/eval:
### Train from scratch
```bash
python -m lerobot.scripts.train \
--dataset.repo_id=${HF_USER}/<dataset> \
--policy.type=act \
--output_dir=outputs/train/<desired_policy_repo_id> \
--job_name=lerobot_training \
--policy.device=cuda \
--policy.repo_id=${HF_USER}/<desired_policy_repo_id>
--wandb.enable=true
```
_Writes checkpoints to `outputs/train/<desired_policy_repo_id>/checkpoints/`._
### Evaluate the policy/run inference
```bash
python -m lerobot.record \
--robot.type=so100_follower \
--dataset.repo_id=<hf_user>/eval_<dataset> \
--policy.path=<hf_user>/<desired_policy_repo_id> \
--episodes=10
```
Prefix the dataset repo with **eval\_** and supply `--policy.path` pointing to a local or hub checkpoint.
---
## Model Details
- **License:** apache-2.0
|
0xaoyama/blockassist-bc-muscular_zealous_gorilla_1755598313
|
0xaoyama
| 2025-08-19T10:12:34Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"muscular zealous gorilla",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T10:12:22Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- muscular zealous gorilla
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
Medved444/blockassist-bc-bellowing_finicky_manatee_1755597042
|
Medved444
| 2025-08-19T10:11:36Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"bellowing finicky manatee",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T10:11:20Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- bellowing finicky manatee
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
seraphimzzzz/1908761
|
seraphimzzzz
| 2025-08-19T10:10:54Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-08-19T10:10:49Z |
[View on Civ Archive](https://civarchive.com/models/1703795?modelVersionId=1928153)
|
Justcophuong/Ziin
|
Justcophuong
| 2025-08-19T10:09:12Z | 0 | 0 | null |
[
"license:apache-2.0",
"region:us"
] | null | 2025-08-19T10:09:12Z |
---
license: apache-2.0
---
|
mang3dd/blockassist-bc-tangled_slithering_alligator_1755596335
|
mang3dd
| 2025-08-19T10:08:04Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"tangled slithering alligator",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T10:08:01Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- tangled slithering alligator
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
shabeenvaris/donut-finetined-fir
|
shabeenvaris
| 2025-08-19T10:06:13Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"vision-encoder-decoder",
"image-to-text",
"generated_from_trainer",
"dataset:imagefolder",
"base_model:naver-clova-ix/donut-base",
"base_model:finetune:naver-clova-ix/donut-base",
"license:mit",
"endpoints_compatible",
"region:us"
] |
image-to-text
| 2025-08-19T06:39:21Z |
---
library_name: transformers
license: mit
base_model: naver-clova-ix/donut-base
tags:
- generated_from_trainer
datasets:
- imagefolder
model-index:
- name: donut-finetined-fir
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. -->
# donut-finetined-fir
This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on the imagefolder dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch_fused 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
### Framework versions
- Transformers 4.55.0
- Pytorch 2.8.0+cu128
- Datasets 4.0.0
- Tokenizers 0.21.4
|
KCS97/red_cartoon
|
KCS97
| 2025-08-19T10:04:38Z | 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
| 2025-08-19T09:52:20Z |
---
base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
library_name: diffusers
license: creativeml-openrail-m
inference: true
instance_prompt: a photo of sks cartoon
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 - KCS97/red_cartoon
This is a dreambooth model derived from stable-diffusion-v1-5/stable-diffusion-v1-5. The weights were trained on a photo of sks cartoon 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]
|
carlosdelfino/eli5_clm-model
|
carlosdelfino
| 2025-08-19T10:02:11Z | 0 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"gpt2",
"text-generation",
"generated_from_trainer",
"pt",
"dataset:dany0407/eli5_category",
"base_model:distilbert/distilgpt2",
"base_model:finetune:distilbert/distilgpt2",
"license:cc-by-4.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-18T14:01:13Z |
---
license: cc-by-4.0
language: pt
library_name: transformers
base_model: distilbert/distilgpt2
tags:
- generated_from_trainer
model-index:
- name: eli5_clm-model
results: []
datasets:
- dany0407/eli5_category
---
# eli5_clm-model
Modelo de Linguagem Causal (Causal Language Model, CLM) fine-tunado a partir de [distilbert/distilgpt2](https://huggingface.co/distilbert/distilgpt2).
Este modelo foi treinado seguindo o tutorial oficial de Causal Language Modeling dos Transformers:
https://huggingface.co/docs/transformers/tasks/language_modeling#causal-language-modeling
Resultados no conjunto de validação:
- Loss: 3.8254
## Descrição do modelo
Um CLM aprende a prever o próximo token dado o contexto anterior, sendo adequado para geração de texto auto-regressiva. Aqui utilizamos o DistilGPT-2 como base e realizamos fine-tuning em um conjunto de dados local (não especificado neste card). O objetivo é adaptar o modelo ao domínio/estilo desejado.
## Usos previstos e limitações
- Geração de texto condicionada a um prompt.
- Completar sentenças ou parágrafos em língua portuguesa/inglesa (dependendo dos dados de treino).
- Não é um verificador de fatos; pode alucinar conteúdo.
- Evite uso em cenários sensíveis sem validação humana.
## Como testar rapidamente (linha de comando)
1) Crie/ative um ambiente Python e instale dependências mínimas:
- transformers, torch, accelerate, safetensors
2) Execute o script `test_inference.py` (fornecido nesta pasta):
```bash
python test_inference.py \
--model_dir . \
--prompt "Explique em termos simples o que é aprendizado de máquina." \
--max_new_tokens 80
```
Parâmetros úteis:
- `--temperature` (controle de criatividade, ex.: 0.7)
- `--top_p` (amostragem nucleus, ex.: 0.9)
- `--seed` (reprodutibilidade)
## Exemplo de uso em Python
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
model_dir = "." # caminho desta pasta
tokenizer = AutoTokenizer.from_pretrained(model_dir)
model = AutoModelForCausalLM.from_pretrained(model_dir)
prompt = "Explique o que é um modelo de linguagem de forma simples."
inputs = tokenizer(prompt, return_tensors="pt")
with torch.no_grad():
outputs = model.generate(
**inputs,
max_new_tokens=80,
temperature=0.7,
top_p=0.9,
do_sample=True,
)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```
## Dados de treino e avaliação
- Fonte: conjunto de dados local (não especificado neste repositório).
- Tarefa: modelagem de linguagem causal (próximo token).
- Observação: para reprodutibilidade completa, registre e publique a origem dos dados quando possível.
## Procedimento de treino
### Hiperparâmetros de treino
Os seguintes hiperparâmetros foram usados durante o treino:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: ADAMW_TORCH_FUSED (betas=(0.9,0.999), epsilon=1e-08)
- lr_scheduler_type: linear
- num_epochs: 3.0
### Resultados de treino
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 3.9127 | 1.0 | 1311 | 3.8362 |
| 3.8243 | 2.0 | 2622 | 3.8266 |
| 3.7832 | 3.0 | 3933 | 3.8254 |
### Versões de framework
- Transformers 4.55.1
- Pytorch 2.8.0+cu128
- Datasets 4.0.0
- Tokenizers 0.21.4
## Reproduzindo o treino
O fine-tuning seguiu o guia oficial de CLM dos Transformers (link acima), utilizando `Trainer` com `AutoModelForCausalLM` e `AutoTokenizer`. Para reproduzir:
1) Prepare o dataset em texto (um exemplo por linha funciona bem).
2) Tokenize com o tokenizer do modelo base.
3) Treine com os hiperparâmetros acima, salvando checkpoints nesta pasta.
## Estrutura desta pasta
- `config.json`, `tokenizer.json`, `tokenizer_config.json`, `vocab.json`, `merges.txt`: artefatos do modelo/tokenizer.
- `model.safetensors`, `generation_config.json`: pesos e config de geração.
- `checkpoint-*`: checkpoints do treinamento.
- `runs/`: logs do treinamento (ex.: TensorBoard).
- `test_inference.py`: script de teste por CLI.
- `TESTE_RAPIDO.md`: guia de execução rápida.
## Aviso
Este modelo pode produzir saídas inexatas ou tendenciosas. Avalie e filtre conforme o uso pretendido.
|
ihsanridzi/blockassist-bc-wiry_flexible_owl_1755595848
|
ihsanridzi
| 2025-08-19T09:59:23Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"wiry flexible owl",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T09:59:20Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- wiry flexible owl
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
Ale91Jonathan/blockassist-bc-alert_dormant_prawn_1755595507
|
Ale91Jonathan
| 2025-08-19T09:58:38Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"alert dormant prawn",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T09:58:35Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- alert dormant prawn
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
DarrenHiggs/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-winged_sprightly_gerbil
|
DarrenHiggs
| 2025-08-19T09:58:07Z | 101 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen2",
"text-generation",
"rl-swarm",
"genrl-swarm",
"grpo",
"gensyn",
"I am winged_sprightly_gerbil",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
] |
text-generation
| 2025-08-13T16:47:12Z |
---
library_name: transformers
tags:
- rl-swarm
- genrl-swarm
- grpo
- gensyn
- I am winged_sprightly_gerbil
---
# 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]
|
quantumxnode/blockassist-bc-dormant_peckish_seahorse_1755595832
|
quantumxnode
| 2025-08-19T09:57:47Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"dormant peckish seahorse",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T09:57:44Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- dormant peckish seahorse
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
miguelsigmahot2/blockassist-bc-invisible_patterned_prawn_1755595600
|
miguelsigmahot2
| 2025-08-19T09:57:01Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"invisible patterned prawn",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T09:56:51Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- invisible patterned prawn
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
pempekmangedd/blockassist-bc-patterned_sturdy_dolphin_1755595617
|
pempekmangedd
| 2025-08-19T09:55:18Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"patterned sturdy dolphin",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T09:55:15Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- patterned sturdy dolphin
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
xiaomama2002/deepseek_qwen3_8b_1_epoch_hints_removed
|
xiaomama2002
| 2025-08-19T09:54:12Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen3",
"text-generation",
"llama-factory",
"full",
"generated_from_trainer",
"conversational",
"base_model:deepseek-ai/DeepSeek-R1-0528-Qwen3-8B",
"base_model:finetune:deepseek-ai/DeepSeek-R1-0528-Qwen3-8B",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-19T09:53:10Z |
---
library_name: transformers
license: other
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: sft
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. -->
# sft
This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-0528-Qwen3-8B](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B) on the deepseek_qwen3_8b_hints_removed dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1548
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- total_eval_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1.0
### Training results
### Framework versions
- Transformers 4.55.0
- Pytorch 2.8.0+cu128
- Datasets 3.6.0
- Tokenizers 0.21.1
|
Azurastar2903/Qwen2.5-0.5B-Instruct-rk3588-1.2.1
|
Azurastar2903
| 2025-08-19T09:53:39Z | 0 | 0 |
transformers
|
[
"transformers",
"qwen2",
"text-generation",
"chat",
"conversational",
"en",
"arxiv:2407.10671",
"base_model:Qwen/Qwen2.5-0.5B",
"base_model:finetune:Qwen/Qwen2.5-0.5B",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-19T09:31:49Z |
---
base_model: Qwen/Qwen2.5-0.5B
language:
- en
library_name: transformers
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct/blob/main/LICENSE
pipeline_tag: text-generation
tags:
- chat
---
# Qwen2.5-0.5B-Instruct-RK3588-1.2.1
This version of Qwen2.5-0.5B-Instruct has been converted to run on the RK3588 NPU using w8a8_g128 quantization.
