modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-08-18 12:29:09
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 509
values | tags
listlengths 1
4.05k
| pipeline_tag
stringclasses 55
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-08-18 12:27:30
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
Muapi/body.-flux-fix
|
Muapi
| 2025-08-18T11:28:58Z | 0 | 0 | null |
[
"lora",
"stable-diffusion",
"flux.1-d",
"license:openrail++",
"region:us"
] | null | 2025-08-18T11:28:43Z |
---
license: openrail++
tags:
- lora
- stable-diffusion
- flux.1-d
model_type: LoRA
---
# Body. FLUX FIX
**Base model**: Flux.1 D
**Trained words**: woman, hips
## 🧠 Usage (Python)
🔑 **Get your MUAPI key** from [muapi.ai/access-keys](https://muapi.ai/access-keys)
```python
import requests, os
url = "https://api.muapi.ai/api/v1/flux_dev_lora_image"
headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")}
payload = {
"prompt": "masterpiece, best quality, 1girl, looking at viewer",
"model_id": [{"model": "civitai:773439@865067", "weight": 1.0}],
"width": 1024,
"height": 1024,
"num_images": 1
}
print(requests.post(url, headers=headers, json=payload).json())
```
|
lwj786/Qwen3-0.6B-Gensyn-Swarm-polished_territorial_crane
|
lwj786
| 2025-08-18T10:26:56Z | 23 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen3",
"text-generation",
"rl-swarm",
"genrl-swarm",
"grpo",
"gensyn",
"I am polished_territorial_crane",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-26T08:44:35Z |
---
library_name: transformers
tags:
- rl-swarm
- genrl-swarm
- grpo
- gensyn
- I am polished_territorial_crane
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
Muapi/geometric-woman
|
Muapi
| 2025-08-18T09:17:44Z | 0 | 0 | null |
[
"lora",
"stable-diffusion",
"flux.1-d",
"license:openrail++",
"region:us"
] | null | 2025-08-18T09:17:33Z |
---
license: openrail++
tags:
- lora
- stable-diffusion
- flux.1-d
model_type: LoRA
---
# Geometric Woman
**Base model**: Flux.1 D
**Trained words**:
## 🧠 Usage (Python)
🔑 **Get your MUAPI key** from [muapi.ai/access-keys](https://muapi.ai/access-keys)
```python
import requests, os
url = "https://api.muapi.ai/api/v1/flux_dev_lora_image"
headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")}
payload = {
"prompt": "masterpiece, best quality, 1girl, looking at viewer",
"model_id": [{"model": "civitai:103528@743778", "weight": 1.0}],
"width": 1024,
"height": 1024,
"num_images": 1
}
print(requests.post(url, headers=headers, json=payload).json())
```
|
WeiJay/finetuned_model
|
WeiJay
| 2025-08-18T08:28:06Z | 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 | 2025-08-18T08:28:01Z |
---
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:** WeiJay
- **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)
|
helmutsukocok/blockassist-bc-loud_scavenging_kangaroo_1755502937
|
helmutsukocok
| 2025-08-18T08:08:52Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"loud scavenging kangaroo",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-18T08:08:49Z |
---
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).
|
unitova/blockassist-bc-zealous_sneaky_raven_1755502175
|
unitova
| 2025-08-18T07:54:53Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"zealous sneaky raven",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-18T07:54:50Z |
---
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).
|
fizzarif7/llama2_pklaw_gpt
|
fizzarif7
| 2025-08-18T07:27:04Z | 15 | 0 |
peft
|
[
"peft",
"safetensors",
"base_model:meta-llama/Llama-2-7b-chat-hf",
"base_model:adapter:meta-llama/Llama-2-7b-chat-hf",
"region:us"
] | null | 2025-08-13T10:15:22Z |
---
base_model: meta-llama/Llama-2-7b-chat-hf
library_name: peft
---
# Model Card for LLaMA-2-7B-Chat Fine-tuned on Pakistani Legal Q&A Dataset (QLoRA)
## Model Details
### Model Description
This repository contains **LoRA adapter weights** for **LLaMA-2-7B-Chat**, fine-tuned on a **Pakistani legal Q&A dataset** using **QLoRA (4-bit quantization)**.
