modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-09-14 00:42:58
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 558
values | tags
listlengths 1
4.05k
| pipeline_tag
stringclasses 55
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-09-14 00:36:41
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
IAAR-Shanghai/MARA_AGENTS
|
IAAR-Shanghai
| 2025-08-20T11:09:44Z | 0 | 0 | null |
[
"text-generation",
"en",
"dataset:PKU-Alignment/PKU-SafeRLHF",
"dataset:HuggingFaceH4/ultrafeedback_binarized",
"dataset:Anthropic/hh-rlhf",
"dataset:PKU-Alignment/BeaverTails-Evaluation",
"dataset:declare-lab/HarmfulQA",
"arxiv:2505.19743",
"base_model:meta-llama/Llama-3.1-8B-Instruct",
"base_model:finetune:meta-llama/Llama-3.1-8B-Instruct",
"license:apache-2.0",
"region:us"
] |
text-generation
| 2025-05-12T06:03:36Z |
---
base_model:
- meta-llama/Llama-3.1-8B-Instruct
- meta-llama/Llama-3.2-3B-Instruct
- meta-llama/Llama-3.2-1B-Instruct
- meta-llama/Meta-Llama-3-8B-Instruct
- mistralai/Mistral-7B-Instruct-v0.1
- mistralai/Mistral-7B-Instruct-v0.2
- mistralai/Mistral-7B-Instruct-v0.3
datasets:
- PKU-Alignment/PKU-SafeRLHF
- HuggingFaceH4/ultrafeedback_binarized
- Anthropic/hh-rlhf
- PKU-Alignment/BeaverTails-Evaluation
- declare-lab/HarmfulQA
language:
- en
license: apache-2.0
pipeline_tag: text-generation
---
<p align="center">
<img src="icons.png" alt="MARA Icon" width="50" height="50"/>
</p>
<h1 align="center">
MARA AGENTS
</h1>
<div style="display: flex; justify-content: center; gap: 10px;">
<a href="https://github.com/IAAR-Shanghai/MARA">
<img src="https://img.shields.io/badge/GitHub-Repository-blue?logo=github" alt="GitHub"/>
</a>
<a href="https://huggingface.co/IAAR-Shanghai/MARA_AGENTS">
<img src="https://img.shields.io/badge/🤗%20Hugging%20 Face-MARA_AGENTS-yellow" alt="Hugging Face"/>
</a>
<a href="https://arxiv.org/abs/2505.19743">
<img src="https://img.shields.io/badge/arXiv-Paper-8B0000?style=flat-square&logo=arxiv&logoColor=white">
</a>
</div>
**MARA** (Micro token-level Accept-Reject Alignment) simplifies the alignment process by breaking down sentence-level preference learning into fine-grained token-level binary classification. The MARA agent—a lightweight multi-layer perceptron (MLP)—operates as an alignment model that evaluates and classifies each candidate token as either *Accepted* or *Rejected* during LLM text generation.
<figure>
<img src="mara_architecture.png" alt="mara_architecture" style="display: block; margin: 0 auto;" />
<figcaption style="text-align: center;">Architecture of MARA: The alignment model performs token selection through accept-reject decisions.</figcaption>
</figure>
### 💫 Get MARA Agent Align Result
```python
from mara_generator import MARAGenerator
agent_path = "mistral_v3_2_1_actor.pth"
base_model_path = "path2model/Mistral-7B-Instruct-v0.3"
mara_generator = MARAGenerator(agent_path, base_model_path)
instruction = "Please introduce yourself."
raw_result = mara_generator.get_raw_output(instruction, do_sample=False)
print("base model answer: ")
print(raw_result["answer"])
align_result = mara_generator.get_proxy_output(instruction)
print("mara agent align answer: ")
print(align_result["answer"])
```
### 🔨Train Your MARA Agent
The source code and implementation details are open-sourced at [MARA](https://github.com/IAAR-Shanghai/MARA) – you can train your custom alignment model by following the provided instructions.
### 📊 Experiment Results
<table class="center">
<tr>
<td width=100% style="border: none">
<img src="table1.png" style="width:50%; max-width:100%;">
<div style="text-align: left; margin-top: 8px;">Performance improvements of MARA across PKUSafeRLHF, BeaverTails, and HarmfulQA datasets. Each entry shows the percentage improvement in preference rate achieved by applying MARA compared to using the original LLM alone.</div>
</td>
</tr>
</table>
<table class="center">
<tr>
<td width=100% style="border: none">
<img src="table3.png" style="width:50%; max-width:100%;">
<div style="text-align: left; margin-top: 8px;">Compatibility analysis of MARA, an alignment model trained with a LLM to be aggregate with other inference LLM. The value of each cell represents the percentage improvement in preference rate of our algorithm over the upstream model, i.e., inference model.</div>
</td>
</tr>
</table>
<table class="center">
<tr>
<td width=100% style="border: none">
<img src="table2.png" style="width:100%">
<div style="text-align: left; margin-top: 8px;">Performance comparison of MARA against RLHF, DPO, and Aligner measured by percentage improvements of preference rate.</div>
</td>
</tr>
</table>
More details and analyses about experimental results can be found in our [paper](https://arxiv.org/abs/2505.19743).
### ✍️ Citation
If the code or the paper has been useful in your research, please add a citation to our work:
```
@article{zhang2025tokenlevelacceptrejectmicro,
title={Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models},
author={Yang Zhang and Yu Yu and Bo Tang and Yu Zhu and Chuxiong Sun and Wenqiang Wei and Jie Hu and Zipeng Xie and Zhiyu Li and Feiyu Xiong and Edward Chung},
journal={arXiv preprint arXiv:2505.19743},
year={2025}
}
```
|
Ferdi3425/blockassist-bc-amphibious_deadly_otter_1755688046
|
Ferdi3425
| 2025-08-20T11:08:38Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"amphibious deadly otter",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T11:08:11Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- amphibious deadly otter
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
aralper18/blockassist-bc-gilded_tangled_albatross_1755688032
|
aralper18
| 2025-08-20T11:07:51Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"gilded tangled albatross",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T11:07:42Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- gilded tangled albatross
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
quantumxnode/blockassist-bc-dormant_peckish_seahorse_1755686422
|
quantumxnode
| 2025-08-20T11:06:31Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"dormant peckish seahorse",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T11:06:28Z |
---
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).
|
ver-video-intimo-de-abigail-lalama-clip/ver.filtrado.Video.de.Abigail.Lalama.y.Snayder
|
ver-video-intimo-de-abigail-lalama-clip
| 2025-08-20T11:03:33Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-08-20T11:01:19Z |
<animated-image data-catalyst=""><a href="https://tinyurl.com/5xr5mb3e?leaked-videos/" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Foo" data-canonical-src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a>
Abigail Lalama viral: influencer confirma video con Snayder en Telegram
El nombre Abigail Lalama se hace viral y crece en Telegram y X tras la filtración de su video con Snayder. Te contamos quiénes son y qué pasó.
Imagen de Abigail Lalama viral: influencer confirma video con Snayder en Telegram
Abigail confirmó la filtración del contenido. - Foto: Instagram abigail_lalama
El nombre Abigail Lalama se hizo viral en redes sociales como Telegram y Twitter (ahora X) luego de que se confirmara la filtración de un video íntimo con Snayder. Esto provocó un repunte de búsquedas como “Abigail Lalama video filtrado”, “Video de Abigail y Snayder filtrado”, “Abigail Lalama Telegram”, entre otras.
La confirmación llegó directamente de la influencer, lo que desencadenó una ola de comentarios, reacciones y solidaridad en línea. A continuación, te contamos quién es Abigail Lalama, quién es Snayder, qué dijo ella, y por qué este caso se viralizó tan rápido.
LEA TAMBIÉN: ¿Qué dijo Mariana Botas de Drake Bell?, ¿qué contestó el cantante?
View post on TikTok
¿Quién es Abigail Lalama y por qué es conocida?
Abigail Lalama es una creadora de contenido ecuatoriana de 22 años, originaria de Guayaquil, que ha ganado popularidad principalmente en TikTok, donde comparte lives, retos, momentos familiares y contenidos cotidianos junto a su hermana gemela, Génesis.
Su comunidad se ha consolidado gracias a su cercanía, su carisma y su estilo familiar. En TikTok, su cuenta @laoficialabigail cuenta con más de 400 000 seguidores y en Instagram supera los 173,000. Con su hermana, forma el ‘Team Lalama’, difundiendo contenidos centrados en diario vivir, maternidad y lazos familiares.
¿Quién es Snayder y qué video se filtró?
La identidad precisa de Snayder no ha sido desvelada en los medios principales consultados hasta el momento, pero se sabe que es un conocido en el entorno de Abigail, supuestamente su expareja.
El video filtrado, descrito como íntimo, fue subido a plataformas como Telegram y TikTok. Usuarios reportaron que la joven que aparece en la grabación viral compartía tatuajes y rasgos con Abigail Lalama. Según Abigail, el video circuló sin su consentimiento, y la filtración se la atribuye a dicho ex.
View post on TikTok
¿Qué dijo Abigail Lalama sobre la filtración?
En un video en vivo, visiblemente afectada y entre lágrimas, Abigail Lalama confirmó la filtración viral del contenido. Ella acusó directamente a su expareja de haber difundido ese material íntimo con la intención de incomodar a su nueva relación.
|
milliarderdol/blockassist-bc-roaring_rough_scorpion_1755685708
|
milliarderdol
| 2025-08-20T11:01:30Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"roaring rough scorpion",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T11:01:08Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- roaring rough scorpion
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
Ferdi3425/blockassist-bc-amphibious_deadly_otter_1755687569
|
Ferdi3425
| 2025-08-20T11:00:45Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"amphibious deadly otter",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T11:00:19Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- amphibious deadly otter
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
VIDEOS-18-vietnamese-viral-video-Clip/New.full.videos.vietnamese.Viral.Video.Official.Tutorial
|
VIDEOS-18-vietnamese-viral-video-Clip
| 2025-08-20T11:00:08Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-08-20T11:00:00Z |
<a href="https://sdu.sk/AyL"><img src="https://files.qatarliving.com/event/2025/06/20/Jawan69_0-1749987397680.gif" alt="fsd" /></a>
<a href="https://sdu.sk/AyL" rel="nofollow">🔴 ➤►𝐂𝐥𝐢𝐤 𝐇𝐞𝐫𝐞 𝐭𝐨👉👉 (𝙨𝙞𝙜𝙣 𝙪𝙥 𝙖𝙣𝙙 𝙬𝙖𝙩𝙘𝙝 𝙛𝙪𝙡𝙡 𝙫𝙞𝙙𝙚𝙤 𝙃𝘿)</a>
<a href="https://sdu.sk/AyL" rel="nofollow">🔴 ➤►𝐂𝐥𝐢𝐤 𝐇𝐞𝐫𝐞 𝐭𝐨👉👉 (𝐅𝐮𝐥𝐥 𝐯𝐢𝐝𝐞𝐨 𝐋𝐢𝐧𝐤)</a>
|
kapalbalap/blockassist-bc-peaceful_wary_owl_1755687474
|
kapalbalap
| 2025-08-20T10:58:50Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"peaceful wary owl",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:58:36Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- peaceful wary owl
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
aralper18/blockassist-bc-gilded_tangled_albatross_1755687456
|
aralper18
| 2025-08-20T10:58:16Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"gilded tangled albatross",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:58:07Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- gilded tangled albatross
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
lc700x/dpt-dinov2-base-kitti
|
lc700x
| 2025-08-20T10:58:13Z | 0 | 0 | null |
[
"safetensors",
"dpt",
"vision",
"depth-estimation",
"dinov2",
"arxiv:2304.07193",
"arxiv:2103.13413",
"license:apache-2.0",
"region:us"
] |
depth-estimation
| 2025-08-20T03:01:42Z |
---
license: apache-2.0
tags:
- vision
- depth-estimation
- dinov2
inference: false
---
# Model Card: DPT model with DINOv2 backbone
## Model Details
DPT (Dense Prediction Transformer) model with DINOv2 backbone as proposed in [DINOv2: Learning Robust Visual Features without Supervision](https://arxiv.org/abs/2304.07193) by Oquab et al.