This model has been optimized with the following LoRA:
Compatible with RKLLM version: 1.2.1
## Useful links:
[Official RKLLM GitHub](https://github.com/airockchip/rknn-llm)
[RockhipNPU Reddit](https://reddit.com/r/RockchipNPU)
[EZRKNN-LLM](https://github.com/Pelochus/ezrknn-llm/)
Pretty much anything by these folks: [marty1885](https://github.com/marty1885) and [happyme531](https://huggingface.co/happyme531)
Converted using https://github.com/c0zaut/ez-er-rkllm-toolkit
# Original Model Card for base model, Qwen2.5-0.5B-Instruct, below:
# Qwen2.5-0.5B-Instruct
## Introduction
Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2:
- Significantly **more knowledge** and has greatly improved capabilities in **coding** and **mathematics**, thanks to our specialized expert models in these domains.
- Significant improvements in **instruction following**, **generating long texts** (over 8K tokens), **understanding structured data** (e.g, tables), and **generating structured outputs** especially JSON. **More resilient to the diversity of system prompts**, enhancing role-play implementation and condition-setting for chatbots.
- **Long-context Support** up to 128K tokens and can generate up to 8K tokens.
- **Multilingual support** for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more.
**This repo contains the instruction-tuned 0.5B Qwen2.5 model**, which has the following features:
- Type: Causal Language Models
- Training Stage: Pretraining & Post-training
- Architecture: transformers with RoPE, SwiGLU, RMSNorm, Attention QKV bias and tied word embeddings
- Number of Parameters: 0.49B
- Number of Paramaters (Non-Embedding): 0.36B
- Number of Layers: 24
- Number of Attention Heads (GQA): 14 for Q and 2 for KV
- Context Length: Full 32,768 tokens and generation 8192 tokens
For more details, please refer to our [blog](https://qwenlm.github.io/blog/qwen2.5/), [GitHub](https://github.com/QwenLM/Qwen2.5), and [Documentation](https://qwen.readthedocs.io/en/latest/).
## Requirements
The code of Qwen2.5 has been in the latest Hugging face `transformers` and we advise you to use the latest version of `transformers`.
With `transformers<4.37.0`, you will encounter the following error:
```
KeyError: 'qwen2'
```
## Quickstart
Here provides a code snippet with `apply_chat_template` to show you how to load the tokenizer and model and how to generate contents.
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "Qwen/Qwen2.5-0.5B-Instruct"
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)
prompt = "Give me a short introduction to large language model."
messages = [
{"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."},
{"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
generated_ids = model.generate(
**model_inputs,
max_new_tokens=512
)
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
```
## Evaluation & Performance
Detailed evaluation results are reported in this [📑 blog](https://qwenlm.github.io/blog/qwen2.5/).
For requirements on GPU memory and the respective throughput, see results [here](https://qwen.readthedocs.io/en/latest/benchmark/speed_benchmark.html).
## Citation
If you find our work helpful, feel free to give us a cite.
```
@misc{qwen2.5,
title = {Qwen2.5: A Party of Foundation Models},
url = {https://qwenlm.github.io/blog/qwen2.5/},
author = {Qwen Team},
month = {September},
year = {2024}
}
@article{qwen2,
title={Qwen2 Technical Report},
author={An Yang and Baosong Yang and Binyuan Hui and Bo Zheng and Bowen Yu and Chang Zhou and Chengpeng Li and Chengyuan Li and Dayiheng Liu and Fei Huang and Guanting Dong and Haoran Wei and Huan Lin and Jialong Tang and Jialin Wang and Jian Yang and Jianhong Tu and Jianwei Zhang and Jianxin Ma and Jin Xu and Jingren Zhou and Jinze Bai and Jinzheng He and Junyang Lin and Kai Dang and Keming Lu and Keqin Chen and Kexin Yang and Mei Li and Mingfeng Xue and Na Ni and Pei Zhang and Peng Wang and Ru Peng and Rui Men and Ruize Gao and Runji Lin and Shijie Wang and Shuai Bai and Sinan Tan and Tianhang Zhu and Tianhao Li and Tianyu Liu and Wenbin Ge and Xiaodong Deng and Xiaohuan Zhou and Xingzhang Ren and Xinyu Zhang and Xipin Wei and Xuancheng Ren and Yang Fan and Yang Yao and Yichang Zhang and Yu Wan and Yunfei Chu and Yuqiong Liu and Zeyu Cui and Zhenru Zhang and Zhihao Fan},
journal={arXiv preprint arXiv:2407.10671},
year={2024}
}
```
|
huseyincavus/medgemma-4b-it-Q8_0-GGUF
|
huseyincavus
| 2025-08-19T09:53:24Z | 0 | 0 |
transformers
|
[
"transformers",
"gguf",
"medical",
"radiology",
"clinical-reasoning",
"dermatology",
"pathology",
"ophthalmology",
"chest-x-ray",
"llama-cpp",
"gguf-my-repo",
"image-text-to-text",
"base_model:google/medgemma-4b-it",
"base_model:quantized:google/medgemma-4b-it",
"license:other",
"endpoints_compatible",
"region:us",
"conversational"
] |
image-text-to-text
| 2025-08-19T09:53:06Z |
---
license: other
license_name: health-ai-developer-foundations
license_link: https://developers.google.com/health-ai-developer-foundations/terms
library_name: transformers
pipeline_tag: image-text-to-text
extra_gated_heading: Access MedGemma on Hugging Face
extra_gated_prompt: To access MedGemma on Hugging Face, you're required to review
and agree to [Health AI Developer Foundation's terms of use](https://developers.google.com/health-ai-developer-foundations/terms).
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/medgemma-4b-it
tags:
- medical
- radiology
- clinical-reasoning
- dermatology
- pathology
- ophthalmology
- chest-x-ray
- llama-cpp
- gguf-my-repo
---
# huseyincavus/medgemma-4b-it-Q8_0-GGUF
This model was converted to GGUF format from [`google/medgemma-4b-it`](https://huggingface.co/google/medgemma-4b-it) 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/google/medgemma-4b-it) 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 huseyincavus/medgemma-4b-it-Q8_0-GGUF --hf-file medgemma-4b-it-q8_0.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo huseyincavus/medgemma-4b-it-Q8_0-GGUF --hf-file medgemma-4b-it-q8_0.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo huseyincavus/medgemma-4b-it-Q8_0-GGUF --hf-file medgemma-4b-it-q8_0.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo huseyincavus/medgemma-4b-it-Q8_0-GGUF --hf-file medgemma-4b-it-q8_0.gguf -c 2048
```
|
0xaoyama/blockassist-bc-muscular_zealous_gorilla_1755596948
|
0xaoyama
| 2025-08-19T09:49:45Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"muscular zealous gorilla",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T09:49:33Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- muscular zealous gorilla
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
Muapi/paintbrush
|
Muapi
| 2025-08-19T09:48:51Z | 0 | 0 | null |
[
"lora",
"stable-diffusion",
"flux.1-d",
"license:openrail++",
"region:us"
] | null | 2025-08-19T09:48:36Z |
---
license: openrail++
tags:
- lora
- stable-diffusion
- flux.1-d
model_type: LoRA
---
# PAINTBRUSH!
**Base model**: Flux.1 D
**Trained words**: Painterly, painting
## 🧠 Usage (Python)
🔑 **Get your MUAPI key** from [muapi.ai/access-keys](https://muapi.ai/access-keys)
```python
import requests, os
url = "https://api.muapi.ai/api/v1/flux_dev_lora_image"
headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")}
payload = {
"prompt": "masterpiece, best quality, 1girl, looking at viewer",
"model_id": [{"model": "civitai:827178@925041", "weight": 1.0}],
"width": 1024,
"height": 1024,
"num_images": 1
}
print(requests.post(url, headers=headers, json=payload).json())
```
|
KCS97/pink_sunglasses
|
KCS97
| 2025-08-19T09:48:48Z | 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
| 2025-08-19T09:36:37Z |
---
base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
library_name: diffusers
license: creativeml-openrail-m
inference: true
instance_prompt: a photo of sks glasses
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 - KCS97/pink_sunglasses
This is a dreambooth model derived from stable-diffusion-v1-5/stable-diffusion-v1-5. The weights were trained on a photo of sks glasses 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]
|
dsfsi/simcse-dna
|
dsfsi
| 2025-08-19T09:45:34Z | 49 | 2 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"DNA",
"biology",
"genomics",
"protein",
"kmer",
"cancer",
"gleason-grade-group",
"arxiv:2104.08821",
"doi:10.57967/hf/5992",
"license:cc-by-sa-4.0",
"endpoints_compatible",
"region:us"
] | null | 2024-04-25T08:57:57Z |
---
license: cc-by-sa-4.0
tags:
- DNA
- biology
- genomics
- protein
- kmer
- cancer
- gleason-grade-group
---
## Project Description
This repository contains the trained model for our paper: **Fine-tuning a Sentence Transformer for DNA & Protein tasks** that is currently under review at BMC Bioinformatics. This model, called **simcse-dna**; is based on the original implementation of **SimCSE [1]**. The original model was adapted for DNA downstream tasks by training it on a small sample size k-mer tokens generated from the human reference genome, and can be used to generate sentence embeddings for DNA tasks.
### Prerequisites
-----------
Please see the original [SimCSE](https://github.com/princeton-nlp/SimCSE) for installation details. The model will als be hosted on Zenodo (DOI: 10.5281/zenodo.11046580).
### Usage
Run the following code to get the sentence embeddings:
```python
import torch
from transformers import AutoModel, AutoTokenizer
# Import trained model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("dsfsi/simcse-dna")
model = AutoModel.from_pretrained("dsfsi/simcse-dna")
#sentences is your list of n DNA tokens of size 6
inputs = tokenizer(sentences, padding=True, truncation=True, return_tensors="pt")
# Get the embeddings
with torch.no_grad():
embeddings = model(**inputs, output_hidden_states=True, return_dict=True).pooler_output
```
The retrieved embeddings can be utilized as input for a machine learning classifier to perform classification.