The model is intended for **legal information retrieval and educational purposes only**.
⚠️ It should **not** be used as a substitute for professional legal advice.
---
## 🚀 Quick Start (Google Colab)
You need a **GPU runtime** (preferably **T4** or higher).
In Colab, go to:
`Runtime` ➝ `Change runtime type` ➝ Select **T4\GPU**.
- **Base model**: meta-llama/Llama-2-7b-chat-hf
- **Fine-tuning method**: QLoRA (4-bit quantization)
- **Framework**: Hugging Face Transformers + PEFT
- **Primary purpose**: Legal information and education (non-advisory)
### Model Sources
- **Repository:** [[https://huggingface.co/fizzarif7/llama2_pklaw_gpt](https://huggingface.co/fizzarif7/llama2_pklaw_gpt/tree/main)](https://huggingface.co/fizzarif7/llama2_pklaw_gpt/tree/main)
- **Dataset source:** Official Pakistani government websites (public domain legal acts & regulations)
- **Demo:**
---
## Uses
### Direct Use
- Legal **information retrieval**
- **Educational** purposes: Understanding Pakistani laws, procedures, and definitions
### Downstream Use
- Integration into legal research assistants
- Support in law-related educational tools
### Out-of-Scope Use
- Real legal decision-making
- Providing confidential legal advice
- Any **non-Pakistani law** domain queries
---
## Dataset
- **Source**: Collected from **official Pakistani government websites** hosting public legal documents, acts, and regulations.
- **Format**: Converted from PDF to structured **Q&A format** (`Dataset.csv`).
- **Contents**: Includes questions about legal definitions, processes, and roles as per Pakistani law.
- **Size**: 1941 rows
- **Language**: English
## Bias, Risks, and Limitations
- The model’s knowledge is **limited** to the dataset scope and law versions at the time of collection
- May **hallucinate** answers for out-of-domain or ambiguous queries
- Not updated for recent law amendments unless retrained
### Recommendations
Users must **verify** answers against official legal sources before acting upon them.
---
## License
- Base model: LLaMA-2 license by Meta
- Dataset: Public government documents (open to public use, verify each source)
## Ethical Considerations & Risks
- **Do not** use for real legal decision-making.
- May misinterpret complex or ambiguous legal terms.
- Should not replace a qualified lawyer or legal expert.
### Evaluation
**Example Usage**
- **Q:** What is the significance of Article 181 of the Limitation Act, 1908, in relation to applications filed under various statutes, as interpreted by the High Court in this case?
- **A:** Article 181 of the Limitation Act, 1908, is significant because it provides a general rule for the computation of time for filing applications, including those under various statutes. The High Court's interpretation of this article, as seen in the case of "Mst. Naseem Bibi v. Mst. Hameeda Bibi", is that the limitation period begins to run on the day the application is made, rather than on the date of the event or occurrence that triggered the application. This interpretation ensures that applications are filed within the prescribed time frame, and it highlights the importance of considering the specific provision and context of each statute when determining the applicable limitation period.
### Citation
@misc{fizza2025paklawqlora,
- author = {Fizza Arif},
- title = {LLaMA-2-7B-Chat fine-tuned on Pakistani Legal Q\&A Dataset (QLoRA)},
- year = {2025},
- publisher = {Hugging Face},
}
## How to Get Started with the Model
This is the fine-tuned model on HF only contains the LoRA adapter weights.
When you try to from_pretrained(...), 🤗 Transformers automatically tries to fetch the base model: meta-llama/Llama-2-7b-chat-hf.
That base repo is gated (you need to request access on Hugging Face) and also you must be logged in with your HF token.