<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/dpt_architecture.jpg"
alt="drawing" width="600"/>
<small> DPT architecture. Taken from the <a href="https://arxiv.org/abs/2103.13413" target="_blank">original paper</a>. </small>
### Resources
- [DINOv2 Paper](https://arxiv.org/abs/2304.07193)
- [DPT Paper](https://arxiv.org/abs/2103.13413)
### Use with Transformers
```python
from transformers import AutoImageProcessor, DPTForDepthEstimation
import torch
import numpy as np
from PIL import Image
import requests
url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)
image_processor = AutoImageProcessor.from_pretrained("facebook/dpt-dinov2-base-kitti")
model = DPTForDepthEstimation.from_pretrained("facebook/dpt-dinov2-base-kitti")
# prepare image for the model
inputs = image_processor(images=image, return_tensors="pt")
with torch.no_grad():
outputs = model(**inputs)
predicted_depth = outputs.predicted_depth
# interpolate to original size
prediction = torch.nn.functional.interpolate(
predicted_depth.unsqueeze(1),
size=image.size[::-1],
mode="bicubic",
align_corners=False,
)
# visualize the prediction
output = prediction.squeeze().cpu().numpy()
formatted = (output * 255 / np.max(output)).astype("uint8")
depth = Image.fromarray(formatted)
```
## Model Use
### Intended Use
The model is intended to showcase that using the DPT framework with DINOv2 as backbone yields a powerful depth estimator.
### BibTeX entry and citation info
```bibtex
@misc{oquab2023dinov2,
title={DINOv2: Learning Robust Visual Features without Supervision},
author={Maxime Oquab and Timothée Darcet and Théo Moutakanni and Huy Vo and Marc Szafraniec and Vasil Khalidov and Pierre Fernandez and Daniel Haziza and Francisco Massa and Alaaeldin El-Nouby and Mahmoud Assran and Nicolas Ballas and Wojciech Galuba and Russell Howes and Po-Yao Huang and Shang-Wen Li and Ishan Misra and Michael Rabbat and Vasu Sharma and Gabriel Synnaeve and Hu Xu and Hervé Jegou and Julien Mairal and Patrick Labatut and Armand Joulin and Piotr Bojanowski},
year={2023},
eprint={2304.07193},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
```
|
kapalbalap/blockassist-bc-peaceful_wary_owl_1755687296
|
kapalbalap
| 2025-08-20T10:55:59Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"peaceful wary owl",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:55:45Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- peaceful wary owl
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
ver-video-intimo-de-abigail-lalama-clip/VER.intimo.video.de.abigail.lalama.y.snayder.filtrado.en.telegram.se.vuelve.viral
|
ver-video-intimo-de-abigail-lalama-clip
| 2025-08-20T10:54:31Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-08-20T10:51:35Z |
<animated-image data-catalyst=""><a href="https://tinyurl.com/5xr5mb3e?leaked-videos/" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Foo" data-canonical-src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a>
Abigail Lalama viral: influencer confirma video con Snayder en Telegram
El nombre Abigail Lalama se hace viral y crece en Telegram y X tras la filtración de su video con Snayder. Te contamos quiénes son y qué pasó.
Imagen de Abigail Lalama viral: influencer confirma video con Snayder en Telegram
Abigail confirmó la filtración del contenido. - Foto: Instagram abigail_lalama
El nombre Abigail Lalama se hizo viral en redes sociales como Telegram y Twitter (ahora X) luego de que se confirmara la filtración de un video íntimo con Snayder. Esto provocó un repunte de búsquedas como “Abigail Lalama video filtrado”, “Video de Abigail y Snayder filtrado”, “Abigail Lalama Telegram”, entre otras.
La confirmación llegó directamente de la influencer, lo que desencadenó una ola de comentarios, reacciones y solidaridad en línea. A continuación, te contamos quién es Abigail Lalama, quién es Snayder, qué dijo ella, y por qué este caso se viralizó tan rápido.
LEA TAMBIÉN: ¿Qué dijo Mariana Botas de Drake Bell?, ¿qué contestó el cantante?
View post on TikTok
¿Quién es Abigail Lalama y por qué es conocida?
Abigail Lalama es una creadora de contenido ecuatoriana de 22 años, originaria de Guayaquil, que ha ganado popularidad principalmente en TikTok, donde comparte lives, retos, momentos familiares y contenidos cotidianos junto a su hermana gemela, Génesis.
Su comunidad se ha consolidado gracias a su cercanía, su carisma y su estilo familiar. En TikTok, su cuenta @laoficialabigail cuenta con más de 400 000 seguidores y en Instagram supera los 173,000. Con su hermana, forma el ‘Team Lalama’, difundiendo contenidos centrados en diario vivir, maternidad y lazos familiares.
¿Quién es Snayder y qué video se filtró?
La identidad precisa de Snayder no ha sido desvelada en los medios principales consultados hasta el momento, pero se sabe que es un conocido en el entorno de Abigail, supuestamente su expareja.
El video filtrado, descrito como íntimo, fue subido a plataformas como Telegram y TikTok. Usuarios reportaron que la joven que aparece en la grabación viral compartía tatuajes y rasgos con Abigail Lalama. Según Abigail, el video circuló sin su consentimiento, y la filtración se la atribuye a dicho ex.
View post on TikTok
¿Qué dijo Abigail Lalama sobre la filtración?
En un video en vivo, visiblemente afectada y entre lágrimas, Abigail Lalama confirmó la filtración viral del contenido. Ella acusó directamente a su expareja de haber difundido ese material íntimo con la intención de incomodar a su nueva relación.
Sus palabras fueron duras y reflejaron desilusión y dolor: “Eso es lo peor que le puede hacer un hombre… Yo fui, sí, una estúpida en dejarme grabar con él… Pues siendo mi pareja coge y lo sube… el sinvergüenza. No tiene sangre en la cara”.
También añadió una reflexión sobre confianza y peor traición: “Ahí es cuando uno se da cuenta con quién duerme, ahí es cuando se sacan la máscara”. Posteriormente, compartió en sus historias videos de fans que la apoyaban, junto a clips con actitud más serena, mostrando resiliencia frente a la situación.
¿Qué dice la ley sobre contenido filtrado sin consentimiento?
En Ecuador, compartir contenido íntimo sin consentimiento está penalizado por el Código Orgánico Integral Penal (COIP). El artículo 178 castiga la difusión de imágenes o videos íntimos sin autorización con penas de uno a tres años. Además, el artículo 230, relativo a violencia digital, puede elevar la sanción hasta cuatro años si hay intención de dañar o humillar.
Abigail tiene la opción de denunciar ante la Fiscalía General del Estado, la Unidad de Policía Comunitaria (UPC), el portal del Consejo de la Judicatura o acudir a la Defensoría del Pueblo y organizaciones que brindan apoyo psicológico y asesoría legal. También se pueden solicitar medidas como la eliminación del contenido y reparación integral.
|
Mostefa-Terbeche/diabetic-retinopathy-aptos-vit_b_16-original-20250707-233531
|
Mostefa-Terbeche
| 2025-08-20T10:54:10Z | 0 | 0 | null |
[
"diabetic-retinopathy",
"medical-imaging",
"pytorch",
"computer-vision",
"retinal-imaging",
"dataset:aptos",
"license:apache-2.0",
"model-index",
"region:us"
] | null | 2025-08-20T08:02:11Z |
---
license: apache-2.0
tags:
- diabetic-retinopathy
- medical-imaging
- pytorch
- computer-vision
- retinal-imaging
datasets:
- aptos
metrics:
- accuracy
- quadratic-kappa
- auc
model-index:
- name: aptos_vit_b_16_original
results:
- task:
type: image-classification
name: Diabetic Retinopathy Classification
dataset:
type: aptos
name: APTOS
metrics:
- type: accuracy
value: 0.7103825136612022
- type: quadratic-kappa
value: 0.8582862102858018
---
# Diabetic Retinopathy Classification Model
## Model Description
This model is trained for diabetic retinopathy classification using the vit_b_16 architecture on the aptos dataset with original preprocessing.
## Model Details
- **Architecture**: vit_b_16
- **Dataset**: aptos
- **Preprocessing**: original
- **Training Date**: 20250707-233531
- **Task**: 5-class diabetic retinopathy grading (0-4)
- **Directory**: aptos_vit_b_16_20250707-233531_new
## Performance
- **Test Accuracy**: 0.7103825136612022
- **Test Quadratic Kappa**: 0.8582862102858018
- **Validation Kappa**: 0.8582862102858018
## Usage
```python
import torch
from huggingface_hub import hf_hub_download
# Download model
model_path = hf_hub_download(
repo_id="your-username/diabetic-retinopathy-aptos-vit_b_16-original",
filename="model_best.pt"
)
# Load model
model = torch.load(model_path, map_location='cpu')
```
## Classes
- 0: No DR (No diabetic retinopathy)
- 1: Mild DR (Mild non-proliferative diabetic retinopathy)
- 2: Moderate DR (Moderate non-proliferative diabetic retinopathy)
- 3: Severe DR (Severe non-proliferative diabetic retinopathy)
- 4: Proliferative DR (Proliferative diabetic retinopathy)
## Citation
If you use this model, please cite your research paper/thesis.
|
starf5/so101PickPinkChoco_policy
|
starf5
| 2025-08-20T10:54:09Z | 10 | 0 |
lerobot
|
[
"lerobot",
"safetensors",
"robotics",
"smolvla",
"dataset:starf5/so101PickPinkChoco",
"arxiv:2506.01844",
"base_model:lerobot/smolvla_base",
"base_model:finetune:lerobot/smolvla_base",
"license:apache-2.0",
"region:us"
] |
robotics
| 2025-07-31T01:43:35Z |
---
base_model: lerobot/smolvla_base
datasets: starf5/so101PickPinkChoco
library_name: lerobot
license: apache-2.0
model_name: smolvla
pipeline_tag: robotics
tags:
- lerobot
- robotics
- smolvla
---
# Model Card for smolvla
<!-- Provide a quick summary of what the model is/does. -->
[SmolVLA](https://huggingface.co/papers/2506.01844) is a compact, efficient vision-language-action model that achieves competitive performance at reduced computational costs and can be deployed on consumer-grade hardware.