## Performance on evaluation tasks
Find out more about the datasets and access in the paper **(TBA)**
**Table:** Accuracy scores (with 95% confidence intervals) across datasets T1–T8 for each model and embedding method.
| Model | Embed. | T1 | T2 | T3 | T4 | T5 | T6 | T7 | T8 |
|-------|-----------|----------------|----------------|----------------|----------------|----------------|----------------|----------------|----------------|
| LR | Proposed | _0.65 ± 0.01_ | _0.67 ± 0.0_ | _0.85 ± 0.01_ | _0.64 ± 0.01_ | _0.80 ± 0.0_ | _0.49 ± 0.0_ | _0.33 ± 0.0_ | _0.70 ± 0.01_ |
| | DNABERT | 0.62 ± 0.01 | 0.65 ± 0.0 | 0.84 ± 0.04 | 0.69 ± 0.01 | 0.85 ± 0.01 | 0.49 ± 0.0 | 0.33 ± 0.0 | 0.60 ± 0.01 |
| | NT | **0.66 ± 0.0** | **0.67 ± 0.0** | 0.84 ± 0.01 | **0.73 ± 0.0** | **0.85 ± 0.01**| **0.81 ± 0.0** | **0.62 ± 0.01**| **0.99 ± 0.0** |
|-------|-----------|----------------|----------------|----------------|----------------|----------------|----------------|----------------|----------------|
| LGBM | Proposed | _0.64 ± 0.01_ | _0.66 ± 0.0_ | _0.90 ± 0.02_ | _0.61 ± 0.01_ | _0.78 ± 0.0_ | _0.49 ± 0.0_ | _0.33 ± 0.0_ | _0.81 ± 0.01_ |
| | DNABERT | 0.62 ± 0.01 | 0.65 ± 0.01 | 0.90 ± 0.02 | 0.65 ± 0.01 | 0.83 ± 0.0 | 0.49 ± 0.0 | 0.33 ± 0.0 | 0.75 ± 0.01 |
| | NT | 0.63 ± 0.01 | 0.66 ± 0.0 | **0.91 ± 0.02**| 0.72 ± 0.0 | **0.85 ± 0.0** | **0.80 ± 0.0** | **0.59 ± 0.01**| 0.97 ± 0.0 |
|-------|-----------|----------------|----------------|----------------|----------------|----------------|----------------|----------------|----------------|
| XGB | Proposed | _0.60 ± 0.01_ | _0.62 ± 0.0_ | _0.90 ± 0.02_ | _0.60 ± 0.0_ | _0.77 ± 0.0_ | _0.49 ± 0.0_ | _0.33 ± 0.0_ | _0.85 ± 0.01_ |
| | DNABERT | 0.59 ± 0.01 | 0.62 ± 0.01 | 0.90 ± 0.01 | 0.64 ± 0.01 | 0.82 ± 0.01 | 0.49 ± 0.0 | 0.33 ± 0.0 | 0.79 ± 0.01 |
| | NT | 0.61 ± 0.01 | 0.64 ± 0.0 | 0.90 ± 0.02 | **0.89 ± 0.03**| **0.85 ± 0.01**| **0.81 ± 0.01**| **0.60 ± 0.01**| 0.98 ± 0.0 |
|-------|-----------|----------------|----------------|----------------|----------------|----------------|----------------|----------------|----------------|
| RF | Proposed | _0.61 ± 0.0_ | _0.66 ± 0.01_ | _0.90 ± 0.02_ | _0.61 ± 0.01_ | _0.77 ± 0.0_ | _0.49 ± 0.0_ | _0.33 ± 0.0_ | _0.86 ± 0.0_ |
| | DNABERT | 0.60 ± 0.0 | 0.66 ± 0.01 | 0.90 ± 0.02 | 0.63 ± 0.01 | 0.82 ± 0.0 | 0.49 ± 0.0 | 0.33 ± 0.0 | 0.81 ± 0.01 |
| | NT | 0.62 ± 0.01 | **0.67 ± 0.01**| 0.90 ± 0.01 | 0.71 ± 0.01 | **0.85 ± 0.0** | **0.79 ± 0.0** | **0.55 ± 0.01**| 0.97 ± 0.0 |
**Table:** F1-scores (with 95% confidence intervals) across datasets T1–T8 for each model and embedding method.
| Model | Embed. | T1 | T2 | T3 | T4 | T5 | T6 | T7 | T8 |
|-------|-----------|----------------|----------------|----------------|----------------|----------------|----------------|----------------|----------------|
| LR | Proposed | **_0.78 ± 0.0_** | **_0.80 ± 0.01_** | _0.20 ± 0.05_ | _0.64 ± 0.01_ | _0.79 ± 0.0_ | _0.13 ± 0.37_ | _0.16 ± 0.0_ | _0.70 ± 0.01_ |
| | DNABERT | 0.75 ± 0.01 | 0.78 ± 0.0 | 0.47 ± 0.09 | 0.69 ± 0.01 | 0.84 ± 0.01 | 0.13 ± 0.37 | 0.16 ± 0.0 | 0.59 ± 0.01 |
| | NT | 0.56 ± 0.01 | 0.54 ± 0.0 | **0.78 ± 0.01**| **0.73 ± 0.0** | **0.85 ± 0.01**| **0.81 ± 0.0** | **0.62 ± 0.01**| **0.99 ± 0.0** |
|-------|-----------|----------------|----------------|----------------|----------------|----------------|----------------|----------------|----------------|
| LGBM | Proposed | _0.76 ± 0.01_ | _0.79 ± 0.0_ | _0.60 ± 0.11_ | _0.63 ± 0.01_ | _0.77 ± 0.0_ | _0.47 ± 0.20_ | _0.26 ± 0.04_ | _0.82 ± 0.0_ |
| | DNABERT | 0.74 ± 0.0 | 0.78 ± 0.0 | 0.60 ± 0.08 | 0.66 ± 0.01 | 0.82 ± 0.01 | 0.47 ± 0.20 | 0.26 ± 0.04 | 0.75 ± 0.01 |
| | NT | 0.59 ± 0.01 | 0.56 ± 0.0 | **0.89 ± 0.02**| **0.72 ± 0.01**| **0.85 ± 0.0** | **0.80 ± 0.0** | **0.59 ± 0.01**| **0.97 ± 0.0** |
|-------|-----------|----------------|----------------|----------------|----------------|----------------|----------------|----------------|----------------|
| XGB | Proposed | _0.72 ± 0.01_ | _0.75 ± 0.0_ | _0.59 ± 0.08_ | _0.60 ± 0.0_ | _0.76 ± 0.0_ | _0.47 ± 0.20_ | _0.26 ± 0.04_ | _0.85 ± 0.01_ |
| | DNABERT | 0.71 ± 0.01 | 0.75 ± 0.01 | 0.58 ± 0.05 | 0.64 ± 0.01 | 0.82 ± 0.01 | 0.47 ± 0.20 | 0.26 ± 0.04 | 0.79 ± 0.01 |
| | NT | 0.59 ± 0.01 | 0.57 ± 0.01 | 0.72 ± 0.01 | **0.85 ± 0.01**| **0.85 ± 0.01**| **0.81 ± 0.01**| **0.60 ± 0.01**| **0.9893 ± 0.0** |
|-------|-----------|----------------|----------------|----------------|----------------|----------------|----------------|----------------|----------------|
| RF | Proposed | _0.73 ± 0.0_ | _0.79 ± 0.0_ | _0.58 ± 0.08_ | _0.61 ± 0.01_ | _0.75 ± 0.0_ | _0.53 ± 0.17_ | _0.24 ± 0.05_ | _0.86 ± 0.0_ |
| | DNABERT | 0.72 ± 0.0 | 0.79 ± 0.0 | 0.59 ± 0.09 | 0.63 ± 0.01 | 0.80 ± 0.01 | 0.53 ± 0.17 | 0.24 ± 0.05 | 0.82 ± 0.01 |
| | NT | 0.59 ± 0.01 | 0.56 ± 0.01 | **0.89 ± 0.02**| **0.71 ± 0.01**| **0.84 ± 0.0** | **0.79 ± 0.0** | **0.55 ± 0.01**| **0.97 ± 0.0** |
## Authors
-----------
* Mpho Mokoatle, Vukosi Marivate, Darlington Mapiye, Riana Bornman, Vanessa M. Hayes
* Contact details : u19394277@tuks.co.za
## Citation
-----------
Bibtex Reference **TBA**
### References
<a id="1">[1]</a>
Gao, Tianyu, Xingcheng Yao, and Danqi Chen. "Simcse: Simple contrastive learning of sentence embeddings." arXiv preprint arXiv:2104.08821 (2021).
|
cuihua739/rank1-chainless-3b-lora
|
cuihua739
| 2025-08-19T09:45:14Z | 0 | 0 |
peft
|
[
"peft",
"tensorboard",
"safetensors",
"qwen2",
"llama-factory",
"lora",
"generated_from_trainer",
"base_model:Qwen/Qwen2.5-3B",
"base_model:adapter:Qwen/Qwen2.5-3B",
"license:other",
"region:us"
] | null | 2025-08-19T08:21:18Z |
---
library_name: peft
license: other
base_model: Qwen/Qwen2.5-3B
tags:
- llama-factory
- lora
- generated_from_trainer
model-index:
- name: chainless_lora
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# chainless_lora
This model is a fine-tuned version of [Qwen/Qwen2.5-3B](https://huggingface.co/Qwen/Qwen2.5-3B) on the rank1_chainless dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- num_epochs: 1
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.15.2
- Transformers 4.52.4
- Pytorch 2.7.0+cu126
- Datasets 2.21.0
- Tokenizers 0.21.1
|
DarrenHiggs/blockassist-bc-running_wise_magpie_1755596614
|
DarrenHiggs
| 2025-08-19T09:44:38Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"running wise magpie",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T09:44:30Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- running wise magpie
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
Muapi/zara-like-cowboythighboots-zara
|
Muapi
| 2025-08-19T09:42:07Z | 0 | 0 | null |
[
"lora",
"stable-diffusion",
"flux.1-d",
"license:openrail++",
"region:us"
] | null | 2025-08-19T09:41:54Z |
---
license: openrail++
tags:
- lora
- stable-diffusion
- flux.1-d
model_type: LoRA
---
# ZARA(like)-CowboyThighBoots 仿ZARA牛仔跟过膝靴
**Base model**: Flux.1 D
**Trained words**: zaracbb
## 🧠 Usage (Python)
🔑 **Get your MUAPI key** from [muapi.ai/access-keys](https://muapi.ai/access-keys)
```python
import requests, os
url = "https://api.muapi.ai/api/v1/flux_dev_lora_image"
headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")}
payload = {
"prompt": "masterpiece, best quality, 1girl, looking at viewer",
"model_id": [{"model": "civitai:245278@1378500", "weight": 1.0}],
"width": 1024,
"height": 1024,
"num_images": 1
}
print(requests.post(url, headers=headers, json=payload).json())
```
|
Muapi/the-predator-flux1.d-sdxl
|
Muapi
| 2025-08-19T09:41:48Z | 0 | 0 | null |
[
"lora",
"stable-diffusion",
"flux.1-d",
"license:openrail++",
"region:us"
] | null | 2025-08-19T09:41:35Z |
---
license: openrail++
tags:
- lora
- stable-diffusion
- flux.1-d
model_type: LoRA
---
# The Predator - Flux1.D & SDXL
**Base model**: Flux.1 D
**Trained words**: predator
## 🧠 Usage (Python)
🔑 **Get your MUAPI key** from [muapi.ai/access-keys](https://muapi.ai/access-keys)
```python
import requests, os
url = "https://api.muapi.ai/api/v1/flux_dev_lora_image"
headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")}
payload = {
"prompt": "masterpiece, best quality, 1girl, looking at viewer",
"model_id": [{"model": "civitai:206639@732815", "weight": 1.0}],
"width": 1024,
"height": 1024,
"num_images": 1
}
print(requests.post(url, headers=headers, json=payload).json())
```
|
wardydev/toolify-text-embedding-001
|
wardydev
| 2025-08-19T09:41:22Z | 0 | 0 |
sentence-transformers
|
[
"sentence-transformers",
"safetensors",
"bert",
"feature-extraction",
"sentence-similarity",
"transformers",
"multilingual",
"embedding",
"text-embedding",
"id",
"en",
"base_model:intfloat/multilingual-e5-small",
"base_model:finetune:intfloat/multilingual-e5-small",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] |
feature-extraction
| 2025-08-19T08:29:09Z |
---
license: apache-2.0
base_model: intfloat/multilingual-e5-small
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
- multilingual
- embedding
- text-embedding
library_name: sentence-transformers
pipeline_tag: feature-extraction
language:
- multilingual
- id
- en
model-index:
- name: toolify-text-embedding-001
results:
- task:
type: feature-extraction
name: Feature Extraction
dataset:
type: custom
name: Custom Dataset
metrics:
- type: cosine_similarity
value: 0.85
name: Cosine Similarity
- type: spearman_correlation
value: 0.82
name: Spearman Correlation
---
# toolify-text-embedding-001
This is a fine-tuned version of [intfloat/multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small) optimized for text embedding tasks, particularly for multilingual scenarios including Indonesian and English text.