```python
from huggingface_hub import login
login(token="YourHFTokenHere")
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
from peft import PeftModel
import torch
base_model = "meta-llama/Llama-2-7b-chat-hf" # gated model
adapter_model = "fizzarif7/llama2_pklaw_gpt" # your LoRA fine-tuned repo
# Load tokenizer ---
tokenizer = AutoTokenizer.from_pretrained(base_model)
# quantization to save VRAM ---
bnb_config = BitsAndBytesConfig(load_in_4bit=True, bnb_4bit_compute_dtype=torch.float16)
# Load base model ---
model = AutoModelForCausalLM.from_pretrained(
base_model,
quantization_config=bnb_config,
device_map="auto"
)
# --- Load LoRA adapter ---
model = PeftModel.from_pretrained(model, adapter_model)
# Examplpe Usage
prompt = "What is the importance of the general manager under Pakistani corporate law?"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(
**inputs,
max_new_tokens=200,
temperature=0.7,
top_p=0.9
)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
roeker/blockassist-bc-quick_wiry_owl_1755501625
|
roeker
| 2025-08-18T07:21:41Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"quick wiry owl",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-18T07:21:10Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- quick wiry owl
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
Mincroft/Qwen2.5-7B-Instruct-3D
|
Mincroft
| 2025-08-18T07:15:47Z | 0 | 0 | null |
[
"license:apache-2.0",
"region:us"
] | null | 2025-08-18T02:45:16Z |
---
license: apache-2.0
---
|
sii-research/InnoSpark-HPC-RM-32B
|
sii-research
| 2025-08-18T07:07:12Z | 22 | 1 | null |
[
"safetensors",
"qwen2",
"arxiv:2507.20335",
"arxiv:2507.22947",
"license:mit",
"region:us"
] | null | 2025-07-20T07:39:23Z |
---
license: mit
---
<div align="center">
# 🌟 InnoSpark 🌟
[](https://innospark.aiecnu.cn/innospark/)
[](https://huggingface.co/sii-research)
[](https://github.com/Inno-Spark/elmes)
<div style="background: linear-gradient(135deg, #667eea 0%, #764ba2 100%); padding: 2px; border-radius: 10px; margin: 20px 0;">
<div style="background: white; padding: 20px; border-radius: 8px;">
<h3>🚀 Advanced Educational Large Language Model</h3>
</div>
</div>
**Language / 语言**: English | [中文](README_zh.md)
</div>
---
## 📖 Project Introduction
**InnoSpark** is an advanced educational large language model independently developed by Shanghai Innovation Institute and East China Normal University. It aims to explore the deep application of artificial intelligence technology in the field of education. Based on the domestic Qwen large language model with secondary pre-training, combined with subdomain fine-tuning and reinforcement learning for educational scenarios, we have launched InnoSpark-1.0.
## 🔗 Related Resources
### 📱 Main Products
- **Homepage**: [InnoSpark Official](https://innospark.aiecnu.cn/innospark/)
- **RM Model**: [InnoSpark-HPC-RM-32B](https://huggingface.co/sii-research/InnoSpark-HPC-RM-32B)
- **Educational Evaluation System**: [ELMES](https://github.com/Inno-Spark/elmes)
- **Data Cleaning Pipeline**: [COCLP](https://github.com/sii-research/COCLP.git)
### 🤖 Model Series
| Model Version | Parameters | Link |
|---------------|------------|------|
| **InnoSpark-min** | 0.5B | [🔗 Download](https://huggingface.co/sii-research/InnoSpark-0.5B-0717) |
| **InnoSpark-turbo** | 7B | [🔗 Download](https://huggingface.co/sii-research/InnoSpark-7B-0715) |
| **InnoSpark-plus** | 72B | [🔗 Standard](https://huggingface.co/sii-research/InnoSpark-72B-0710) / [🔗 Reasoning](https://huggingface.co/sii-research/InnoSpark-R-72B-0701) |
### 📊 Datasets
- **Model Scoring Dataset**: [HPC-LLM-8k](https://huggingface.co/datasets/ECNU-InnoSpark/HPC-LLM-8k)
- **Human Scoring Dataset**: [HPC-Human-8k](https://huggingface.co/datasets/ECNU-InnoSpark/HPC-Human-8k)
## 🚀 Quickstart
Here provides a code snippet with `apply_chat_template` to show you how to load the tokenizer and model and how to generate contents.