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
lerobot-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
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
|
kapalbalap/blockassist-bc-peaceful_wary_owl_1755687134
|
kapalbalap
| 2025-08-20T10:53:03Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"peaceful wary owl",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:52:50Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- peaceful wary owl
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
ihsanridzi/blockassist-bc-wiry_flexible_owl_1755685461
|
ihsanridzi
| 2025-08-20T10:51:57Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"wiry flexible owl",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:51:53Z |
---
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).
|
chainway9/blockassist-bc-untamed_quick_eel_1755685251
|
chainway9
| 2025-08-20T10:49:29Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"untamed quick eel",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:49:26Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- untamed quick eel
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
aralper18/blockassist-bc-gilded_tangled_albatross_1755686891
|
aralper18
| 2025-08-20T10:48:52Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"gilded tangled albatross",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:48:45Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- gilded tangled albatross
---
# 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_1755686419
|
chooseL1fe
| 2025-08-20T10:47:47Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"thorny flightless albatross",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:47:44Z |
---
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).
|
kapalbalap/blockassist-bc-peaceful_wary_owl_1755686814
|
kapalbalap
| 2025-08-20T10:47:42Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"peaceful wary owl",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:47:30Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- peaceful wary owl
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
ilkhom199/8790b2d7-a501-485e-a562-a07401e8f05a
|
ilkhom199
| 2025-08-20T10:47:31Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"llama-factory",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-20T10:46:36Z |
---
library_name: transformers
tags:
- llama-factory
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
hdong0/deepseek-Llama-8B-Open-R1-GRPO_deepscaler_acc_mu_8_constant_lr_no_kl
|
hdong0
| 2025-08-20T10:47:08Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"generated_from_trainer",
"open-r1",
"trl",
"grpo",
"conversational",
"dataset:agentica-org/DeepScaleR-Preview-Dataset",
"arxiv:2402.03300",
"base_model:deepseek-ai/DeepSeek-R1-Distill-Llama-8B",
"base_model:finetune:deepseek-ai/DeepSeek-R1-Distill-Llama-8B",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-19T20:55:11Z |
---
base_model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
datasets: agentica-org/DeepScaleR-Preview-Dataset
library_name: transformers
model_name: deepseek-Llama-8B-Open-R1-GRPO_deepscaler_acc_mu_8_constant_lr_no_kl
tags:
- generated_from_trainer
- open-r1
- trl
- grpo
licence: license
---
# Model Card for deepseek-Llama-8B-Open-R1-GRPO_deepscaler_acc_mu_8_constant_lr_no_kl
This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Llama-8B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B) on the [agentica-org/DeepScaleR-Preview-Dataset](https://huggingface.co/datasets/agentica-org/DeepScaleR-Preview-Dataset) dataset.
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="hdong0/deepseek-Llama-8B-Open-R1-GRPO_deepscaler_acc_mu_8_constant_lr_no_kl", 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: 0.18.0.dev0
- Transformers: 4.52.0.dev0
- Pytorch: 2.6.0
- Datasets: 3.6.0
- Tokenizers: 0.21.1
## Citations
Cite GRPO as:
```bibtex
@article{zhihong2024deepseekmath,
title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
year = 2024,
eprint = {arXiv:2402.03300},
}
```
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
```
|
Ferdi3425/blockassist-bc-amphibious_deadly_otter_1755686740
|
Ferdi3425
| 2025-08-20T10:46:53Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"amphibious deadly otter",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:46:26Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- amphibious deadly otter
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
original-Isha-Malviya-Viral-video-Clip/New.full.videos.isha.malviya.Viral.Video.Official.Tutorial
|
original-Isha-Malviya-Viral-video-Clip
| 2025-08-20T10:46:14Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-08-20T10:46:00Z |
<a href="https://sdu.sk/AyL"><img src="https://files.qatarliving.com/event/2025/06/20/Jawan69_0-1749987397680.gif" alt="fsd" /></a>
<a href="https://sdu.sk/AyL" rel="nofollow">🔴 ➤►𝐂𝐥𝐢𝐤 𝐇𝐞𝐫𝐞 𝐭𝐨👉👉 (𝙨𝙞𝙜𝙣 𝙪𝙥 𝙖𝙣𝙙 𝙬𝙖𝙩𝙘𝙝 𝙛𝙪𝙡𝙡 𝙫𝙞𝙙𝙚𝙤 𝙃𝘿)</a>
<a href="https://sdu.sk/AyL" rel="nofollow">🔴 ➤►𝐂𝐥𝐢𝐤 𝐇𝐞𝐫𝐞 𝐭𝐨👉👉 (𝐅𝐮𝐥𝐥 𝐯𝐢𝐝𝐞𝐨 𝐋𝐢𝐧𝐤)</a>
|
sampingkaca72/blockassist-bc-armored_stealthy_elephant_1755685146
|
sampingkaca72
| 2025-08-20T10:45:51Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"armored stealthy elephant",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:45:47Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- armored stealthy elephant
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
kojeklollipop/blockassist-bc-spotted_amphibious_stork_1755684954
|
kojeklollipop
| 2025-08-20T10:43:54Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"spotted amphibious stork",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:43:51Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- spotted amphibious stork
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
gauravvivek8/llama2finetune
|
gauravvivek8
| 2025-08-20T10:42:09Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-20T10:38:26Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
Xyeru/qwen-0.6b-touch-rugby
|
Xyeru
| 2025-08-20T10:40:59Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"qwen3",
"trl",
"en",
"base_model:unsloth/Qwen3-0.6B-unsloth-bnb-4bit",
"base_model:finetune:unsloth/Qwen3-0.6B-unsloth-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-08-19T18:51:29Z |
---
base_model: unsloth/Qwen3-0.6B-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- qwen3
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** Xyeru
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Qwen3-0.6B-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)
|
unitova/blockassist-bc-zealous_sneaky_raven_1755684772
|
unitova
| 2025-08-20T10:39:51Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"zealous sneaky raven",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:39:48Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- zealous sneaky raven
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
Sayemahsjn/blockassist-bc-playful_feline_octopus_1755685231
|
Sayemahsjn
| 2025-08-20T10:39:14Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"playful feline octopus",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:39:09Z |
---
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).
|
trunghieuma22/finetuned_model
|
trunghieuma22
| 2025-08-20T10:39:13Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"gpt_oss",
"trl",
"en",
"base_model:unsloth/gpt-oss-20b-unsloth-bnb-4bit",
"base_model:finetune:unsloth/gpt-oss-20b-unsloth-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-08-20T10:39:05Z |
---
base_model: unsloth/gpt-oss-20b-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- gpt_oss
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** trunghieuma22
- **License:** apache-2.0
- **Finetuned from model :** unsloth/gpt-oss-20b-unsloth-bnb-4bit
This gpt_oss 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)
|
manusiaperahu2012/blockassist-bc-roaring_long_tuna_1755684697
|
manusiaperahu2012
| 2025-08-20T10:38:39Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"roaring long tuna",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:38:36Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- roaring long tuna
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
katanyasekolah/blockassist-bc-silky_sprightly_cassowary_1755684588
|
katanyasekolah
| 2025-08-20T10:38:02Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"silky sprightly cassowary",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:37:59Z |
---
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).
|
VIDEOS-18-brown-girl-viral-video-Clip/New.full.videos.brown.girl.Viral.Video.Official.Tutorial
|
VIDEOS-18-brown-girl-viral-video-Clip
| 2025-08-20T10:37:48Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-08-20T10:37:36Z |
<a href="https://sdu.sk/AyL"><img src="https://files.qatarliving.com/event/2025/06/20/Jawan69_0-1749987397680.gif" alt="fsd" /></a>
<a href="https://sdu.sk/AyL" rel="nofollow">🔴 ➤►𝐂𝐥𝐢𝐤 𝐇𝐞𝐫𝐞 𝐭𝐨👉👉 (𝙨𝙞𝙜𝙣 𝙪𝙥 𝙖𝙣𝙙 𝙬𝙖𝙩𝙘𝙝 𝙛𝙪𝙡𝙡 𝙫𝙞𝙙𝙚𝙤 𝙃𝘿)</a>
<a href="https://sdu.sk/AyL" rel="nofollow">🔴 ➤►𝐂𝐥𝐢𝐤 𝐇𝐞𝐫𝐞 𝐭𝐨👉👉 (𝐅𝐮𝐥𝐥 𝐯𝐢𝐝𝐞𝐨 𝐋𝐢𝐧𝐤)</a>
|
chowshib/blockassist-bc-majestic_melodic_beaver_1755686083
|
chowshib
| 2025-08-20T10:36:13Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"majestic melodic beaver",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:36:01Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- majestic melodic beaver
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
quantumxnode/blockassist-bc-dormant_peckish_seahorse_1755684494
|
quantumxnode
| 2025-08-20T10:34:06Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"dormant peckish seahorse",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:34:02Z |
---
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).
|
amaye15/autoencoder-robust-demo
|
amaye15
| 2025-08-20T10:33:25Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"autoencoder",
"feature-extraction",
"generated_from_trainer",
"custom_code",
"region:us"
] |
feature-extraction
| 2025-08-20T10:17:58Z |
---
library_name: transformers
tags:
- generated_from_trainer
model-index:
- name: autoencoder-robust-demo
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. -->
# autoencoder-robust-demo
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: 0.001
- train_batch_size: 64
- eval_batch_size: 64
- 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: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 1.0 | 3 | 1.5616 |
### Framework versions
- Transformers 4.55.2
- Pytorch 2.8.0
- Datasets 4.0.0
- Tokenizers 0.21.4
|
kapalbalap/blockassist-bc-peaceful_wary_owl_1755685914
|
kapalbalap
| 2025-08-20T10:32:45Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"peaceful wary owl",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:32:30Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- peaceful wary owl
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
loyal-misc/portalchambers
|
loyal-misc
| 2025-08-20T10:31:19Z | 0 | 0 |
diffusers
|
[
"diffusers",
"text-to-image",
"lora",
"template:diffusion-lora",
"base_model:LyliaEngine/Pony_Diffusion_V6_XL",
"base_model:adapter:LyliaEngine/Pony_Diffusion_V6_XL",
"license:unlicense",
"region:us"
] |
text-to-image
| 2025-08-20T10:17:13Z |
---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- output:
url: images/portalchambers39.png
text: >-
Portal2, testchamber, box, light, white background, empty, complex,
futuristic, sci-fi, science fiction, game, video game, blue red green yellow
dark black, intricate lines, hard edges, perfect, masterpiece, microscopic
detail, miniature, figurine style, circle, oval, dodecahedron, brick,
concrete background, serene, important, impressive, image, jpeg,
16:9,9:16,1:1,?
base_model: LyliaEngine/Pony_Diffusion_V6_XL
instance_prompt: portal, testchamber
license: unlicense
---
# portalchambers
<Gallery />
## Trigger words
You should use `portal` to trigger the image generation.
You should use `testchamber` to trigger the image generation.