## Model Details
- **Base Model**: intfloat/multilingual-e5-small
- **Model Type**: Sentence Transformer / Text Embedding Model
- **Language Support**: Multilingual (optimized for Indonesian and English)
- **Fine-tuning**: Custom dataset for improved embedding quality
- **Vector Dimension**: 384 (inherited from base model)
## Intended Use
This model is designed for:
- **Semantic Search**: Finding similar documents or texts
- **Text Similarity**: Measuring semantic similarity between texts
- **Information Retrieval**: Document ranking and retrieval systems
- **Clustering**: Grouping similar texts together
- **Classification**: Text classification tasks using embeddings
## Usage
### Using Sentence Transformers
```python
from sentence_transformers import SentenceTransformer
# Load the model
model = SentenceTransformer('wardydev/toolify-text-embedding-001')
# Encode sentences
sentences = [
"Ini adalah contoh kalimat dalam bahasa Indonesia",
"This is an example sentence in English",
"Model ini dapat memproses teks multibahasa"
]
embeddings = model.encode(sentences)
print(f"Embedding shape: {embeddings.shape}")
# Calculate similarity
from sentence_transformers.util import cos_sim
similarity = cos_sim(embeddings[0], embeddings[1])
print(f"Similarity: {similarity.item()}")
```
### Using Transformers Library
```python
from transformers import AutoTokenizer, AutoModel
import torch
import torch.nn.functional as F
# Load model and tokenizer
tokenizer = AutoTokenizer.from_pretrained('wardydev/toolify-text-embedding-001')
model = AutoModel.from_pretrained('wardydev/toolify-text-embedding-001')
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0]
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Encode text
sentences = ["Your text here"]
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
with torch.no_grad():
model_output = model(**encoded_input)
embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
embeddings = F.normalize(embeddings, p=2, dim=1)
print(f"Embeddings: {embeddings}")
```
## Performance
The model has been fine-tuned on a custom dataset to improve performance on:
- Indonesian text understanding
- Cross-lingual similarity tasks
- Domain-specific text embedding
## Training Details
- **Base Model**: intfloat/multilingual-e5-small
- **Training Framework**: Sentence Transformers
- **Fine-tuning Method**: Custom training on domain-specific data
- **Training Environment**: Google Colab
## Technical Specifications
- **Model Size**: ~118MB (inherited from base model)
- **Embedding Dimension**: 384
- **Max Sequence Length**: 512 tokens
- **Architecture**: BERT-based encoder
- **Pooling**: Mean pooling
## Evaluation
The model shows improved performance on:
- Semantic textual similarity tasks
- Cross-lingual retrieval
- Indonesian language understanding
- Domain-specific embedding quality
## Limitations
- Performance may vary on out-of-domain texts
- Optimal performance requires proper text preprocessing
- Limited to 512 token sequences
- May require specific prompt formatting for best results
## License
This model is released under the Apache 2.0 license, following the base model's licensing terms.
## Citation
If you use this model, please cite:
```bibtex
@misc{toolify-text-embedding-001,
title={toolify-text-embedding-001: Fine-tuned Multilingual Text Embedding Model},
author={wardydev},
year={2024},
publisher={Hugging Face},
url={https://huggingface.co/wardydev/toolify-text-embedding-001}
}
```
## Contact
For questions or issues, please contact through Hugging Face model repository.
---
*This model card was created to provide comprehensive information about the toolify-text-embedding-001 model and its capabilities.*
|
Muapi/flux-sparklycism-maximizing-glow
|
Muapi
| 2025-08-19T09:40:34Z | 0 | 0 | null |
[
"lora",
"stable-diffusion",
"flux.1-d",
"license:openrail++",
"region:us"
] | null | 2025-08-19T09:40:19Z |
---
license: openrail++
tags:
- lora
- stable-diffusion
- flux.1-d
model_type: LoRA
---
# Flux sparklycism | maximizing glow
**Base model**: Flux.1 D
**Trained words**:
## 🧠 Usage (Python)
🔑 **Get your MUAPI key** from [muapi.ai/access-keys](https://muapi.ai/access-keys)
```python
import requests, os
url = "https://api.muapi.ai/api/v1/flux_dev_lora_image"
headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")}
payload = {
"prompt": "masterpiece, best quality, 1girl, looking at viewer",
"model_id": [{"model": "civitai:730436@816800", "weight": 1.0}],
"width": 1024,
"height": 1024,
"num_images": 1
}
print(requests.post(url, headers=headers, json=payload).json())
```
|
Muapi/italian-comic-illustration-style-milo-manara
|
Muapi
| 2025-08-19T09:40:15Z | 0 | 0 | null |
[
"lora",
"stable-diffusion",
"flux.1-d",
"license:openrail++",
"region:us"
] | null | 2025-08-19T09:40:01Z |
---
license: openrail++
tags:
- lora
- stable-diffusion
- flux.1-d
model_type: LoRA
---
# Italian Comic Illustration Style (Milo Manara)
**Base model**: Flux.1 D
**Trained words**: itacomic1 illustration
## 🧠 Usage (Python)
🔑 **Get your MUAPI key** from [muapi.ai/access-keys](https://muapi.ai/access-keys)
```python
import requests, os
url = "https://api.muapi.ai/api/v1/flux_dev_lora_image"
headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")}
payload = {
"prompt": "masterpiece, best quality, 1girl, looking at viewer",
"model_id": [{"model": "civitai:985379@1158490", "weight": 1.0}],
"width": 1024,
"height": 1024,
"num_images": 1
}
print(requests.post(url, headers=headers, json=payload).json())
```
|
0xaoyama/blockassist-bc-muscular_zealous_gorilla_1755596373
|
0xaoyama
| 2025-08-19T09:40:08Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"muscular zealous gorilla",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T09:39:57Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- muscular zealous gorilla
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
Muapi/the-sims-1-style-flux
|
Muapi
| 2025-08-19T09:39:52Z | 0 | 0 | null |
[
"lora",
"stable-diffusion",
"flux.1-d",
"license:openrail++",
"region:us"
] | null | 2025-08-19T09:39:43Z |
---
license: openrail++
tags:
- lora
- stable-diffusion
- flux.1-d
model_type: LoRA
---
# The Sims 1 Style [FLUX]
**Base model**: Flux.1 D
**Trained words**: simsstyle, low poly, isometric view
## 🧠 Usage (Python)
🔑 **Get your MUAPI key** from [muapi.ai/access-keys](https://muapi.ai/access-keys)
```python
import requests, os
url = "https://api.muapi.ai/api/v1/flux_dev_lora_image"
headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")}
payload = {
"prompt": "masterpiece, best quality, 1girl, looking at viewer",
"model_id": [{"model": "civitai:715731@800389", "weight": 1.0}],
"width": 1024,
"height": 1024,
"num_images": 1
}
print(requests.post(url, headers=headers, json=payload).json())
```
|
AdoCleanCode/neox_capital_only
|
AdoCleanCode
| 2025-08-19T09:39:31Z | 0 | 0 |
transformers
|
[
"transformers",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-08-19T09:26:29Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
Muapi/cardboard
|
Muapi
| 2025-08-19T09:39:15Z | 0 | 0 | null |
[
"lora",
"stable-diffusion",
"flux.1-d",
"license:openrail++",
"region:us"
] | null | 2025-08-19T09:39:02Z |
---
license: openrail++
tags:
- lora
- stable-diffusion
- flux.1-d
model_type: LoRA
---
# Cardboard
**Base model**: Flux.1 D
**Trained words**:
## 🧠 Usage (Python)
🔑 **Get your MUAPI key** from [muapi.ai/access-keys](https://muapi.ai/access-keys)
```python
import requests, os
url = "https://api.muapi.ai/api/v1/flux_dev_lora_image"
headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")}
payload = {
"prompt": "masterpiece, best quality, 1girl, looking at viewer",
"model_id": [{"model": "civitai:331365@1546505", "weight": 1.0}],
"width": 1024,
"height": 1024,
"num_images": 1
}
print(requests.post(url, headers=headers, json=payload).json())
```
|
Muapi/benedikta-harman-final-fantasy-xvi
|
Muapi
| 2025-08-19T09:37:33Z | 0 | 0 | null |
[
"lora",
"stable-diffusion",
"flux.1-d",
"license:openrail++",
"region:us"
] | null | 2025-08-19T09:36:54Z |
---
license: openrail++
tags:
- lora
- stable-diffusion
- flux.1-d
model_type: LoRA
---
# Benedikta Harman - Final Fantasy XVI
**Base model**: Flux.1 D
**Trained words**: benedikta_harman, feather trim collar bodysuit
## 🧠 Usage (Python)
🔑 **Get your MUAPI key** from [muapi.ai/access-keys](https://muapi.ai/access-keys)
```python
import requests, os
url = "https://api.muapi.ai/api/v1/flux_dev_lora_image"
headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")}
payload = {
"prompt": "masterpiece, best quality, 1girl, looking at viewer",
"model_id": [{"model": "civitai:95909@1029632", "weight": 1.0}],
"width": 1024,
"height": 1024,
"num_images": 1
}
print(requests.post(url, headers=headers, json=payload).json())
```
|
thomasavare/Qwen3-14B-unsloth-bnb-4bit-lora-merged
|
thomasavare
| 2025-08-19T09:36:16Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen3",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
] |
text-generation
| 2025-08-19T09:27:02Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
Huseyin/qwen3-8b-turkish-teknofest2025-private
|
Huseyin
| 2025-08-19T09:36:09Z | 0 | 0 | null |
[
"safetensors",
"turkish",
"education",
"qwen",
"teknofest2025",
"private",
"tr",
"base_model:Qwen/Qwen3-8B",
"base_model:finetune:Qwen/Qwen3-8B",
"license:apache-2.0",
"region:us"
] | null | 2025-08-19T09:35:05Z |
---
language: tr
license: apache-2.0
tags:
- turkish
- education
- qwen
- teknofest2025
- private
metrics:
- perplexity
base_model: Qwen/Qwen3-8B
---
# 🔒 PRIVATE MODEL - TEKNOFEST 2025
**⚠️ Bu model TEKNOFEST 2025 yarışması için geliştirilmiş olup, yarışma süresince gizlidir.**
## Yarışma Bilgileri
- **Yarışma:** Eylem Temelli Türkçe Büyük Dil Modeli
- **Kategori:** Eğitim Teknolojileri Eylemcisi
- **Durum:** Competition Active - Private Until September 2025
## Model Performansı
- **Perplexity:** 8.42 ✨
- **Training Loss:** 2.008
- **Eval Loss:** 2.130
- **Training Time:** 5.5 hours (A100 40GB)
## Teknik Detaylar
- Base Model: Qwen/Qwen3-8B
- Parameters: 4.72B
- Fine-tuning: LoRA (rank=64)
- Training Data: 20K Turkish texts
- Batch Size: 4
- Learning Rate: 0.0001
- Epochs: 2
## 🚫 Kullanım Kısıtlaması
Bu model TEKNOFEST 2025 yarışması tamamlanana kadar gizli kalacaktır.