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto
model = AutoModelForCausalLM.from_pretrained(
"sii-research/InnoSpark-72B-0710",
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("sii-research/InnoSpark-72B-0710")
prompt = "Introduce yourself in detail."
messages = [
{"role": "system", "content": "You are InnoSpark（启创）, created by Shanghai Innovation Institute （上海创智学院） and East China Normal University(华东师范大学). You are a helpful assistant."},
{"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(device)
generated_ids = model.generate(
model_inputs.input_ids,
max_new_tokens=512
)
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
```
### VLLM
We recommend deploying our model using 4 A100 GPUs. You can run the vllm server-side with the following code in terminal:
```python
python -m vllm.entrypoints.openai.api_server --served-model-name InnoSpark --model path/to/InnoSpark --gpu-memory-utilization 0.98 --tensor-parallel-size 4 --port 6000
```
Then, you can use the following code to deploy client-side:
```python
import requests
import json
def Innospark_stream(inputs,history):
url = 'http://loaclhost:6000/v1/chat/completions'
history+=[{"role": "user", "content": inputs},]
headers = {"User-Agent": "vLLM Client"}
pload = {
"model": "InnoSpark",
"stream": True,
"messages": history
}
response = requests.post(url,
headers=headers,
json=pload,
stream=True)
for chunk in response.iter_lines(chunk_size=1,
decode_unicode=False,
delimiter=b"\n"):
if chunk:
string_data = chunk.decode("utf-8")
try:
json_data = json.loads(string_data[6:])
delta_content = json_data["choices"][0]["delta"]["content"]
assistant_reply+=delta_content
yield delta_content
except KeyError as e:
delta_content = json_data["choices"][0]["delta"]["role"]
except json.JSONDecodeError as e:
history+=[{
"role": "assistant",
"content": assistant_reply,
"tool_calls": []
},]
delta_content='[DONE]'
assert '[DONE]'==chunk.decode("utf-8")[6:]
inputs='hi'
history=[]
for response_text in Innospark_stream(inputs,history):
print(response_text,end='')
```
## 🌟 Core Features
### 🎯 Open Source Product Matrix
<div align="left">
**1. 📚 InnoSpark Model Series**
- 4 models with different parameter scales: min(0.5B), turbo(7B), plus(72B) and their corresponding inference model R versions
**2. 🔍 ELMES Evaluation System**
- Education Language Model Evaluation System
- Automated evaluation system for educational tasks
- Helps continuously optimize large model capabilities in teaching scenarios
**3. 🛠️ COCLP Data Cleaning Pipeline**
- Corpus Cleansing Pipeline
- Visual node-based framework based on ComfyUI
- Supports OCR, audio/video transcription, format conversion, PII removal, text filtering, and other functions
- **GitHub**: [COCLP](https://github.com/sii-research/COCLP.git)
**4. ⭐ HPC-RM Reward Model**
- Helpful, Personalization, and Creativity Reward Model
- Provides scoring in three educational dimensions: helpfulness, personalization, and creativity
- Includes corresponding model scoring and human scoring datasets
</div>
## 📚 Citation
If you find our work useful, please cite our papers:
```bibtex
@misc{song2025cultivatinghelpfulpersonalizedcreative,
title={Cultivating Helpful, Personalized, and Creative AI Tutors: A Framework for Pedagogical Alignment using Reinforcement Learning},
author={Siyu Song and Wentao Liu and Ye Lu and Ruohua Zhang and Tao Liu and Jinze Lv and Xinyun Wang and Aimin Zhou and Fei Tan and Bo Jiang and Hao Hao},