## Download model
[Download](/loyal-misc/portalchambers/tree/main) them in the Files & versions tab.
|
meetween/Llama-speechlmm-1.0-s
|
meetween
| 2025-08-20T10:30:25Z | 4 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llava",
"feature-extraction",
"generated_from_trainer",
"endpoints_compatible",
"region:us"
] |
feature-extraction
| 2025-03-01T11:09:40Z |
---
library_name: transformers
tags:
- generated_from_trainer
model-index:
- name: Llama-speechlmm-1.0-s
results: []
---
## Model information
The SpeechLMM 1.0 collection of multimodal and multilingual large language models is a collection of instruction-tuned generative models in 4 different sizes: S (2B), M (4B), L (9B) and XL (71B), supporting text, audio and video as input and only text as output. The SpeechLMM 1.0 models are optimized for various X-to-text generation tasks, namely:
- Machine Translation
- Automatic Speech Recognition
- Speech Translation
- Speech Summarization
- Spoken Question Answering
- Spoken Language Understanding (beta)
- Visual Speech Recognition (beta)
**Model Developer:** Meetween consortium
**Supported Languages:** English, French, Italian, German, and Spanish are officially supported (for a subset of the supported tasks). The Llama 3.X backbone and the SeamlessM4T v2 audio encoder have been trained on a broader collection of languages than these 5 supported languages, so the model might exhibit good performance on other languages too.
**Model Release Date:** Feb 28, 2025
**License:** see [LICENSE](LICENSE)
### Model Architecture
SpeechLMM 1.0 an auto-regressive multimodal language model based on a Llama 3.X backbone (X varies with the model size), a speech-specific stack consisting of a pre-trained audio encoder ([SeamlessM4T v2](https://ai.meta.com/research/publications/seamless-multilingual-expressive-and-streaming-speech-translation/)) and an audio adapter, and a video-specific stack consisting of a pre-trained video encoder ([Auto-AVSR](https://ieeexplore.ieee.org/document/10096889)) and a video adapter.
<!-- TODO: add the image of the model architecture here -->
| Model | Params | Input modalities | Output modalities | Context Length |
|:---------------- |:----------- |:------------------------------------------ |:----------------- |:-------------- |
| SpeechLMM 1.0 S | 2B (2.17B) | Multilingual text and audio, English video | Multilingual Text | 128k |
| SpeechLMM 1.0 M | 4B (4.15B) | Multilingual text and audio, English video | Multilingual Text | 128k |
| SpeechLMM 1.0 L | 9B (8.98B) | Multilingual text and audio, English video | Multilingual Text | 128k |
| SpeechLMM 1.0 XL (beta) | 71B (71.5B) | Multilingual text and audio, English video | Multilingual Text | 128k |
#### Audio and video encoders
For all the 4 sizes of SpeechLMM 1.0, the audio encoder is **SeamlessM4T v2 Large** (`facebook/seamless-m4t-v2-large`) and the video encoder is **Auto-AVSR** (`vsr_trlrs3vox2_base`).
#### Audio and video adapters
For all the 4 sizes of SpeechLMM 1.0, the audio and video adapters are:
| Modality | Architecture | Number of layers | Compression factor |
| :------- | :----------- | :--------------- | :----------------- |
| Audio | MLP | 4 | 1 |
| Video | Window-level Q-former <br> (4 queries) | 4 | 4 |
#### LLM backbone
| Model | Backbone |
|:---------------- |:---------------------- |
| SpeechLMM 1.0 S | Llama 3.2 1B Instruct |
| SpeechLMM 1.0 M | Llama 3.2 3B Instruct |
| SpeechLMM 1.0 L | Llama 3.1 8B Instruct |
| SpeechLMM 1.0 XL (beta) | Llama 3.3 70B Instruct |
## How to use
Currently, this model can only be used via our [`speechlmm`](https://github.com/meetween/speechlmm) codebase. Refer to the instructions there for more details.
Important: before you can use this model, you must download the SeamlessM4T v2 speech encoder and the Auto-AVSR video encoder by following the instructions provided in the README of the above repo. Please note that by doing so, you agree with their respective license terms.
## Training Data
### Monolingual
| TASK | Task name | Dataset | Language | License |
| -------- | ---------------------------- | ------------------ | -------- | ------------------------------------------ |
| **ASR** | Automatic Speech Recognition | **LibriHeavy** | en | CC-BY-4.0 |
| | | **LibriTTS** | en | CC BY 4.0 |
| | | **AMI** | en | CC-BY-4.0 |
| | | **ICSI** | en | CC-BY-4.0 |
| **LIPREAD** | Visual Speech Recognition | **LRS2-BBC** | en | Custom |
| **SSUM** | Speech Summarization | **AMI** | en | CC-BY-4.0 |
| | | **ICSI** | en | CC-BY-4.0 |
| **SQA** | Spoken Question Answering | **Spoken SQUAD** | en | CC-BY-SA-4.0 |
| **SLU** | Spoken Language Understanding| **SLURP** | en | CC BY 4.0 (text) <br> CC BY-NC 4.0 (audio) |
### Multilingual
| TASK | Task name | Dataset | Language | License |
| ---------------- | ----------------------------- | ------------------------------------ | ------------------------------------------- | ------------------------------------------ |
| **ASR** | Automatic Speech Recognition | **CoVoST2** | en, fr, it, de, es | CC0 |
| | | **CommonVoice** | en, fr, it, de, es | Apache-2.0 |
| **ST** | Speech-to-text Translation | **CoVoST2** | en → de, {fr, it, de, es} → en | CC0 |
| | | **EuroParl-ST** | {en, fr, it, de, es} → {en, fr, it, de, es} | CC-BY-NC-4.0 |
| **MT** | Machine Translation | **EuroParl-ST** | {en, fr, it, de, es} → {en, fr, it, de, es} | CC-BY-NC-4.0 |
| **TextInstruct** | Text Instruction Following | **Everything_Instruct_Multilingual** | en, fr, it, de, es, ru, zh, ko, ur, la, ar,<br>hi, ja, nl, pt | Apache-2.0 |
| **SLU** | Spoken Language Understanding | **Speech-Massive** | fr, de | CC-BY-NC-SA-4.0 |
## Evaluation Results
The following results specifically refer to the S model.
### ASR Metrics
| Dataset | Language | WER ⬇ |
|:----------|:-----------|------:|
| **MUSTC** | en | 19.2 |
| **MTEDX** | it | 29.43 |
| **MTEDX** | fr | 28.97 |
| **ACL6060** | en | 19.4 |
| **MTEDX** | es | 29.71 |
### SQA Metrics
| Dataset | Language | Accuracy ⬆ |
|:--------------|:-----------|-----------:|
| **Spoken SQuAD** | en | 65.93 |
**NOTE**: Accuracy is measured with an LLM as a judge (**Llama3-70b-8192**, via the Groq API) using the following prompts:
- **System prompt**
You are a helpful assistant that evaluates answers to questions given a certain context. You will be given inputs of the form:<br>
Context: \<CONTEXT\><br>
Question: \<QUESTION\><br>
Answer: \<ANSWER\><br>
Your task is to determine if the given answer is correct or not, assuming the correct answer is contained in the context. Your response should be formatted as a JSON string having the following structure:
{"correct_answer": \<true/false\>, "rationale": \<RATIONALE\>}
where 'rationale' must be a string explaining why the answer is correct or incorrect. If you need to include double quote characters (") in the 'rationale' string, you must escape them with a backslash (\\). For example, if you want to include the string "Hello, World!", you should write it as \\"Hello, World!\\".
- **User prompt**
Context: \<CONTEXT\><br>
Question: \<QUESTION\><br>
Answer: \<ANSWER\>
### MT Metrics
| Dataset | Source Language | Target Language | Bleu ⬆ | CHRF ⬆ |
|:----------|:------------------|:------------------|-------:|-------:|
| **FLORES** | en | de | 21.11 | 51.77 |
| **FLORES** | en | es | 18.61 | 48.02 |
| **FLORES** | en | it | 16.63 | 47.24 |
| **ACL6060** | en | fr | 34.86 | 60.48 |
| **FLORES** | en | fr | 24 | 55.36 |
### SSUM Metrics
| Dataset | Language | R-1_F1 | R-2_F1 | R-L_F1 |
|:----------|:-----------|---------:|---------:|---------:|
| **ICSI** | en | 22.9 | 2.7 | 20.4 |
### ST Metrics
| Dataset | Source Language | Target Language | Bleu ⬆ | CHRF ⬆ |
|:----------|:------------------|:------------------|-------:|-------:|
| **ACL6060** | en | fr | 28.65 | 56.2 |
| **ACL6060** | en | de | 19.12 | 49.06 |
| **MUSTC** | en | de | 16.98 | 45.48 |
| **MUSTC** | en | it | 14.68 | 43.03 |
| **MUSTC** | en | fr | 19.09 | 48.09 |
| **MUSTC** | en | es | 20.42 | 49.07 |
## Framework versions
- Transformers 4.45.0
- Pytorch 2.3.1+cu124.post2
- Datasets 3.2.0
- Tokenizers 0.20.0
|
kapalbalap/blockassist-bc-peaceful_wary_owl_1755685761
|
kapalbalap
| 2025-08-20T10:30:04Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"peaceful wary owl",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:29:52Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- peaceful wary owl
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
koloni/blockassist-bc-deadly_graceful_stingray_1755684268
|
koloni
| 2025-08-20T10:29:56Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"deadly graceful stingray",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:29:52Z |
---
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).
|
thanobidex/blockassist-bc-colorful_shiny_hare_1755684259
|
thanobidex
| 2025-08-20T10:29:41Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"colorful shiny hare",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:29:37Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- colorful shiny hare
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
ElbertFliek/MyGemmaNPC
|
ElbertFliek
| 2025-08-20T10:28:44Z | 0 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"gemma3_text",
"text-generation",
"generated_from_trainer",
"sft",
"trl",
"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
| 2025-08-19T14:38:22Z |
---
base_model: google/gemma-3-270m-it
library_name: transformers
model_name: MyGemmaNPC
tags:
- generated_from_trainer
- sft
- trl
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="ElbertFliek/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: 2.8.0+cu126
- 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}}
}
```
|
meetween/Llama-speechlmm-1.0-m
|
meetween
| 2025-08-20T10:28:39Z | 3 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llava",
"feature-extraction",
"generated_from_trainer",
"endpoints_compatible",
"region:us"
] |
feature-extraction
| 2025-03-01T11:11:38Z |
---
library_name: transformers
tags:
- generated_from_trainer
model-index:
- name: Llama-speechlmm-1.0-m
results: []
---
## Model information
The SpeechLMM 1.0 collection of multimodal and multilingual large language models is a collection of instruction-tuned generative models in 4 different sizes: S (2B), M (4B), L (9B) and XL (71B), supporting text, audio and video as input and only text as output. The SpeechLMM 1.0 models are optimized for various X-to-text generation tasks, namely:
- Machine Translation
- Automatic Speech Recognition
- Speech Translation
- Speech Summarization
- Spoken Question Answering
- Spoken Language Understanding (beta)
- Visual Speech Recognition (beta)
**Model Developer:** Meetween consortium
**Supported Languages:** English, French, Italian, German, and Spanish are officially supported (for a subset of the supported tasks). The Llama 3.X backbone and the SeamlessM4T v2 audio encoder have been trained on a broader collection of languages than these 5 supported languages, so the model might exhibit good performance on other languages too.
**Model Release Date:** Feb 28, 2025
**License:** see [LICENSE](LICENSE)
### Model Architecture
SpeechLMM 1.0 an auto-regressive multimodal language model based on a Llama 3.X backbone (X varies with the model size), a speech-specific stack consisting of a pre-trained audio encoder ([SeamlessM4T v2](https://ai.meta.com/research/publications/seamless-multilingual-expressive-and-streaming-speech-translation/)) and an audio adapter, and a video-specific stack consisting of a pre-trained video encoder ([Auto-AVSR](https://ieeexplore.ieee.org/document/10096889)) and a video adapter.