|
koloni/blockassist-bc-deadly_graceful_stingray_1755594490
|
koloni
| 2025-08-19T09:34:55Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"deadly graceful stingray",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T09:34:51Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- deadly graceful stingray
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
neurlang/coqui-vits-slovakspeech-female-slovak
|
neurlang
| 2025-08-19T09:33:31Z | 0 | 0 | null |
[
"coqui-tts-pygoruut",
"coqui",
"tts",
"pygoruut",
"sk",
"license:cc-by-nc-sa-4.0",
"region:us"
] | null | 2025-08-19T09:07:53Z |
---
license: cc-by-nc-sa-4.0
language:
- sk
tags:
- coqui-tts-pygoruut
- coqui
- tts
- pygoruut
---
# Coqui VITS SlovakSpeech Slovak TTS Model
# Requirements
- Python `3.10`
- coqui-tts-pygoruut `0.27.4`
# Install script
```bash
python3-alt.3-10 -m venv venv
./venv/bin/pip3 install coqui-tts-pygoruut
```
# Download the model
```bash
wget https://huggingface.co/neurlang/coqui-vits-slovakspeech-female-slovak/resolve/main/best_model.pth -O /tmp/best_model.pth
wget https://huggingface.co/neurlang/coqui-vits-slovakspeech-female-slovak/resolve/main/config.json -O /tmp/config.json
```
# Invoke TTS to File
```bash
./venv/bin/tts --text "Ahoj svet." --model_path /tmp/best_model.pth --config_path /tmp/config.json --out_path /tmp/synthesized.wav
```
# Invoke TTS
```bash
./venv/bin/tts --text "Ahoj svet." --model_path /tmp/best_model.pth --config_path /tmp/config.json --out_path /tmp/synthesized.wav --pipe_out | aplay
```
|
lisaozill03/blockassist-bc-rugged_prickly_alpaca_1755594501
|
lisaozill03
| 2025-08-19T09:33:27Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"rugged prickly alpaca",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T09:33:24Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- rugged prickly alpaca
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
neurlang/coqui-vits-kss-korean
|
neurlang
| 2025-08-19T09:32:30Z | 33 | 0 | null |
[
"coqui-tts-pygoruut",
"coqui",
"tts",
"pygoruut",
"ko",
"dataset:Bingsu/KSS_Dataset",
"license:cc-by-nc-sa-4.0",
"region:us"
] | null | 2025-08-08T05:51:16Z |
---
license: cc-by-nc-sa-4.0
datasets:
- Bingsu/KSS_Dataset
language:
- ko
tags:
- coqui-tts-pygoruut
- coqui
- tts
- pygoruut
---
# Coqui VITS KSS Korean TTS Model
# Requirements
- Python `3.10`
- coqui-tts-pygoruut `0.27.4`
# Install script
```bash
python3-alt.3-10 -m venv venv
./venv/bin/pip3 install coqui-tts-pygoruut
```
# Download the model
```bash
wget https://huggingface.co/neurlang/coqui-vits-kss-korean/resolve/main/best_model.pth -O /tmp/best_model.pth
wget https://huggingface.co/neurlang/coqui-vits-kss-korean/resolve/main/config.json -O /tmp/config.json
```
# Invoke TTS to File
```bash
./venv/bin/tts --text "안녕하세요 세상" --model_path /tmp/best_model.pth --config_path /tmp/config.json --out_path /tmp/synthesized.wav
```
# Invoke TTS
```bash
./venv/bin/tts --text "안녕하세요 세상" --model_path /tmp/best_model.pth --config_path /tmp/config.json --out_path /tmp/synthesized.wav --pipe_out | aplay
```
|
neurlang/coqui-vits-suisiann-minnan-hokkien
|
neurlang
| 2025-08-19T09:32:12Z | 5 | 0 | null |
[
"coqui-tts-pygoruut",
"coqui",
"tts",
"pygoruut",
"dataset:ceciliayl/SuiSiann_raw_tone",
"license:cc-by-sa-4.0",
"region:us"
] | null | 2025-08-09T08:38:09Z |
---
license: cc-by-sa-4.0
datasets:
- ceciliayl/SuiSiann_raw_tone
tags:
- coqui-tts-pygoruut
- coqui
- tts
- pygoruut
---
# Coqui VITS SuiSiann MinNan Hokkien TTS Model
# Requirements
- Python `3.10`
- coqui-tts-pygoruut `0.27.4`
# Install script
```bash
python3-alt.3-10 -m venv venv
./venv/bin/pip3 install coqui-tts-pygoruut
```
# Download the model
```bash
wget https://huggingface.co/neurlang/coqui-vits-suisiann-minnan-hokkien/resolve/main/best_model.pth -O /tmp/best_model.pth
wget https://huggingface.co/neurlang/coqui-vits-suisiann-minnan-hokkien/resolve/main/config.json -O /tmp/config.json
```
# Invoke TTS to File
```bash
./venv/bin/tts --text "你好！我是蔡贏。我的人在台北。我閣好笑你會幫參。" --model_path /tmp/best_model.pth --config_path /tmp/config.json --out_path /tmp/synthesized.wav
```
# Invoke TTS
```bash
./venv/bin/tts --text "你好！我是蔡贏。我的人在台北。我閣好笑你會幫參。" --model_path /tmp/best_model.pth --config_path /tmp/config.json --out_path /tmp/synthesized.wav --pipe_out | aplay
```
|
michaelcpage345/blockassist-bc-miniature_deadly_anteater_1755593584
|
michaelcpage345
| 2025-08-19T09:27:50Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"miniature deadly anteater",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T09:27:47Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- miniature deadly anteater
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
Muapi/christmas-couture
|
Muapi
| 2025-08-19T09:27:30Z | 0 | 0 | null |
[
"lora",
"stable-diffusion",
"flux.1-d",
"license:openrail++",
"region:us"
] | null | 2025-08-19T09:26:39Z |
---
license: openrail++
tags:
- lora
- stable-diffusion
- flux.1-d
model_type: LoRA
---
# Christmas Couture
**Base model**: Flux.1 D
**Trained words**:
## 🧠 Usage (Python)
🔑 **Get your MUAPI key** from [muapi.ai/access-keys](https://muapi.ai/access-keys)
```python
import requests, os
url = "https://api.muapi.ai/api/v1/flux_dev_lora_image"
headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")}
payload = {
"prompt": "masterpiece, best quality, 1girl, looking at viewer",
"model_id": [{"model": "civitai:1016234@1139381", "weight": 1.0}],
"width": 1024,
"height": 1024,
"num_images": 1
}
print(requests.post(url, headers=headers, json=payload).json())
```
|
IvanJAjebu/blockassist-bc-thorny_slender_capybara_1755595520
|
IvanJAjebu
| 2025-08-19T09:26:43Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"thorny slender capybara",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T09:26:19Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- thorny slender capybara
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
aleebaster/blockassist-bc-sly_eager_boar_1755594069
|
aleebaster
| 2025-08-19T09:26:38Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"sly eager boar",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T09:26:32Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- sly eager boar
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
hoan17/saving_LOe400s16_scratchtttt_2
|
hoan17
| 2025-08-19T09:23:24Z | 0 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"trl",
"o2o",
"reinforcement-learning",
"text-to-image",
"stable-diffusion",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2025-08-19T09:22:57Z |
---
license: apache-2.0
tags:
- trl
- o2o
- diffusers
- reinforcement-learning
- text-to-image
- stable-diffusion
---
# TRL O2O Model
This is a diffusion model that has been fine-tuned with reinforcement learning to
guide the model outputs according to a value, function, or human feedback. The model can be used for image generation conditioned with text.
|
ihsanridzi/blockassist-bc-wiry_flexible_owl_1755593713
|
ihsanridzi
| 2025-08-19T09:22:36Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"wiry flexible owl",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T09:22:32Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- wiry flexible owl
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
phospho-app/SvenBorodun-ACT_BBOX-so100-tictactoe-n086k
|
phospho-app
| 2025-08-19T09:20:52Z | 0 | 0 |
phosphobot
|
[
"phosphobot",
"act",
"robotics",
"dataset:phospho-ai/so100-tictactoe",
"region:us"
] |
robotics
| 2025-08-19T09:16:47Z |
---
datasets: phospho-ai/so100-tictactoe
library_name: phosphobot
pipeline_tag: robotics
model_name: act
tags:
- phosphobot
- act
task_categories:
- robotics
---
# act Model - phospho Training Pipeline
## Error Traceback
We faced an issue while training your model.
```
Parquet file /__modal/volumes/vo-jpHx3K78b6s9tZZNuqKoXe/datasets/phospho-ai/so100-tictactoe_bboxes/data/chunk-000/episode_000000.parquet does not contain 'observation.environment_state' key. This is unexpected after computing bounding boxes.
```
## Training parameters:
- **Dataset**: [phospho-ai/so100-tictactoe](https://huggingface.co/datasets/phospho-ai/so100-tictactoe)
- **Wandb run URL**: None
- **Epochs**: None
- **Batch size**: 100
- **Training steps**: 10000
📖 **Get Started**: [docs.phospho.ai](https://docs.phospho.ai?utm_source=huggingface_readme)
🤖 **Get your robot**: [robots.phospho.ai](https://robots.phospho.ai?utm_source=huggingface_readme)
|
IvanJAjebu/blockassist-bc-thorny_slender_capybara_1755595160
|
IvanJAjebu
| 2025-08-19T09:20:31Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"thorny slender capybara",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T09:20:20Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- thorny slender capybara
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
Muapi/artsy-realism
|
Muapi
| 2025-08-19T09:19:56Z | 0 | 0 | null |
[
"lora",
"stable-diffusion",
"flux.1-d",
"license:openrail++",
"region:us"
] | null | 2025-08-19T09:19:48Z |
---
license: openrail++
tags:
- lora
- stable-diffusion
- flux.1-d
model_type: LoRA
---
# Artsy Realism
**Base model**: Flux.1 D
**Trained words**: Artsy Photo
## 🧠 Usage (Python)
🔑 **Get your MUAPI key** from [muapi.ai/access-keys](https://muapi.ai/access-keys)
```python
import requests, os
url = "https://api.muapi.ai/api/v1/flux_dev_lora_image"
headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")}
payload = {
"prompt": "masterpiece, best quality, 1girl, looking at viewer",
"model_id": [{"model": "civitai:855574@957271", "weight": 1.0}],
"width": 1024,
"height": 1024,
"num_images": 1
}
print(requests.post(url, headers=headers, json=payload).json())
```
|
crocodlo/blockassist-bc-soft_barky_scorpion_1755595151
|
crocodlo
| 2025-08-19T09:19:52Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"soft barky scorpion",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T09:19:42Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- soft barky scorpion
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
lqpl/blockassist-bc-hairy_insectivorous_antelope_1755595015
|
lqpl
| 2025-08-19T09:19:50Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"hairy insectivorous antelope",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T09:17:45Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- hairy insectivorous antelope
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
deerr120a/blockassist-bc-prehistoric_arctic_otter_1755592752
|
deerr120a
| 2025-08-19T09:19:18Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"prehistoric arctic otter",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T09:18:59Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- prehistoric arctic otter
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
0xaoyama/blockassist-bc-muscular_zealous_gorilla_1755595095
|
0xaoyama