year={2025},
eprint={2507.20335},
archivePrefix={arXiv},
primaryClass={cs.LG},
url={https://arxiv.org/abs/2507.20335},
}
```
```bibtex
@misc{wei2025elmesautomatedframeworkevaluating,
title={ELMES: An Automated Framework for Evaluating Large Language Models in Educational Scenarios},
author={Shou'ang Wei and Xinyun Wang and Shuzhen Bi and Jian Chen and Ruijia Li and Bo Jiang and Xin Lin and Min Zhang and Yu Song and BingDong Li and Aimin Zhou and Hao Hao},
year={2025},
eprint={2507.22947},
archivePrefix={arXiv},
primaryClass={cs.CY},
url={https://arxiv.org/abs/2507.22947},
}
```
## 📈 Performance Results
We achieved optimal performance in 4 key educational scenarios:
### 🏆 Evaluation Results
| Scenario | Performance |
|----------|-------------|
| 📝 Knowledge Explanation |  |
| 🧭 Guided Problem Solving |  |
| 📚 Interdisciplinary Lesson Plans |  |
| 🎭 Contextual Question Generation |  |
### 📊 Detailed Evaluation Tables
| Scenario | Evaluation Table |
|----------|------------------|
| 📝 Knowledge Explanation |  |
| 🧭 Guided Problem Solving |  |
| 📚 Interdisciplinary Lesson Plans |  |
| 🎭 Contextual Question Generation |  |
### 🎨 Application Examples
| Scenario | Demo |
|----------|------|
| 📖 Knowledge Explanation |  |
| 🎯 Guided Problem Solving |  |
| 🌟 Interdisciplinary Lesson Plans |  |
| 🎪 Contextual Question Generation |  |
## 🏛️ Technical Support
This project is jointly developed by East China Normal University and Shanghai Innovation Institute. The reward model was trained using the SiiRL training framework provided by Shanghai Innovation Institute.
## 📄 License
Please refer to the relevant model pages for specific license information.
---
<div align="center">
## 🤝 Contact & Collaboration
**East China Normal University**
[](https://innospark.aiecnu.cn/innospark/)
[](mailto:[email protected])
---
<sub>🚀 Empowering Education with AI</sub>
</div>
|
chainway9/blockassist-bc-untamed_quick_eel_1755498037
|
chainway9
| 2025-08-18T06:48:05Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"untamed quick eel",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-18T06:48:02Z |
---
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).
|
master-of-hardcore/dr119s-kc
|
master-of-hardcore
| 2025-08-18T06:43:48Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-08-18T04:23:07Z |
# Container Template for SoundsRight Subnet Miners
This repository contains a contanierized version of [SGMSE+](https://huggingface.co/sp-uhh/speech-enhancement-sgmse) and serves as a tutorial for miners to format their models on [Bittensor's](https://bittensor.com/) [SoundsRight Subnet](https://github.com/synapsec-ai/SoundsRightSubnet). The branches `DENOISING_16000HZ` and `DEREVERBERATION_16000HZ` contain SGMSE fitted with the approrpriate checkpoints for denoising and dereverberation tasks at 16kHz, respectively.
This container has only been tested with **Ubuntu 24.04** and **CUDA 12.6**. It may run on other configurations, but it is not guaranteed.
To run the container, first configure NVIDIA Container Toolkit and generate a CDI specification. Follow the instructions to download the [NVIDIA Container Toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html) with Apt.
Next, follow the instructions for [generating a CDI specification](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/cdi-support.html).