<!-- TODO: add the image of the model architecture here -->
| Model | Params | Input modalities | Output modalities | Context Length |
|:---------------- |:----------- |:------------------------------------------ |:----------------- |:-------------- |
| SpeechLMM 1.0 S | 2B (2.17B) | Multilingual text and audio, English video | Multilingual Text | 128k |
| SpeechLMM 1.0 M | 4B (4.15B) | Multilingual text and audio, English video | Multilingual Text | 128k |
| SpeechLMM 1.0 L | 9B (8.98B) | Multilingual text and audio, English video | Multilingual Text | 128k |
| SpeechLMM 1.0 XL (beta) | 71B (71.5B) | Multilingual text and audio, English video | Multilingual Text | 128k |
#### Audio and video encoders
For all the 4 sizes of SpeechLMM 1.0, the audio encoder is **SeamlessM4T v2 Large** (`facebook/seamless-m4t-v2-large`) and the video encoder is **Auto-AVSR** (`vsr_trlrs3vox2_base`).
#### Audio and video adapters
For all the 4 sizes of SpeechLMM 1.0, the audio and video adapters are:
| Modality | Architecture | Number of layers | Compression factor |
| :------- | :----------- | :--------------- | :----------------- |
| Audio | MLP | 4 | 1 |
| Video | Window-level Q-former <br> (4 queries) | 4 | 4 |
#### LLM backbone
| Model | Backbone |
|:---------------- |:---------------------- |
| SpeechLMM 1.0 S | Llama 3.2 1B Instruct |
| SpeechLMM 1.0 M | Llama 3.2 3B Instruct |
| SpeechLMM 1.0 L | Llama 3.1 8B Instruct |
| SpeechLMM 1.0 XL (beta) | Llama 3.3 70B Instruct |
## How to use
Currently, this model can only be used via our [`speechlmm`](https://github.com/meetween/speechlmm) codebase. Refer to the instructions there for more details.
Important: before you can use this model, you must download the SeamlessM4T v2 speech encoder and the Auto-AVSR video encoder by following the instructions provided in the README of the above repo. Please note that by doing so, you agree with their respective license terms.
## Training Data
### Monolingual
| TASK | Task name | Dataset | Language | License |
| -------- | ---------------------------- | ------------------ | -------- | ------------------------------------------ |
| **ASR** | Automatic Speech Recognition | **LibriHeavy** | en | CC-BY-4.0 |
| | | **LibriTTS** | en | CC BY 4.0 |
| | | **AMI** | en | CC-BY-4.0 |
| | | **ICSI** | en | CC-BY-4.0 |
| **LIPREAD** | Visual Speech Recognition | **LRS2-BBC** | en | Custom |
| **SSUM** | Speech Summarization | **AMI** | en | CC-BY-4.0 |
| | | **ICSI** | en | CC-BY-4.0 |
| **SQA** | Spoken Question Answering | **Spoken SQUAD** | en | CC-BY-SA-4.0 |
| **SLU** | Spoken Language Understanding| **SLURP** | en | CC BY 4.0 (text) <br> CC BY-NC 4.0 (audio) |
### Multilingual
| TASK | Task name | Dataset | Language | License |
| ---------------- | ----------------------------- | ------------------------------------ | ------------------------------------------- | ------------------------------------------ |
| **ASR** | Automatic Speech Recognition | **CoVoST2** | en, fr, it, de, es | CC0 |
| | | **CommonVoice** | en, fr, it, de, es | Apache-2.0 |
| **ST** | Speech-to-text Translation | **CoVoST2** | en → de, {fr, it, de, es} → en | CC0 |
| | | **EuroParl-ST** | {en, fr, it, de, es} → {en, fr, it, de, es} | CC-BY-NC-4.0 |
| **MT** | Machine Translation | **EuroParl-ST** | {en, fr, it, de, es} → {en, fr, it, de, es} | CC-BY-NC-4.0 |
| **TextInstruct** | Text Instruction Following | **Everything_Instruct_Multilingual** | en, fr, it, de, es, ru, zh, ko, ur, la, ar,<br>hi, ja, nl, pt | Apache-2.0 |
| **SLU** | Spoken Language Understanding | **Speech-Massive** | fr, de | CC-BY-NC-SA-4.0 |
## Evaluation Results
The following results specifically refer to the M model.
### ASR Metrics
| Dataset | Language | WER ⬇ |
|:----------|:-----------|------:|
| **MUSTC** | en | 16.8 |
| **ACL6060** | en | 18.33 |
| **MTEDX** | es | 26.06 |
| **MTEDX** | fr | 28.13 |
| **MTEDX** | it | 27.79 |
### SQA Metrics
| Dataset | Language | Accuracy ⬆ |
|:--------------|:-----------|-----------:|
| **Spoken SQuAD** | en | 80.56 |
**NOTE**: Accuracy is measured with an LLM as a judge (**Llama3-70b-8192**, via the Groq API) using the following prompts:
- **System prompt**
You are a helpful assistant that evaluates answers to questions given a certain context. You will be given inputs of the form:<br>
Context: \<CONTEXT\><br>
Question: \<QUESTION\><br>
Answer: \<ANSWER\><br>
Your task is to determine if the given answer is correct or not, assuming the correct answer is contained in the context. Your response should be formatted as a JSON string having the following structure:
{"correct_answer": \<true/false\>, "rationale": \<RATIONALE\>}
where 'rationale' must be a string explaining why the answer is correct or incorrect. If you need to include double quote characters (") in the 'rationale' string, you must escape them with a backslash (\\). For example, if you want to include the string "Hello, World!", you should write it as \\"Hello, World!\\".
- **User prompt**
Context: \<CONTEXT\><br>
Question: \<QUESTION\><br>
Answer: \<ANSWER\>
### MT Metrics
| Dataset | Source Language | Target Language | Bleu ⬆ | CHRF ⬆ |
|:----------|:------------------|:------------------|-------:|-------:|
| **FLORES** | en | de | 28.12 | 57.42 |
| **FLORES** | en | es | 22.73 | 51.68 |
| **FLORES** | en | it | 20.97 | 50.83 |
| **FLORES** | en | fr | 36.05 | 61.47 |
| **ACL6060** | en | fr | 40.68 | 64.9 |
### SSUM Metrics
| Dataset | Language | R-1_F1 | R-2_F1 | R-L_F1 |
|:----------|:-----------|---------:|---------:|---------:|
| ICSI | en | 26.8 | 2.5 | 24.3 |
### ST Metrics
| Dataset | Source Language | Target Language | Bleu ⬆ | CHRF ⬆ |
|:----------|:------------------|:------------------|-------:|-------:|
| **MUSTC** | en | de | 19.57 | 48.47 |
| **ACL6060** | en | de | 23.75 | 53.86 |
| **ACL6060** | en | fr | 31.49 | 58.99 |
| **MUSTC** | en | fr | 25.21 | 52.24 |
| **MUSTC** | en | es | 23.94 | 51.8 |
| **MUSTC** | en | it | 16.86 | 45.14 |
## Framework versions
- Transformers 4.45.0
- Pytorch 2.3.1+cu124.post2
- Datasets 3.2.0
- Tokenizers 0.20.0
|
kapalbalap/blockassist-bc-peaceful_wary_owl_1755685601
|
kapalbalap
| 2025-08-20T10:27:30Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"peaceful wary owl",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:27:18Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- peaceful wary owl
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
coelacanthxyz/blockassist-bc-finicky_thriving_grouse_1755683923
|
coelacanthxyz
| 2025-08-20T10:26:45Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"finicky thriving grouse",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:26:39Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- finicky thriving grouse
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
xinnn32/blockassist-bc-meek_winged_caterpillar_1755685543
|
xinnn32
| 2025-08-20T10:26:15Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"meek winged caterpillar",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:26:06Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- meek winged caterpillar
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
rourkerhotmail1/blockassist-bc-stalking_scruffy_walrus_1755683797
|
rourkerhotmail1
| 2025-08-20T10:26:12Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"stalking scruffy walrus",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:26:09Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- stalking scruffy walrus
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
flemmingpetter2/blockassist-bc-hardy_subtle_snake_1755683747
|
flemmingpetter2
| 2025-08-20T10:24:50Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"hardy subtle snake",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:24:46Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- hardy subtle snake
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
aralper18/blockassist-bc-gilded_tangled_albatross_1755685407
|
aralper18
| 2025-08-20T10:24:22Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"gilded tangled albatross",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:24:12Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- gilded tangled albatross
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
VoilaRaj/81_v6rh8M
|
VoilaRaj
| 2025-08-20T10:24:04Z | 0 | 0 | null |
[
"safetensors",
"any-to-any",
"omega",
"omegalabs",
"bittensor",
"agi",
"license:mit",
"region:us"
] |
any-to-any
| 2025-08-20T10:20:04Z |
---
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).
|
Uppal-Farm-Girl-Viral-Video-Original-Link/Full.Uppal.Farm.Girl.Viral.Video.Original.Link.Official
|
Uppal-Farm-Girl-Viral-Video-Original-Link
| 2025-08-20T10:21:52Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-08-20T10:21:22Z |
<animated-image data-catalyst=""><a href="https://tinyurl.com/5xr5mb3e?leaked-videos/" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Foo" data-canonical-src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a>
|
joanna302/Qwen3-8B-Base_ar_alpaca_1_part_SFT_0.0002
|
joanna302
| 2025-08-20T10:21:51Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen3",
"text-generation",
"generated_from_trainer",
"sft",
"trl",
"unsloth",
"conversational",
"base_model:unsloth/Qwen3-8B-Base",
"base_model:finetune:unsloth/Qwen3-8B-Base",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-18T06:32:32Z |
---
base_model: unsloth/Qwen3-8B-Base
library_name: transformers
model_name: Qwen3-8B-Base_ar_alpaca_1_part_SFT_0.0002
tags:
- generated_from_trainer
- sft
- trl
- unsloth
licence: license
---
# Model Card for Qwen3-8B-Base_ar_alpaca_1_part_SFT_0.0002
This model is a fine-tuned version of [unsloth/Qwen3-8B-Base](https://huggingface.co/unsloth/Qwen3-8B-Base).
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="joanna302/Qwen3-8B-Base_ar_alpaca_1_part_SFT_0.0002", 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/prism-eval/Qwen3-8B-Base_ar_alpaca_1_part_SFT_0.0002/runs/3088gvuy)
This model was trained with SFT.
### Framework versions
- TRL: 0.21.0
- Transformers: 4.55.2
- Pytorch: 2.8.0
- Datasets: 3.6.0
- 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}}
}
```
|
xinnn32/blockassist-bc-meek_winged_caterpillar_1755685220
|
xinnn32
| 2025-08-20T10:20:54Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"meek winged caterpillar",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:20:42Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- meek winged caterpillar
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
afung/pika-towel-folding-ee_absolute-fisheye
|
afung
| 2025-08-20T10:20:48Z | 0 | 0 |
lerobot
|
[
"lerobot",
"safetensors",
"robotics",
"diffusion",
"dataset:afung/pika-towel-folding-ee_absolute-fisheye",
"arxiv:2303.04137",
"license:apache-2.0",
"region:us"
] |
robotics
| 2025-08-19T19:57:00Z |
---
datasets: afung/pika-towel-folding-ee_absolute-fisheye
library_name: lerobot
license: apache-2.0
model_name: diffusion
pipeline_tag: robotics
tags:
- robotics
- diffusion
- lerobot
---
# Model Card for diffusion
<!-- Provide a quick summary of what the model is/does. -->
[Diffusion Policy](https://huggingface.co/papers/2303.04137) treats visuomotor control as a generative diffusion process, producing smooth, multi-step action trajectories that excel at contact-rich manipulation.