| 2025-08-19T09:18:49Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"muscular zealous gorilla",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T09:18:38Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- muscular zealous gorilla
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
aiface/CafeBERT_nli
|
aiface
| 2025-08-19T09:18:46Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"xlm-roberta",
"text-classification",
"generated_from_trainer",
"base_model:uitnlp/CafeBERT",
"base_model:finetune:uitnlp/CafeBERT",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2025-08-19T07:17:23Z |
---
library_name: transformers
license: apache-2.0
base_model: uitnlp/CafeBERT
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: CafeBERT_nli
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. -->
# CafeBERT_nli
This model is a fine-tuned version of [uitnlp/CafeBERT](https://huggingface.co/uitnlp/CafeBERT) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.2989
- Accuracy: 0.8306
- Precision Macro: 0.8307
- Recall Macro: 0.8308
- F1 Macro: 0.8306
- F1 Weighted: 0.8306
## 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: 128
- eval_batch_size: 128
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 256
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision Macro | Recall Macro | F1 Macro | F1 Weighted |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------------:|:------------:|:--------:|:-----------:|
| 1.0641 | 1.0 | 72 | 0.6313 | 0.7565 | 0.7672 | 0.7575 | 0.7562 | 0.7561 |
| 0.64 | 2.0 | 144 | 0.5313 | 0.8044 | 0.8077 | 0.8042 | 0.8039 | 0.8040 |
| 0.3679 | 3.0 | 216 | 0.5117 | 0.8062 | 0.8078 | 0.8067 | 0.8060 | 0.8059 |
| 0.2855 | 4.0 | 288 | 0.5816 | 0.8098 | 0.8150 | 0.8101 | 0.8087 | 0.8087 |
| 0.1571 | 5.0 | 360 | 0.6372 | 0.8058 | 0.8060 | 0.8058 | 0.8058 | 0.8059 |
| 0.1165 | 6.0 | 432 | 0.6929 | 0.8177 | 0.8186 | 0.8177 | 0.8178 | 0.8178 |
| 0.0855 | 7.0 | 504 | 0.7374 | 0.8084 | 0.8090 | 0.8087 | 0.8084 | 0.8084 |
| 0.0704 | 8.0 | 576 | 0.8241 | 0.8075 | 0.8107 | 0.8071 | 0.8075 | 0.8075 |
| 0.0593 | 9.0 | 648 | 0.9712 | 0.8098 | 0.8108 | 0.8094 | 0.8095 | 0.8096 |
| 0.0415 | 10.0 | 720 | 0.8643 | 0.8155 | 0.8165 | 0.8153 | 0.8155 | 0.8155 |
| 0.034 | 11.0 | 792 | 0.9662 | 0.8124 | 0.8149 | 0.8120 | 0.8123 | 0.8123 |
| 0.0273 | 12.0 | 864 | 1.0114 | 0.8182 | 0.8188 | 0.8181 | 0.8182 | 0.8182 |
| 0.0189 | 13.0 | 936 | 1.2237 | 0.8155 | 0.8195 | 0.8159 | 0.8156 | 0.8155 |
| 0.0068 | 14.0 | 1008 | 1.2312 | 0.8244 | 0.8265 | 0.8247 | 0.8244 | 0.8244 |
| 0.011 | 15.0 | 1080 | 1.2062 | 0.8315 | 0.8316 | 0.8316 | 0.8314 | 0.8314 |
| 0.003 | 16.0 | 1152 | 1.2550 | 0.8279 | 0.8280 | 0.8280 | 0.8280 | 0.8279 |
| 0.0024 | 17.0 | 1224 | 1.2774 | 0.8302 | 0.8303 | 0.8303 | 0.8302 | 0.8302 |
| 0.003 | 18.0 | 1296 | 1.2946 | 0.8293 | 0.8295 | 0.8295 | 0.8292 | 0.8292 |
| 0.0023 | 19.0 | 1368 | 1.2969 | 0.8306 | 0.8307 | 0.8308 | 0.8306 | 0.8306 |
| 0.0012 | 20.0 | 1440 | 1.2989 | 0.8306 | 0.8307 | 0.8308 | 0.8306 | 0.8306 |
### Framework versions
- Transformers 4.55.0
- Pytorch 2.7.0+cu126
- Datasets 4.0.0
- Tokenizers 0.21.4
|
Muapi/circuitboardstyle
|
Muapi
| 2025-08-19T09:18:28Z | 0 | 0 | null |
[
"lora",
"stable-diffusion",
"flux.1-d",
"license:openrail++",
"region:us"
] | null | 2025-08-19T09:18:17Z |
---
license: openrail++
tags:
- lora
- stable-diffusion
- flux.1-d
model_type: LoRA
---
# CircuitBoardStyle
**Base model**: Flux.1 D
**Trained words**: TzigoCBS
## 🧠 Usage (Python)
🔑 **Get your MUAPI key** from [muapi.ai/access-keys](https://muapi.ai/access-keys)
```python
import requests, os
url = "https://api.muapi.ai/api/v1/flux_dev_lora_image"
headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")}
payload = {
"prompt": "masterpiece, best quality, 1girl, looking at viewer",
"model_id": [{"model": "civitai:579493@750520", "weight": 1.0}],
"width": 1024,
"height": 1024,
"num_images": 1
}
print(requests.post(url, headers=headers, json=payload).json())
```
|
Muapi/stellaris-character-race-style-lora-flux-xl-illustrous-xl-pony
|
Muapi
| 2025-08-19T09:17:08Z | 0 | 0 | null |
[
"lora",
"stable-diffusion",
"flux.1-d",
"license:openrail++",
"region:us"
] | null | 2025-08-19T09:17:01Z |
---
license: openrail++
tags:
- lora
- stable-diffusion
- flux.1-d
model_type: LoRA
---
# Stellaris Character/race Style Lora [FLUX+XL+Illustrous XL+Pony]
**Base model**: Flux.1 D
**Trained words**: fungoid, necroid, avian
## 🧠 Usage (Python)
🔑 **Get your MUAPI key** from [muapi.ai/access-keys](https://muapi.ai/access-keys)
```python
import requests, os
url = "https://api.muapi.ai/api/v1/flux_dev_lora_image"
headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")}
payload = {
"prompt": "masterpiece, best quality, 1girl, looking at viewer",
"model_id": [{"model": "civitai:351525@1028132", "weight": 1.0}],
"width": 1024,
"height": 1024,
"num_images": 1
}
print(requests.post(url, headers=headers, json=payload).json())
```
|
Muapi/arcane-style-ayanna-ai
|
Muapi
| 2025-08-19T09:16:13Z | 0 | 0 | null |
[
"lora",
"stable-diffusion",
"flux.1-d",
"license:openrail++",
"region:us"
] | null | 2025-08-19T09:16:06Z |
---
license: openrail++
tags:
- lora
- stable-diffusion
- flux.1-d
model_type: LoRA
---
# Arcane Style Ayanna AI
**Base model**: Flux.1 D
**Trained words**: Arcane Style
## 🧠 Usage (Python)
🔑 **Get your MUAPI key** from [muapi.ai/access-keys](https://muapi.ai/access-keys)
```python
import requests, os
url = "https://api.muapi.ai/api/v1/flux_dev_lora_image"
headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")}
payload = {
"prompt": "masterpiece, best quality, 1girl, looking at viewer",
"model_id": [{"model": "civitai:1024432@1274224", "weight": 1.0}],
"width": 1024,
"height": 1024,
"num_images": 1
}
print(requests.post(url, headers=headers, json=payload).json())
```
|
Muapi/damaged-photo-daguerreotype
|
Muapi
| 2025-08-19T09:15:55Z | 0 | 0 | null |
[
"lora",
"stable-diffusion",
"flux.1-d",
"license:openrail++",
"region:us"
] | null | 2025-08-19T09:15:44Z |
---
license: openrail++
tags:
- lora
- stable-diffusion
- flux.1-d
model_type: LoRA
---
# Damaged Photo Daguerreotype
**Base model**: Flux.1 D
**Trained words**: damagedphoto, edges, black shape, blur, border, corners, crease, fingerprints, foggy, heavy damage, liquid stain, mottled, scratches, smudges, speckles, streak, tape, torn, vignette
## 🧠 Usage (Python)
🔑 **Get your MUAPI key** from [muapi.ai/access-keys](https://muapi.ai/access-keys)
```python
import requests, os
url = "https://api.muapi.ai/api/v1/flux_dev_lora_image"
headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")}
payload = {
"prompt": "masterpiece, best quality, 1girl, looking at viewer",
"model_id": [{"model": "civitai:101127@1210919", "weight": 1.0}],
"width": 1024,
"height": 1024,
"num_images": 1
}
print(requests.post(url, headers=headers, json=payload).json())
```
|
MDscs/CodeLlama-13B-Reparador-Software-v1
|
MDscs
| 2025-08-19T09:15:33Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"base_model:codellama/CodeLlama-13b-Instruct-hf",
"base_model:finetune:codellama/CodeLlama-13b-Instruct-hf",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-08-19T09:15:12Z |
---
base_model: codellama/CodeLlama-13b-Instruct-hf
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** MDscs
- **License:** apache-2.0
- **Finetuned from model :** codellama/CodeLlama-13b-Instruct-hf
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)
|
quantumxnode/blockassist-bc-dormant_peckish_seahorse_1755593299
|
quantumxnode
| 2025-08-19T09:15:12Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"dormant peckish seahorse",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T09:15:09Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- dormant peckish seahorse
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
aligne/deneme1
|
aligne
| 2025-08-19T09:14:20Z | 0 | 0 |
peft
|
[
"peft",
"tensorboard",
"safetensors",
"base_model:adapter:deepseek-ai/deepseek-coder-7b-instruct-v1.5",
"lora",
"transformers",
"text-generation",
"base_model:deepseek-ai/deepseek-coder-7b-instruct-v1.5",
"license:other",
"region:us"
] |
text-generation
| 2025-08-19T08:07:11Z |
---
library_name: peft
license: other
base_model: deepseek-ai/deepseek-coder-7b-instruct-v1.5
tags:
- base_model:adapter:deepseek-ai/deepseek-coder-7b-instruct-v1.5
- lora
- transformers
pipeline_tag: text-generation
model-index:
- name: deneme1
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. -->
# deneme1
This model is a fine-tuned version of [deepseek-ai/deepseek-coder-7b-instruct-v1.5](https://huggingface.co/deepseek-ai/deepseek-coder-7b-instruct-v1.5) on the None dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- 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
### Framework versions
- PEFT 0.17.0
- Transformers 4.55.2
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.21.4
|
lqpl/blockassist-bc-hairy_insectivorous_antelope_1755594592
|
lqpl
| 2025-08-19T09:12:40Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"hairy insectivorous antelope",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T09:10:44Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- hairy insectivorous antelope
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
mookiezi/Discord-Micae-Hermes-3-3B
|
mookiezi
| 2025-08-19T09:08:46Z | 1,764 | 2 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"causal-lm",
"instruct",
"chat",
"fine-tuned",
"merged-lora",
"llama-3",
"hermes",
"discord-dataset",
"conversational-ai",
"chatml",
"pytorch",
"open-weights",
"3b-parameters",
"conversational",
"dataset:mookiezi/Discord-OpenMicae",
"arxiv:2408.11857",
"base_model:NousResearch/Hermes-3-Llama-3.2-3B",
"base_model:finetune:NousResearch/Hermes-3-Llama-3.2-3B",
"license:llama3",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-02T23:21:01Z |
---
tags:
- transformers
- causal-lm
- text-generation
- instruct
- chat
- fine-tuned
- merged-lora
- llama-3
- hermes
- discord-dataset
- conversational-ai
- chatml
- pytorch
- open-weights
- 3b-parameters
model-index:
- name: Discord-Micae-Hermes-3-3B
results: []
base_model:
- NousResearch/Hermes-3-Llama-3.2-3B
datasets:
- mookiezi/Discord-OpenMicae
library_name: transformers
license: llama3
---
<div style="display: flex; align-items: center; gap: 8px;">
<span>Run this model on Google Colab for free:</span>
<a href="https://colab.research.google.com/drive/1kUtTeey5THhKW6f0BDKB9MFe4JIEew_Z?usp=sharing">
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open in Colab"/>
</a>
</div>
## Discord-Micae-Hermes-3-3B
## Model Description
Discord-Micae-Hermes-3-3B is a new finetune on [NousResearch/Hermes-3-Llama-3.2-3B](https://huggingface.co/NousResearch/Hermes-3-Llama-3.2-3B).
This model serves as a foundation for ongoing exploration into the capabilities of human-adjacent text generation.
- **Training Schedule:**
- 17M tokens of 260 thousand single-turn exchanges (STX) – 6 epochs @ 2e-5
- 5.5M tokens of 101 thousand multi-turn chains – 6 epochs @ 2e-5
- Combined dataset – 1 epoch @ 1e-5
- **Fine-Tuning Method:** LoRA merge (α = 32, r = 8, dropout = 0.1)
- **LoRA target modules:** q_proj, v_proj
- **Scheduler:** Cosine schedule with 220 warmup steps per phase
- **Optimizer:** torch.optim.AdamW (betas = (0.9, 0.999), amsgrad = False, eps = 1e-8, weight decay = 0.01)
- **Batching:** Effective size of 126 (7 batch size × 18 gradient accumulation steps)
- **Timeline and Hardware:** Training took place over 17 days on a GTX 1080 (8GB).
## Dataset
The model was fine-tuned on the [mookiezi/Discord-OpenMicae](https://huggingface.co/datasets/mookiezi/Discord-OpenMicae) dataset.
## Intended Use
- Conversational AI research
- Experimentation with dialogue agents trained on Discord data
- Chatbots requiring **casual, human-like tone**
### Limitations
- The model inherits potential biases from Discord-style language.
- It is **not safety-aligned** for deployment without moderation.
- While it does inhert knowledge from Hermes-3-3B it is not intended for factual or sensitive information retrieval.
## Prompting
Micae uses the same ChatML prompt format as Hermes 3 and handles context and chat history.
```
<|im_start|>user
what do you think about ai?<|im_end|>
<|im_start|>assistant
i'm not a fan of AI but I can understand why people are excited to use it. it's like the first time they got an electric car, or when they were able to fly in space, that excitement is real<|im_end|>
<|im_start|>user
where do you think it's heading?<|im_end|>
<|im_start|>assistant
it will be used for good and bad things just as with other techs<|im_end|>
<|im_start|>user
what do you do use it for personally?<|im_end|>
<|im_start|>assistant
nothing much yet, I hope to find some stuff later on.<|im_end|>
<|im_start|>user
do you like pokemon?<|im_end|>
<|im_start|>assistant
yes I love Pokémon.<|im_end|>
<|im_start|>user
what's your favorite pokemon<|im_end|>
<|im_start|>assistant
garchomp<|im_end|>
```
---
## Inferfacing
A python script for interfacing, optimized for casual, Discord-style conversation, is available at [https://github.com/mookiezi/interface](https://github.com/mookiezi/interface).
To use this model run:
```
python interface.py -m mookiezi/Discord-Micae-Hermes-3-3B
```
<span style="font-size:smaller;">(Example interface with [mookiezi/Discord-Micae-8B-Preview](https://huggingface.co/mookiezi/Discord-Micae-8B-Preview))</span>
---
## License
See the [Meta LLaMA 3 Community License](https://ai.meta.com/llama/license/) for details.
## How to cite:
If you use this model in your work, please cite both **Discord-Micae-Hermes-3-3B** and the base model **Hermes 3**:
```bibtex
@misc{discord-micae-hermes3b,
title = {Discord-Micae-Hermes-3-3B},
author = {mookiezi},
year = {2025},
url={https://huggingface.co/mookiezi/Discord-Micae-Hermes-3-3B}
}
@misc{teknium2024hermes3technicalreport,
title={Hermes 3 Technical Report},
author={Ryan Teknium and Jeffrey Quesnelle and Chen Guang},
year={2024},
eprint={2408.11857},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2408.11857}
}
```
[](https://20000.online/micae)
[](https://20000.online/openmicae)
[](https://20000.online/discord-dialogues)
|
katanyasekolah/blockassist-bc-silky_sprightly_cassowary_1755583662
|
katanyasekolah
| 2025-08-19T09:08:23Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"silky sprightly cassowary",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T06:34:55Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- silky sprightly cassowary
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
LarryAIDraw/dragoxl_v30TEST
|
LarryAIDraw
| 2025-08-19T09:07:20Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2025-08-18T21:19:29Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/1519399?modelVersionId=2089561
|
LarryAIDraw/anim3dilxok_v10
|
LarryAIDraw
| 2025-08-19T09:07:01Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2025-08-18T21:18:59Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/1854435/anim3dilxok?modelVersionId=2098722
|
LarryAIDraw/c1_iuno__wuthering_waves__ilv1_0-xl
|
LarryAIDraw
| 2025-08-19T09:06:44Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2025-08-18T21:17:45Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/1716234/iuno-wuthering-waves-oror
|
yaelahnal/blockassist-bc-mute_clawed_crab_1755594326
|
yaelahnal
| 2025-08-19T09:06:33Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"mute clawed crab",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T09:06:14Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- mute clawed crab
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
lakelee/RLB_MLP_TSC_v1.20250818.16
|
lakelee
| 2025-08-19T09:05:36Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"mlp_swiglu",
"generated_from_trainer",
"endpoints_compatible",
"region:us"
] | null | 2025-08-18T07:13:10Z |
---
library_name: transformers
tags:
- generated_from_trainer
model-index:
- name: RLB_MLP_TSC_v1.20250818.16
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. -->
# RLB_MLP_TSC_v1.20250818.16
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 1.0
### Training results
### Framework versions
- Transformers 4.55.2
- Pytorch 2.6.0+cu124
- Tokenizers 0.21.4
|
dsdsdsdfffff/code_without_auxloss
|
dsdsdsdfffff
| 2025-08-19T09:04:11Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"deepseek_v2",
"text-generation",
"conversational",
"custom_code",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-19T09:00:53Z |
---
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]
|
constehub/qwen3-14B-rerank-evaluation
|
constehub
| 2025-08-19T09:03:04Z | 0 | 0 |
transformers
|
[
"transformers",
"gguf",
"qwen3",
"text-generation-inference",
"unsloth",
"en",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-08-18T12:40:09Z |
---
base_model: unsloth/qwen3-14b-base-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- qwen3
- gguf
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** constehub
- **License:** apache-2.0
- **Finetuned from model :** unsloth/qwen3-14b-base-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)
|
lisaozill03/blockassist-bc-rugged_prickly_alpaca_1755592568
|
lisaozill03
| 2025-08-19T09:02:15Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"rugged prickly alpaca",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T09:02:11Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- rugged prickly alpaca
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
victorguima12/momoper
|
victorguima12
| 2025-08-19T09:01:15Z | 0 | 0 | null |
[
"license:apache-2.0",
"region:us"
] | null | 2025-08-19T09:00:23Z |
---
license: apache-2.0
---
|
koloni/blockassist-bc-deadly_graceful_stingray_1755592400
|
koloni
| 2025-08-19T09:01:02Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"deadly graceful stingray",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T09:00:58Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- deadly graceful stingray
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
csabazs/Qwen2-0.5B-GRPO-test
|
csabazs
| 2025-08-19T09:00:06Z | 0 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"generated_from_trainer",
"trl",
"grpo",
"arxiv:2402.03300",
"base_model:Qwen/Qwen2-0.5B-Instruct",
"base_model:finetune:Qwen/Qwen2-0.5B-Instruct",
"endpoints_compatible",
"region:us"
] | null | 2025-08-19T08:54:00Z |
---
base_model: Qwen/Qwen2-0.5B-Instruct
library_name: transformers
model_name: Qwen2-0.5B-GRPO-test
tags:
- generated_from_trainer
- trl
- grpo
licence: license
---
# Model Card for Qwen2-0.5B-GRPO-test
This model is a fine-tuned version of [Qwen/Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct).
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="csabazs/Qwen2-0.5B-GRPO-test", 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: 0.21.0
- Transformers: 4.55.2
- Pytorch: 2.8.0
- Datasets: 4.0.0
- Tokenizers: 0.21.4
## 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}}
}
```
|
OleksandrLitke/Qwen3-0.6B-Gensyn-Swarm-grassy_scurrying_walrus
|
OleksandrLitke
| 2025-08-19T08:59:10Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen3",
"text-generation",
"rl-swarm",
"genrl-swarm",
"grpo",
"gensyn",
"I am grassy_scurrying_walrus",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-19T04:54:14Z |
---
library_name: transformers
tags:
- rl-swarm
- genrl-swarm
- grpo
- gensyn
- I am grassy_scurrying_walrus
---
# 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]
|
rk2357281/llama32-bhojpuri-translator
|
rk2357281
| 2025-08-19T08:58:40Z | 0 | 0 |
transformers
|
[
"transformers",
"gguf",
"llama",
"text-generation-inference",
"unsloth",
"en",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-08-19T08:51:20Z |
---
base_model: unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- gguf
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** rk2357281
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
IvanJAjebu/blockassist-bc-thorny_slender_capybara_1755593733
|
IvanJAjebu
| 2025-08-19T08:56:35Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"thorny slender capybara",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T08:56:30Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- thorny slender capybara
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
chooseL1fe/blockassist-bc-thorny_flightless_albatross_1755593324
|
chooseL1fe
| 2025-08-19T08:55:03Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"thorny flightless albatross",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T08:54:59Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- thorny flightless albatross
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
imchc/MyGemmaNPC
|
imchc
| 2025-08-19T08:53:25Z | 0 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"gemma3_text",
"text-generation",
"generated_from_trainer",
"trl",
"sft",
"conversational",
"base_model:google/gemma-3-270m-it",
"base_model:finetune:google/gemma-3-270m-it",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-19T07:49:06Z |
---
base_model: google/gemma-3-270m-it
library_name: transformers
model_name: MyGemmaNPC
tags:
- generated_from_trainer
- trl
- sft
licence: license
---
# Model Card for MyGemmaNPC
This model is a fine-tuned version of [google/gemma-3-270m-it](https://huggingface.co/google/gemma-3-270m-it).
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="imchc/MyGemmaNPC", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
This model was trained with SFT.
### Framework versions
- TRL: 0.21.0
- Transformers: 4.55.2
- Pytorch: 2.6.0+cu124
- Datasets: 4.0.0
- Tokenizers: 0.21.4
## Citations
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
```
|
kkokas/task-14-Qwen-Qwen2.5-0.5B-Instruct
|
kkokas
| 2025-08-19T08:51:02Z | 24 | 0 |
peft
|
[
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:Qwen/Qwen2.5-0.5B-Instruct",
"base_model:adapter:Qwen/Qwen2.5-0.5B-Instruct",
"region:us"
] | null | 2025-08-13T07:20:12Z |
---
base_model: Qwen/Qwen2.5-0.5B-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 0.13.2
|
Sayemahsjn/blockassist-bc-playful_feline_octopus_1755592308
|
Sayemahsjn
| 2025-08-19T08:50:52Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"playful feline octopus",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T08:50:47Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- playful feline octopus
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
Ale91Jonathan/blockassist-bc-alert_dormant_prawn_1755591514
|
Ale91Jonathan
| 2025-08-19T08:50:35Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"alert dormant prawn",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T08:50:32Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- alert dormant prawn
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
MoraySmith/CC_ESMplusplus_small
|
MoraySmith
| 2025-08-19T08:46:49Z | 0 | 0 |
peft
|
[
"peft",
"safetensors",
"base_model:adapter:Synthyra/ESMplusplus_small",
"lora",
"transformers",
"arxiv:1910.09700",
"base_model:Synthyra/ESMplusplus_small",
"region:us"
] | null | 2025-08-19T08:42:29Z |
---
base_model: Synthyra/ESMplusplus_small
library_name: peft
tags:
- base_model:adapter:Synthyra/ESMplusplus_small
- lora
- transformers
---
# 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 0.17.0
|
dgambettaphd/M_mis_run2_gen6_WXS_doc1000_synt64_lr1e-04_acm_MPP
|
dgambettaphd
| 2025-08-19T08:44:30Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"unsloth",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-08-19T08:44:16Z |
---
library_name: transformers
tags:
- unsloth
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
WalidAlsafadi/arabert-fake-news-detector
|
WalidAlsafadi
| 2025-08-19T08:42:20Z | 21 | 0 |
transformers
|
[
"transformers",
"safetensors",
"bert",
"text-classification",
"fake-news",
"nlp",
"arabert",
"arabic",
"ar",
"base_model:aubmindlab/bert-base-arabertv02",
"base_model:finetune:aubmindlab/bert-base-arabertv02",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2025-08-18T07:40:47Z |
---
license: apache-2.0
language:
- ar
base_model:
- aubmindlab/bert-base-arabertv02
metrics:
- accuracy
- f1
- precision
- recall
pipeline_tag: text-classification
tags:
- fake-news
- nlp
- text-classification
- arabert
- arabic
- transformers
---
# AraBERT Fake News Detector
## Model Overview
This model is a fine-tuned version of AraBERT (aubmindlab/bert-base-arabertv02) for detecting fake news in Arabic news articles, with a focus on Palestinian news sources.