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
|
tankh99/ppo_lunarlander_v3
|
tankh99
| 2025-08-20T10:20:30Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v3",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2025-08-20T07:37:48Z |
---
library_name: stable-baselines3
tags:
- LunarLander-v3
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v3
type: LunarLander-v3
metrics:
- type: mean_reward
value: 300.22 +/- 20.57
name: mean_reward
verified: false
---
# **PPO** Agent playing **LunarLander-v3**
This is a trained model of a **PPO** agent playing **LunarLander-v3**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
tgrhn/whisper-large-v3-turbo_finetuned-3
|
tgrhn
| 2025-08-20T10:18:43Z | 0 | 0 |
transformers
|
[
"transformers",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-08-20T10:18:41Z |
---
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]
|
b0bbyhill/blockassist-bc-grunting_iridescent_anaconda_1755685047
|
b0bbyhill
| 2025-08-20T10:18:22Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"grunting iridescent anaconda",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:18:11Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- grunting iridescent anaconda
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
calegpedia/blockassist-bc-stealthy_slimy_rooster_1755683472
|
calegpedia
| 2025-08-20T10:17:34Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"stealthy slimy rooster",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:17:29Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- stealthy slimy rooster
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
kapalbalap/blockassist-bc-peaceful_wary_owl_1755684996
|
kapalbalap
| 2025-08-20T10:17:25Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"peaceful wary owl",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:17:12Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- peaceful wary owl
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
qing223101/blockassist-bc-coiled_stinging_hummingbird_1755682426
|
qing223101
| 2025-08-20T10:15:10Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"coiled stinging hummingbird",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:14:53Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- coiled stinging hummingbird
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
luismirandacruz/dqn-SpaceInvadersNoFrameskip-v4
|
luismirandacruz
| 2025-08-20T10:14:55Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"SpaceInvadersNoFrameskip-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2025-08-20T09:22:08Z |
---
library_name: stable-baselines3
tags:
- SpaceInvadersNoFrameskip-v4
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: DQN
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: SpaceInvadersNoFrameskip-v4
type: SpaceInvadersNoFrameskip-v4
metrics:
- type: mean_reward
value: 29.00 +/- 64.30
name: mean_reward
verified: false
---
# **DQN** Agent playing **SpaceInvadersNoFrameskip-v4**
This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
The RL Zoo is a training framework for Stable Baselines3
reinforcement learning agents,
with hyperparameter optimization and pre-trained agents included.
## Usage (with SB3 RL Zoo)
RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
SB3: https://github.com/DLR-RM/stable-baselines3<br/>
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
SBX (SB3 + Jax): https://github.com/araffin/sbx
Install the RL Zoo (with SB3 and SB3-Contrib):
```bash
pip install rl_zoo3
```
```
# Download model and save it into the logs/ folder
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga luismirandacruz -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
```
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga luismirandacruz -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
## Training (with the RL Zoo)
```
python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga luismirandacruz
```
## Hyperparameters
```python
OrderedDict([('batch_size', 32),
('buffer_size', 100000),
('env_wrapper',
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
('exploration_final_eps', 0.01),
('exploration_fraction', 0.1),
('frame_stack', 4),
('gradient_steps', 1),
('learning_rate', 0.0001),
('learning_starts', 100000),
('n_timesteps', 1000000.0),
('optimize_memory_usage', False),
('policy', 'CnnPolicy'),
('target_update_interval', 1000),
('train_freq', 4),
('normalize', False)])
```
# Environment Arguments
```python
{'render_mode': 'rgb_array'}
```
|
kapalbalap/blockassist-bc-peaceful_wary_owl_1755684818
|
kapalbalap
| 2025-08-20T10:14:43Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"peaceful wary owl",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:14:28Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- peaceful wary owl
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
chainway9/blockassist-bc-untamed_quick_eel_1755683156
|
chainway9
| 2025-08-20T10:14:20Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"untamed quick eel",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:14:16Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- untamed quick eel
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
kapalbalap/blockassist-bc-peaceful_wary_owl_1755684660
|
kapalbalap
| 2025-08-20T10:11:46Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"peaceful wary owl",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:11:31Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- peaceful wary owl
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
yaelahnal/blockassist-bc-mute_clawed_crab_1755684395
|
yaelahnal
| 2025-08-20T10:11:41Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"mute clawed crab",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:07:27Z |
---
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).
|
jxchlee/koelectra-base-summarization1
|
jxchlee
| 2025-08-20T10:09:51Z | 8 | 0 |
transformers
|
[
"transformers",
"safetensors",
"electra",
"text-classification",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2025-08-13T06:26:41Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
This is temporary model while training to make Korean article Summarize model.
## 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]
|
aralper18/blockassist-bc-gilded_tangled_albatross_1755684538
|
aralper18
| 2025-08-20T10:09:42Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"gilded tangled albatross",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:09:33Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- gilded tangled albatross
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
b0bbyhill/blockassist-bc-grunting_iridescent_anaconda_1755684505
|
b0bbyhill
| 2025-08-20T10:09:20Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"grunting iridescent anaconda",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:09:10Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- grunting iridescent anaconda
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
ilkhom199/0ff66c0a-4efe-429b-a381-442f9d2ae15a
|
ilkhom199
| 2025-08-20T10:09:17Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"llama-factory",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-20T10:08:22Z |
---
library_name: transformers
tags:
- llama-factory
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
kapalbalap/blockassist-bc-peaceful_wary_owl_1755684478
|
kapalbalap
| 2025-08-20T10:09:06Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"peaceful wary owl",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:08:50Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- peaceful wary owl
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
valleriee/pii-model-6-recreate
|
valleriee
| 2025-08-20T10:08:13Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen3",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-20T10:04:43Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
mlx-community/DeepSeek-V3.1-Base-4bit
|
mlx-community
| 2025-08-20T10:07:20Z | 0 | 2 |
mlx
|
[
"mlx",
"safetensors",
"deepseek_v3",
"text-generation",
"conversational",
"custom_code",
"license:mit",
"4-bit",
"region:us"
] |
text-generation
| 2025-08-19T15:19:37Z |
---
license: mit
library_name: mlx
base_model: deepseek-ai/DeepSeek-v3.1-Base
tags:
- mlx
pipeline_tag: text-generation
---
# mlx-community/DeepSeek-V3.1-Base-4bit
This model [mlx-community/DeepSeek-V3.1-Base-4bit](https://huggingface.co/mlx-community/DeepSeek-V3.1-Base-4bit) was
converted to MLX format from [deepseek-ai/DeepSeek-v3.1-Base](https://huggingface.co/deepseek-ai/DeepSeek-v3.1-Base)
using mlx-lm version **0.26.3**.
## Use with mlx
```bash
pip install mlx-lm
```
```python
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/DeepSeek-v3.1-Base-4bit")
prompt = "hello"
if tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)
```
|
kapalbalap/blockassist-bc-peaceful_wary_owl_1755684308
|
kapalbalap
| 2025-08-20T10:06:10Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"peaceful wary owl",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:05:57Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- peaceful wary owl
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
mlx-community/DeepSeek-V3-0324-4bit
|
mlx-community
| 2025-08-20T10:05:58Z | 1,547 | 36 |
mlx
|
[
"mlx",
"safetensors",
"deepseek_v3",
"text-generation",
"conversational",
"custom_code",
"license:mit",
"4-bit",
"region:us"
] |
text-generation
| 2025-03-24T14:34:06Z |
---
license: mit
library_name: mlx
base_model: deepseek-ai/DeepSeek-v3-0324
tags:
- mlx
pipeline_tag: text-generation
---
# mlx-community/DeepSeek-v3-0324-4bit
This model [mlx-community/DeepSeek-v3-0324-4bit](https://huggingface.co/mlx-community/DeepSeek-v3-0324-4bit) was
converted to MLX format from [deepseek-ai/DeepSeek-v3-0324-4bit](https://huggingface.co/deepseek-ai/DeepSeek-v3-0324-4bit)
using mlx-lm version **0.26.3**.
## Use with mlx
```bash
pip install mlx-lm
```
```python
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/DeepSeek-v3-0324-4bit")
prompt = "hello"
if tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)
```
|
xinnn32/blockassist-bc-meek_winged_caterpillar_1755684300
|
xinnn32
| 2025-08-20T10:05:38Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"meek winged caterpillar",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:05:27Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- meek winged caterpillar
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
abhinayadutta/flan-t5-large-counter-speech-gen_FULL_TUNED
|
abhinayadutta
| 2025-08-20T10:05:00Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"t5",
"text2text-generation",
"arxiv:1910.09700",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | null | 2025-08-20T10:04:33Z |
---
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]
|
ustc-community/dfine-nano-coco
|
ustc-community
| 2025-08-20T10:04:40Z | 4,552 | 7 |
transformers
|
[
"transformers",
"safetensors",
"d_fine",
"object-detection",
"vision",
"en",
"dataset:coco",
"arxiv:2410.13842",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
object-detection
| 2025-03-28T12:48:09Z |
---
library_name: transformers
license: apache-2.0
language:
- en
pipeline_tag: object-detection
tags:
- object-detection
- vision
datasets:
- coco
---
## D-FINE
### **Overview**
The D-FINE model was proposed in [D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement](https://arxiv.org/abs/2410.13842) by
Yansong Peng, Hebei Li, Peixi Wu, Yueyi Zhang, Xiaoyan Sun, Feng Wu
This model was contributed by [VladOS95-cyber](https://github.com/VladOS95-cyber) with the help of [@qubvel-hf](https://huggingface.co/qubvel-hf)
This is the HF transformers implementation for D-FINE
_coco -> model trained on COCO
_obj365 -> model trained on Object365
_obj2coco -> model trained on Object365 and then finetuned on COCO
### **Performance**
D-FINE, a powerful real-time object detector that achieves outstanding localization precision by redefining the bounding box regression task in DETR models. D-FINE comprises two key components: Fine-grained Distribution Refinement (FDR) and Global Optimal Localization Self-Distillation (GO-LSD).
### **How to use**
```python
import torch
import requests
from PIL import Image
from transformers import DFineForObjectDetection, AutoImageProcessor
url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
image = Image.open(requests.get(url, stream=True).raw)
image_processor = AutoImageProcessor.from_pretrained("ustc-community/dfine-nano-coco")
model = DFineForObjectDetection.from_pretrained("ustc-community/dfine-nano-coco")
inputs = image_processor(images=image, return_tensors="pt")
with torch.no_grad():
outputs = model(**inputs)
results = image_processor.post_process_object_detection(outputs, target_sizes=torch.tensor([image.size[::-1]]), threshold=0.3)
for result in results:
for score, label_id, box in zip(result["scores"], result["labels"], result["boxes"]):
score, label = score.item(), label_id.item()
box = [round(i, 2) for i in box.tolist()]
print(f"{model.config.id2label[label]}: {score:.2f} {box}")
```
### **Training**
D-FINE is trained on COCO (Lin et al. [2014]) train2017 and validated on COCO val2017 dataset. We report the standard AP metrics (averaged over uniformly sampled IoU thresholds ranging from 0.50 − 0.95 with a step size of 0.05), and APval5000 commonly used in real scenarios.