## Intended Use
- **Task:** Binary classification (Real vs. Fake news) for Arabic text.
- **Audience:** Journalists, researchers, and the general public interested in verifying Arabic news content.
- **Input:** Arabic news article (max 512 tokens).
- **Output:** "Real" or "Fake" label with confidence scores.
## Dataset
- News articles scraped from Palestinian news sources.
- Cleaned and split into training, validation, and test sets.
- Test set size: 2750 samples.
## Performance
- **Accuracy:** 96.22%
- **F1-score (weighted):** 96.22%
- **F1-score (macro):** 96.21%
- **AUC:** 99.57%
- **Inference time:** ~200ms (CPU)
### Confusion Matrix
```
[[1251 32]
[ 72 1395]]
```
### Classification Report
| Class | Precision | Recall | F1-score | Support |
|-------|-----------|--------|----------|---------|
| Real | 0.9456 | 0.9751 | 0.9601 | 1283 |
| Fake | 0.9776 | 0.9509 | 0.9641 | 1467 |
## Limitations & Biases
- Trained on Palestinian news; performance may vary on other Arabic dialects or regions.
- Potential bias from dataset sources and labeling.
- Not suitable for non-news or non-Arabic text.
## Ethical Considerations
- Use responsibly; predictions are not a substitute for human judgment.
- False positives/negatives may occur.
## Citation
If you use this model, please cite:
```
@misc{haqiqa2025,
author = {Walid Alsafadi},
title = {Haqiqa - Arabic Fake News Detector},
year = {2025},
url = {https://github.com/WalidAlsafadi/Haqiqa-Arabic-Fake-News-Detector}
}
```
## License
**Licensed under Apache 2.0** - see [LICENSE](LICENSE) for details.
|
ElToro2602/blockassist-bc-raging_prehistoric_chameleon_1755592858
|
ElToro2602
| 2025-08-19T08:41:44Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"raging prehistoric chameleon",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T08:41:36Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- raging prehistoric chameleon
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
crocodlo/blockassist-bc-soft_barky_scorpion_1755592820
|
crocodlo
| 2025-08-19T08:40:58Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"soft barky scorpion",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T08:40:50Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- soft barky scorpion
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
IvanJAjebu/blockassist-bc-thorny_slender_capybara_1755592716
|
IvanJAjebu
| 2025-08-19T08:39:43Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"thorny slender capybara",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T08:39:39Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- thorny slender capybara
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
KCS97/dog6
|
KCS97
| 2025-08-19T08:38:19Z | 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
| 2025-08-19T08:25:49Z |
---
base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
library_name: diffusers
license: creativeml-openrail-m
inference: true
instance_prompt: a photo of sks dog
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 - KCS97/dog6
This is a dreambooth model derived from stable-diffusion-v1-5/stable-diffusion-v1-5. The weights were trained on a photo of sks dog 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]
|
resistz/sft_Llama-3.2-1B_ultra200k
|
resistz
| 2025-08-19T08:35:37Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"generated_from_trainer",
"sft",
"trl",
"conversational",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-19T08:32:16Z |
---
library_name: transformers
model_name: sft_Llama3.2-1B_ultra200k
tags:
- generated_from_trainer
- sft
- trl
licence: license
---
# Model Card for sft_Llama3.2-1B_ultra200k
This model is a fine-tuned version of [None](https://huggingface.co/None).
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="None", 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/resistzzz97/Alignment_Influence/runs/iq1tp3b2)
This model was trained with SFT.
### Framework versions
- TRL: 0.21.0
- Transformers: 4.55.2
- Pytorch: 2.7.1
- Datasets: 4.0.0
- Tokenizers: 0.21.4
## Citations
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
```
|
IvanJAjebu/blockassist-bc-thorny_slender_capybara_1755592441
|
IvanJAjebu
| 2025-08-19T08:35:12Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"thorny slender capybara",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T08:35:03Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- thorny slender capybara
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
Alonc/device_to_cve_16bit_8B
|
Alonc
| 2025-08-19T08:33:22Z | 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
| 2025-08-19T08:30:10Z |
---
base_model: unsloth/qwen3-8b-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- qwen3
license: apache-2.0
language:
- en
---
# Uploaded finetuned model
- **Developed by:** Alonc
- **License:** apache-2.0
- **Finetuned from model :** unsloth/qwen3-8b-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)
|
FreddyFazbear0209/fine-tuned-qwen-2.5-vl-kie-vietnamese
|
FreddyFazbear0209
| 2025-08-19T08:33:12Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"qwen2_5_vl",
"trl",
"en",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-08-19T08:09:29Z |
---
base_model: unsloth/qwen2.5-vl-3b-instruct-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- qwen2_5_vl
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** FreddyFazbear0209
- **License:** apache-2.0
- **Finetuned from model :** unsloth/qwen2.5-vl-3b-instruct-bnb-4bit
This qwen2_5_vl 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)
|
ydshieh/kosmos-2.5
|
ydshieh
| 2025-08-19T08:33:10Z | 2 | 0 | null |
[
"safetensors",
"kosmos-2.5",
"en",
"arxiv:2309.11419",
"license:mit",
"region:us"
] | null | 2025-04-28T10:24:13Z |
---
language: en
license: mit
---
# Kosmos-2.5
[Microsoft Document AI](https://www.microsoft.com/en-us/research/project/document-ai/) | [GitHub](https://github.com/microsoft/unilm/tree/master/kosmos-2.5)
## Model description
Kosmos-2.5 is a multimodal literate model for machine reading of text-intensive images. Pre-trained on large-scale text-intensive images, Kosmos-2.5 excels in two distinct yet cooperative transcription tasks: (1) generating spatially-aware text blocks, where each block of text is assigned its spatial coordinates within the image, and (2) producing structured text output that captures styles and structures into the markdown format. This unified multimodal literate capability is achieved through a shared decoder-only auto-regressive Transformer architecture, task-specific prompts, and flexible text representations. We evaluate Kosmos-2.5 on end-to-end document-level text recognition and image-to-markdown text generation. Furthermore, the model can be readily adapted for any text-intensive image understanding task with different prompts through supervised fine-tuning, making it a general-purpose tool for real-world applications involving text-rich images. This work also paves the way for the future scaling of multimodal large language models.
[Kosmos-2.5: A Multimodal Literate Model](https://arxiv.org/abs/2309.11419)
## NOTE:
Since this is a generative model, there is a risk of **hallucination** during the generation process, and it **CAN NOT** guarantee the accuracy of all OCR/Markdown results in the images.
## Inference
**Markdown Task:** For usage instructions, please refer to [md.py](md.py).
**OCR Task:** For usage instructions, please refer to [ocr.py](ocr.py).
## Citation
If you find Kosmos-2.5 useful in your research, please cite the following paper:
```
@article{lv2023kosmos,
title={Kosmos-2.5: A multimodal literate model},
author={Lv, Tengchao and Huang, Yupan and Chen, Jingye and Cui, Lei and Ma, Shuming and Chang, Yaoyao and Huang, Shaohan and Wang, Wenhui and Dong, Li and Luo, Weiyao and others},
journal={arXiv preprint arXiv:2309.11419},
year={2023}
}
```
## License
The content of this project itself is licensed under the [MIT](https://github.com/microsoft/unilm/blob/master/kosmos-2.5/LICENSE)
[Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct)
|
VoilaRaj/78_t73IDA
|
VoilaRaj
| 2025-08-19T08:30:04Z | 0 | 0 | null |
[
"safetensors",
"any-to-any",
"omega",
"omegalabs",
"bittensor",
"agi",
"license:mit",
"region:us"
] |
any-to-any
| 2025-08-19T08:26:04Z |
---
license: mit
tags:
- any-to-any
- omega
- omegalabs
- bittensor
- agi
---
This is an Any-to-Any model checkpoint for the OMEGA Labs x Bittensor Any-to-Any subnet.
Check out the [git repo](https://github.com/omegalabsinc/omegalabs-anytoany-bittensor) and find OMEGA on X: [@omegalabsai](https://x.com/omegalabsai).
|
thailevann/track8_subtask2_v3
|
thailevann
| 2025-08-19T08:29:35Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"qwen3",
"trl",
"en",
"base_model:unsloth/Qwen3-4B-Thinking-2507-unsloth-bnb-4bit",
"base_model:finetune:unsloth/Qwen3-4B-Thinking-2507-unsloth-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-08-19T08:29:15Z |
---
base_model: unsloth/Qwen3-4B-Thinking-2507-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- qwen3
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** thailevann
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Qwen3-4B-Thinking-2507-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)
|
Subsets and Splits
Filtered Qwen2.5 Distill Models
Identifies specific configurations of models by filtering cards that contain 'distill', 'qwen2.5', '7b' while excluding certain base models and incorrect model ID patterns, uncovering unique model variants.
Filtered Model Cards Count
Finds the count of entries with specific card details that include 'distill', 'qwen2.5', '7b' but exclude certain base models, revealing valuable insights about the dataset's content distribution.
Filtered Distill Qwen 7B Models
Filters for specific card entries containing 'distill', 'qwen', and '7b', excluding certain strings and patterns, to identify relevant model configurations.
Filtered Qwen-7b Model Cards
The query performs a detailed filtering based on specific keywords and excludes certain entries, which could be useful for identifying a specific subset of cards but does not provide deeper insights or trends.
Filtered Qwen 7B Model Cards
The query filters for specific terms related to "distilled" or "distill", "qwen", and "7b" in the 'card' column but excludes certain base models, providing a limited set of entries for further inspection.
Qwen 7B Distilled Models
The query provides a basic filtering of records to find specific card names that include keywords related to distilled Qwen 7b models, excluding a particular base model, which gives limited insight but helps in focusing on relevant entries.
Qwen 7B Distilled Model Cards
The query filters data based on specific keywords in the modelId and card fields, providing limited insight primarily useful for locating specific entries rather than revealing broad patterns or trends.
Qwen 7B Distilled Models
Finds all entries containing the terms 'distilled', 'qwen', and '7b' in a case-insensitive manner, providing a filtered set of records but without deeper analysis.
Distilled Qwen 7B Models
The query filters for specific model IDs containing 'distilled', 'qwen', and '7b', providing a basic retrieval of relevant entries but without deeper analysis or insight.
Filtered Model Cards with Distill Qwen2.
Filters and retrieves records containing specific keywords in the card description while excluding certain phrases, providing a basic count of relevant entries.
Filtered Model Cards with Distill Qwen 7
The query filters specific variations of card descriptions containing 'distill', 'qwen', and '7b' while excluding a particular base model, providing limited but specific data retrieval.
Distill Qwen 7B Model Cards
The query filters and retrieves rows where the 'card' column contains specific keywords ('distill', 'qwen', and '7b'), providing a basic filter result that can help in identifying specific entries.