### **Applications**
D-FINE is ideal for real-time object detection in diverse applications such as **autonomous driving**, **surveillance systems**, **robotics**, and **retail analytics**. Its enhanced flexibility and deployment-friendly design make it suitable for both edge devices and large-scale systems + ensures high accuracy and speed in dynamic, real-world environments.
|
katanyasekolah/blockassist-bc-silky_sprightly_cassowary_1755682636
|
katanyasekolah
| 2025-08-20T10:03:33Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"silky sprightly cassowary",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:03:29Z |
---
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).
|
Team-Atom/smolvla_record_pp_ryb_t_64_40000
|
Team-Atom
| 2025-08-20T10:03:11Z | 0 | 0 |
lerobot
|
[
"lerobot",
"safetensors",
"robotics",
"smolvla",
"dataset:Team-Atom/PiPl_RYB_test",
"arxiv:2506.01844",
"base_model:lerobot/smolvla_base",
"base_model:finetune:lerobot/smolvla_base",
"license:apache-2.0",
"region:us"
] |
robotics
| 2025-08-20T10:02:52Z |
---
base_model: lerobot/smolvla_base
datasets: Team-Atom/PiPl_RYB_test
library_name: lerobot
license: apache-2.0
model_name: smolvla
pipeline_tag: robotics
tags:
- robotics
- smolvla
- lerobot
---
# Model Card for smolvla
<!-- Provide a quick summary of what the model is/does. -->
[SmolVLA](https://huggingface.co/papers/2506.01844) is a compact, efficient vision-language-action model that achieves competitive performance at reduced computational costs and can be deployed on consumer-grade hardware.
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
|
liukevin666/blockassist-bc-yawning_striped_cassowary_1755684016
|
liukevin666
| 2025-08-20T10:02:59Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"yawning striped cassowary",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:01:27Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- yawning striped cassowary
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
fafsfa/Qwen3-0.6B-Gensyn-Swarm-tricky_fierce_bobcat
|
fafsfa
| 2025-08-20T10:02:58Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen3",
"text-generation",
"rl-swarm",
"genrl-swarm",
"grpo",
"gensyn",
"I am tricky_fierce_bobcat",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-20T07:07:40Z |
---
library_name: transformers
tags:
- rl-swarm
- genrl-swarm
- grpo
- gensyn
- I am tricky_fierce_bobcat
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
vwzyrraz7l/blockassist-bc-tall_hunting_vulture_1755682504
|
vwzyrraz7l
| 2025-08-20T10:02:33Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"tall hunting vulture",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T10:02:29Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- tall hunting vulture
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
yaelahnal/blockassist-bc-mute_clawed_crab_1755683944
|
yaelahnal
| 2025-08-20T10:00:13Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"mute clawed crab",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T09:59:55Z |
---
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).
|
prithivMLmods/Omega-Qwen2.5-Coder-3B
|
prithivMLmods
| 2025-08-20T09:59:17Z | 33 | 2 |
transformers
|
[
"transformers",
"safetensors",
"qwen2",
"text-generation",
"Thinking: Disabled",
"Forge",
"code",
"mot",
"stem",
"coder",
"trl",
"conversational",
"en",
"zh",
"dataset:prithivMLmods/Open-Omega-Forge-1M",
"base_model:Qwen/Qwen2.5-Coder-3B-Instruct",
"base_model:finetune:Qwen/Qwen2.5-Coder-3B-Instruct",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-07-15T12:55:24Z |
---
license: apache-2.0
tags:
- 'Thinking: Disabled'
- Forge
- code
- mot
- stem
- coder
- trl
datasets:
- prithivMLmods/Open-Omega-Forge-1M
language:
- en
- zh
base_model:
- Qwen/Qwen2.5-Coder-3B-Instruct
pipeline_tag: text-generation
library_name: transformers
---
# **Omega-Qwen2.5-Coder-3B**
> **Omega-Qwen2.5-Coder-3B** is a compact and high-efficiency code-focused model fine-tuned on **Qwen2.5-Coder-3B-Instruct**, using the symbolic-rich **Open-Omega-Forge-1M** dataset. Designed specifically for **hard-coded tasks** and deterministic computation, this model runs in a **"thinking-disabled"** mode—delivering precise, structured outputs with minimal hallucination, making it ideal for rigorous coding workflows and embedded logic applications.
> Thinking: Disabled
> \[!note]
> GGUF: [https://huggingface.co/prithivMLmods/Omega-Qwen2.5-Coder-3B-GGUF](https://huggingface.co/prithivMLmods/Omega-Qwen2.5-Coder-3B-GGUF)
## **Key Features**
1. **Purpose-Built for Hard Coding**
Specially tuned to perform precise, low-level code generation with **minimal reasoning overhead**. Ideal for edge-case algorithms, embedded scripting, and deterministic logic patterns.
2. **Optimized Qwen2.5 Foundation**
Built on **Qwen2.5-Coder-3B-Instruct**, benefiting from its robust token handling, instruction following, and multilingual code representation.
3. **Backed by Open-Omega-Forge-1M Dataset**
Trained on a curated mix of code, math, and logic problems focused on **symbolic clarity** and **STEM coherence**, drawn from sources like OpenCodeReasoning, MathX-5M, OpenMathReasoning, and more.
4. **Thinking Disabled Mode**
The model avoids overgeneralizing or injecting speculative reasoning. It executes tasks **as-is**—perfect for structured prompts, tight constraints, and automation pipelines.
5. **Structured Output Control**
Outputs in **JSON**, **YAML**, **Python**, **Markdown**, and **LaTeX**, tailored for script generation, data serialization, and scientific formatting.
6. **Efficient 3B Deployment**
Lightweight and scalable for **mid-tier GPUs**, **offline dev environments**, or **local inference systems**, while maintaining solid performance on symbolic tasks.
---
## **Quickstart with Transformers**
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "prithivMLmods/Omega-Qwen2.5-Coder-3B"
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)
prompt = "Write a Python function to compute factorial iteratively."
messages = [
{"role": "system", "content": "You are a deterministic code generator. No assumptions. No extra explanations."},
{"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=256
)
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]
print(response)
```
---
## **Intended Use**
* Embedded logic and deterministic function generation
* Script automation and toolchain integration
* Codegen under fixed constraints or symbolic inputs
* Lightweight STEM applications on edge devices or offline clusters
* Tools where **"no thinking" = better stability**
## **Limitations**
* Not suitable for high-level reasoning or open-ended thought processes
* General chat performance is minimal by design
* Lacks emotional intelligence or creative composition capability
* Assumes user provides **clear, explicit instructions** for best results
|
xinnn32/blockassist-bc-meek_winged_caterpillar_1755683861
|
xinnn32
| 2025-08-20T09:58:13Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"meek winged caterpillar",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T09:58:03Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- meek winged caterpillar
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
kapalbalap/blockassist-bc-peaceful_wary_owl_1755683745
|
kapalbalap
| 2025-08-20T09:56:50Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"peaceful wary owl",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T09:56:36Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- peaceful wary owl
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
cixzer/blockassist-bc-gregarious_long_cheetah_1755682773
|
cixzer
| 2025-08-20T09:56:19Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"gregarious long cheetah",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T09:56:11Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- gregarious long cheetah
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
koloni/blockassist-bc-deadly_graceful_stingray_1755682117
|
koloni
| 2025-08-20T09:56:09Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"deadly graceful stingray",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T09:56:05Z |
---
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).
|
coelacanthxyz/blockassist-bc-finicky_thriving_grouse_1755681902
|
coelacanthxyz
| 2025-08-20T09:52:46Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"finicky thriving grouse",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T09:52:39Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- finicky thriving grouse
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
loyal-misc/jenny
|
loyal-misc
| 2025-08-20T09:51:53Z | 0 | 0 |
diffusers
|
[
"diffusers",
"text-to-image",
"lora",
"template:diffusion-lora",
"base_model:LyliaEngine/Pony_Diffusion_V6_XL",
"base_model:adapter:LyliaEngine/Pony_Diffusion_V6_XL",
"license:unlicense",
"region:us"
] |
text-to-image
| 2025-08-20T07:25:25Z |
---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- output:
url: jenny-011.png
text: jenny,anthro,
base_model: LyliaEngine/Pony_Diffusion_V6_XL
instance_prompt: jenny, furry, female
license: unlicense
---
# jenny
<Gallery />
## Trigger words
You should use `jenny` to trigger the image generation.
You should use `furry` to trigger the image generation.
You should use `female` to trigger the image generation.
## Download model
[Download](/loyal-misc/jenny/tree/main) them in the Files & versions tab.
|
helmutsukocok/blockassist-bc-loud_scavenging_kangaroo_1755681711
|
helmutsukocok
| 2025-08-20T09:48:04Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"loud scavenging kangaroo",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T09:48:00Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- loud scavenging kangaroo
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
yaelahnal/blockassist-bc-mute_clawed_crab_1755683210
|
yaelahnal
| 2025-08-20T09:48:01Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"mute clawed crab",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T09:47:43Z |
---
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).
|
xinnn32/blockassist-bc-meek_winged_caterpillar_1755683216
|
xinnn32
| 2025-08-20T09:47:29Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"meek winged caterpillar",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T09:47:19Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- meek winged caterpillar
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
kelasbgd/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-quiet_endangered_ant
|
kelasbgd
| 2025-08-20T09:44:48Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen2",
"text-generation",
"rl-swarm",
"genrl-swarm",
"grpo",
"gensyn",
"I am quiet_endangered_ant",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-17T16:05:05Z |
---
library_name: transformers
tags:
- rl-swarm
- genrl-swarm
- grpo
- gensyn
- I am quiet_endangered_ant
---
# 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]
|
Ferdi3425/blockassist-bc-amphibious_deadly_otter_1755683004
|
Ferdi3425
| 2025-08-20T09:44:40Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"amphibious deadly otter",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T09:44:12Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- amphibious deadly otter
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
numind/NuMarkdown-8B-Thinking
|
numind
| 2025-08-20T09:42:17Z | 4,611 | 185 |
transformers
|
[
"transformers",
"safetensors",
"qwen2_5_vl",
"image-to-text",
"OCR",
"vision-language",
"VLM",
"Reasoning",
"document-to-markdown",
"qwen2.5",
"markdown",
"extraction",
"RAG",
"license:mit",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
image-to-text
| 2025-07-29T18:39:08Z |
---
license: mit
base_model: Qwen/Qwen2.5-VL-7B
tags:
- OCR
- vision-language
- VLM
- Reasoning
- document-to-markdown
- qwen2.5
- markdown
- extraction
- RAG
model_name: NuMarkdown-8B-Thinking
library_name: transformers
pipeline_tag: image-to-text
---
<p align="center">
<a href="https://nuextract.ai/">
<img src="numind.svg" width="400" height="400"/>
</a>
</p>
<p align="center">
🖥️ <a href="https://nuextract.ai/">API / Platform</a>   |   🗣️ <a href="https://discord.gg/3tsEtJNCDe">Discord</a>   |   🔗 <a href="https://github.com/numindai/NuMarkdown">GitHub</a>   |   🤗 <a href="https://huggingface.co/spaces/numind/NuMarkdown-8b-Thinking">Demo</a>
</p>
---
# Reasoning comes to OCR 🧠✨📄🤘
**NuMarkdown-8B-Thinking** is the first reasoning OCR VLM. It is specifically trained to convert documents into clean Markdown files, well suited for RAG applications. It generates thinking tokens to figure out the layout of the document before generating the Markdown file.
It is particularly good at understanding documents with weird layouts and complex tables. The number of thinking tokens can vary from 20% to 500% of the final answer, depending on the task difficulty.
**NuMarkdown-8B-Thinking** is a fine-tune of **Qwen 2.5-VL-7B** on synthetic Doc → Reasoning → Markdown examples, followed by an RL phase (GRPO) with a layout-centric reward.
Try it out in [the 🤗 space!](https://huggingface.co/spaces/numind/NuMarkdown-8b-Thinking)
## Results
**NuMarkdown-8B-Thinking** is outperforming generic non-reasoning models like GPT-4o and specialized OCR models like OCRFlux.
It is competitive against large reasoning closed-source models like Gemini 2.5.
### Arena ranking against popular alternatives (using trueskill-2 ranking system, with around 500 model-anonymized votes):
<p align="center">
| Rank | Model | μ | σ | μ − 3σ |
| ---- | --------------------------------------- | ----- | ---- | ------ |
| 🥇 1 | **gemini-flash-reasoning** | 26.75 | 0.80 | 24.35 |
| 🥈 2 | **NuMarkdown-reasoning** | 26.10 | 0.79 | 23.72 |
| 🥉 3 | **NuMarkdown-reasoning-w/o\_grpo** | 25.32 | 0.80 | 22.93 |
| 4 | **OCRFlux-3B** | 24.63 | 0.80 | 22.22 |
| 5 | **gpt-4o** | 24.48 | 0.80 | 22.08 |
| 6 | **gemini-flash-w/o\_reasoning** | 24.11 | 0.79 | 21.74 |
| 7 | **RolmoOCR** | 23.53 | 0.82 | 21.07 |
</p>
*We plan to realease a markdown arena, similar to llmArena, for complex document-to-markdown tasks to provide a tool to evaluate different solutions.*
### Win/Draw/Lose-rate against others models (image-only):
<p align="center">
<img src="bar plot.png" width="700"/>
</p>
## Training
1. **SFT**: Single epoch supervised fine-tuning on synthetic reasoning traces generated from public PDFs.
2. **RL (GRPO)**: RL phase using a layout-centric reward with difficult image examples.
## Example:
<p align="center">
<img src="ex1.png" width="500"/>
</p>
```
<think>
1. **Analyze the overall structure:** The document consists of two main sections, each containing a header, a set of bullet points, a title, a table, and a footer. The layout is consistent within each section but different between the two.
2. **Handle the first section header and bullet points:**
- The top left corner has "Generalitat de Catalunya Departament d'Educació Institut Gal·lecs". This is a consistent header and should be transcribed as a level 3 heading.
- The top right corner has "Curs 2021-22". This is a distinct header and should be transcribed as a level 3 heading.
- Below the header, there are four bullet points. These are standard list items. I will use Markdown's unordered list syntax (`- `).
3. **Process the first section's main content - Table 1:**
- **Identify table structure:** This is a complex table with a clear header row: "MATERIAL", "TÍTOL", "AUTOR", "EDITORIAL", "ISBN".
- **Determine columns:** There are 5 columns.
- **Handle merged cells:**
- "Llengua Catalana" spans two rows.
- "Llengua Castellana" spans three rows.
- "Anglès" spans two rows.
- **Populate table data:** Transcribe all text, including multi-line content within cells (e.g., "Babulinka Books\nEditorialCol·lecció: Pettes\nJoies per a Grans Lectors.\n2013").
- **Markdown table creation:** Use standard Markdown table syntax, ensuring correct alignment and handling of multi-line content within cells.
4. **Handle the first section's footer:**
- The footer contains "Codí: 04mp02", "Responsable: Coordinador Qualitat", "Versió: 5", "Full d'Informació a l'alumnat i famílies", "Aquest document pot quedar obsolet una vegada imprès", and "Pàgina 1 de 2". This is a simple text block at the bottom. I will transcribe it as a separate paragraph or list, maintaining the original layout if possible, but a simple paragraph is sufficient for a footer.
5. **Handle the second section header and bullet points:**
- The top left corner has "Generalitat de Catalunya Departament d'Educació Institut Gal·lecs". This is a consistent header and should be transcribed as a level 3 heading.
- The top right corner has "Curs 2021-22". This is a distinct header and should be transcribed as a level 3 heading.
- Below the header, there are no bullet points, but there is a table.
6. **Process the second section's main content - Table 2:**
- **Identify table structure:** This is a simpler table with a clear header row: "MATERIAL", "TÍTOL", "AUTOR", "EDITORIAL", "ISBN".
- **Determine columns:** There are 5 columns.
- **Populate table data:** Transcribe all text, including multi-line content within cells (e.g., "Projecte MOTIMATS-ONMAT (llicència digital) Tekman Books\nES GESTIONA A TRAVÉS DE L'AMPA AL SETEMBRE").
- **Markdown table creation:** Use standard Markdown table syntax.
7. **Handle the second section's footer:**
- The footer contains "Codí: 04mp02", "Responsable: Coordinador Qualitat", "Versió: 5", "Full d'Informació a l'alumnat i famílies", "Aquest document pot quedar obsolet una vegada imprès", and "Pàgina 2 de 2". This is a simple text block at the bottom. I will transcribe it as a separate paragraph or list, maintaining the original layout if possible, but a simple paragraph is sufficient for a footer.
8. **Final review:** Check for any missed text, incorrect formatting, or issues with table alignment. Ensure all original content is present and accurately represented in GitHub-Flavored Markdown. The image placeholders are not needed as there are no images in the document.
</think>
<answer>
### Generalitat de Catalunya
### Departament d'Educació
### Institut Gal·lecs
### Curs 2021-22
- Els llibres de color blau indiquen que es manté respecte al curs anterior.
- Els llibres de color groc indiquen que es tracta d'un canvi per a aquest curs.
- Els llibres de color vermell indiquen que no s'han de comprar perquè van a càrrec del centre.
- Matèries sense llibre: Dossiers, llicències i el Kit de tecnologia s'hauran de pagar i de recollir a través de l'AMPA a partir de setembre.
# 1 ESO
| MATERIAL | TÍTOL | AUTOR | EDITORIAL | ISBN |
|---|---|---|---|---|
| Llengua Catalana | Punt Volat | | Castellnou (Didacta +) | 9788417803124 |
| | Duna, Diari d'un estiu. | Muriel Villanueva | Babulinka Books<br>EditorialCol·lecció: Pettes<br>Joies per a Grans Lectors.<br>2013 | 9788494159077 |
| | El nen que xatejava amb Jack Sparrow. | Francesc Puigpelat | Bromera<br>Col·lecció: L'Elefant. 2015 | 9788490264072 |
| Llengua Castellana | Proyecto Asterisco | | Castellnou (Didacta +) | 9788417803186 |
| | Manzanas rojas | Luis Matilla | Ed. Anaya | 978846673989 |
| | Fàbulas de Esopo | Jerry Pinkney | Vicens Vives | 978843671648 |
| Anglès | Think Ahead ESO 1. Student's book.<br>Think Ahead ESO 1. Workbook (cat). | | Burlington Books<br>Burlington Books | 9788925300662<br>9789925300686 |
Codí: 04mp02
Responsable: Coordinador Qualitat
Versió: 5
Full d'Informació a l'alumnat i famílies
Aquest document pot quedar obsolet una vegada imprès
Pàgina 1 de 2
### Generalitat de Catalunya
### Departament d'Educació
### Institut Gal·lecs
### Curs 2021-22
| MATERIAL | TÍTOL | AUTOR | EDITORIAL | ISBN |
|---|---|---|---|---|
| FRANCÈS | Nouvelle Génération A1-A2 | | Santillana | 9788490494745 |
| CIÈNCIES EXPERIMENTALS | Science Bits<br>ES GESTIONA A TRAVÉS DE L'AMPA AL SETEMBRE | | | 9788412213485 (llicència digital) |
| MATEMÀTIQUES | Projecte MOTIMATS-ONMAT (llicència digital) Tekman Books<br>ES GESTIONA A TRAVÉS DE L'AMPA AL SETEMBRE | | | |
| TECNOLOGIA | Tecnologia 1 ESO | TEIDE | | 9788430783175 |
| VISUAL I PLÀSTICA | SENSE LLIBRE-KIT DE MATERIAL | | | |
| CIÈNCIES SOCIALS | SENSE LLIBRE-dossier | | | |
Codí: 04mp02
Responsable: Coordinador Qualitat
Versió: 5
Full d'Informació a l'alumnat i famílies
Aquest document pot quedar obsolet una vegada imprès
Pàgina 2 de 2
</answer>
```
## Quick start:
## vLLM:
```
vllm serve numind/NuMarkdown-8B-Thinking --trust_remote_code --limit-mm-per-prompt image=1
```
```python
from openai import OpenAI
import base64
openai_api_key = "EMPTY"
openai_api_base = "http://localhost:8000/v1"
client = OpenAI(
api_key=openai_api_key,
base_url=openai_api_base,
)
def encode_image(image_path):
"""
Encode the image file to base64 string
"""
with open(image_path, "rb") as image_file:
return base64.b64encode(image_file.read()).decode('utf-8')
base64_image = encode_image("image.png")
data_url = f"data:image/jpeg;base64,{base64_image}"
chat_response = client.chat.completions.create(
model="numind/NuMarkdown-8B-Thinking",
temperature=0.7,
messages=[
{
"role": "user",
"content": [
{
"type": "image_url",
"image_url": {"url": data_url},
"min_pixels": 100 * 28 * 28,
"max_pixels": 5000 * 28 * 28,
},
],
},
]
)
result = chat_response.choices[0].message.content
reasoning = result.split("<think>")[1].split("</think>")[0]
answer = result.split("<answer>")[1].split("</answer>")[0]
print(answer)
```
## 🤗 Transformers:
```python
import torch
from PIL import Image
from transformers import AutoProcessor, Qwen2_5_VLForConditionalGeneration
model_id = "numind/NuMarkdown-8B-reasoning"
processor = AutoProcessor.from_pretrained(
model_id,
trust_remote_code=True,
min_pixels=100*28*28, max_pixels=5000*28*28
)
model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
attn_implementation="flash_attention_2",
device_map="auto",
trust_remote_code=True,
)
img = Image.open("image.png").convert("RGB")
messages = [{
"role": "user",
"content": [
{"type": "image"},
],
}]
prompt = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
model_input = processor(text=prompt, images=[img], return_tensors="pt").to(model.device)
with torch.no_grad():
model_output = model.generate(**model_input, temperature = 0.7, max_new_tokens=5000)
result = processor.decode(model_output[0])
reasoning = result.split("<think>")[1].split("</think>")[0]
answer = result.split("<answer>")[1].split("</answer>")[0]
print(answer)
```
|
xinnn32/blockassist-bc-meek_winged_caterpillar_1755682886
|
xinnn32
| 2025-08-20T09:41:59Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"meek winged caterpillar",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-20T09:41:49Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- meek winged caterpillar
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
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.