Verify that the CDI specification was done correctly with:
```
$ nvidia-ctk cdi list
```
You should see this in your output:
```
nvidia.com/gpu=all
nvidia.com/gpu=0
```
If you are running podman as root, run the following command to start the container:
Run the container with:
```
podman build -t modelapi . && podman run -d --device nvidia.com/gpu=all --user root --name modelapi -p 6500:6500 modelapi
```
Access logs with:
```
podman logs -f modelapi
```
If you are running the container rootless, there are a few more changes to make:
First, modify `/etc/nvidia-container-runtime/config.toml` and set the following parameters:
```
[nvidia-container-cli]
no-cgroups = true
[nvidia-container-runtime]
debug = "/tmp/nvidia-container-runtime.log"
```
You can also run the following command to achieve the same result:
```
$ sudo nvidia-ctk config --set nvidia-container-cli.no-cgroups --in-place
```
Run the container with:
```
podman build -t modelapi . && podman run -d --device nvidia.com/gpu=all --volume /usr/local/cuda-12.6:/usr/local/cuda-12.6 --user 10002:10002 --name modelapi -p 6500:6500 modelapi
```
Access logs with:
```
podman logs -f modelapi
```
Running the container will spin up an API with the following endpoints:
1. `/status/` : Communicates API status
2. `/prepare/` : Download model checkpoint and initialize model
3. `/upload-audio/` : Upload audio files, save to noisy audio directory
4. `/enhance/` : Initialize model, enhance audio files, save to enhanced audio directory
5. `/download-enhanced/` : Download enhanced audio files
By default the API will use host `0.0.0.0` and port `6500`.
### References
1. **Welker, Simon; Richter, Julius; Gerkmann, Timo**
*Speech Enhancement with Score-Based Generative Models in the Complex STFT Domain*.
Proceedings of *Interspeech 2022*, 2022, pp. 2928–2932.
[DOI: 10.21437/Interspeech.2022-10653](https://doi.org/10.21437/Interspeech.2022-10653)
2. **Richter, Julius; Welker, Simon; Lemercier, Jean-Marie; Lay, Bunlong; Gerkmann, Timo**
*Speech Enhancement and Dereverberation with Diffusion-based Generative Models*.
*IEEE/ACM Transactions on Audio, Speech, and Language Processing*, Vol. 31, 2023, pp. 2351–2364.
[DOI: 10.1109/TASLP.2023.3285241](https://doi.org/10.1109/TASLP.2023.3285241)
3. **Richter, Julius; Wu, Yi-Chiao; Krenn, Steven; Welker, Simon; Lay, Bunlong; Watanabe, Shinjii; Richard, Alexander; Gerkmann, Timo**
*EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberation*.
Proceedings of *ISCA Interspeech*, 2024, pp. 4873–4877.
|
dolfsai/Qwen3-Reranker-4B-seq-cls-vllm-W4A16_ASYM
|
dolfsai
| 2025-08-18T06:32:39Z | 0 | 0 | null |
[
"safetensors",
"qwen3",
"text-ranking",
"es",
"en",
"base_model:Qwen/Qwen3-Reranker-4B",
"base_model:quantized:Qwen/Qwen3-Reranker-4B",
"license:apache-2.0",
"compressed-tensors",
"region:us"
] |
text-ranking
| 2025-08-18T06:18:34Z |
---
license: apache-2.0
language:
- es
- en
base_model:
- Qwen/Qwen3-Reranker-4B
pipeline_tag: text-ranking
---
# prudant/Qwen3-Reranker-4B-seq-cls-vllm-fixed-W4A16_ASYM
This is a compressed version of danielchalef/Qwen3-Reranker-4B-seq-cls-vllm-fixed using llm-compressor with the following scheme: W4A16_ASYM
## Serving
``python3 -m vllm.entrypoints.openai.api_server --model 'dolfsai/Qwen3-Reranker-4B-seq-cls-vllm-W4A16_ASYM' --task classify``
**Important**: You MUST read the following guide for correct usage of this model here [Guide](https://github.com/vllm-project/vllm/pull/19260)
## Model Details
- **Original Model**: danielchalef/Qwen3-Reranker-4B-seq-cls-vllm-fixed
- **Quantization Method**: AWQ
- **Compression Libraries**: [llm-compressor](https://github.com/vllm-project/llm-compressor)
- **Calibration Dataset**: ultrachat_200k (512 samples)
- **Optimized For**: Inference with vLLM
- **License**: same as original model
|
peterjaq/navsim_navhard_test
|
peterjaq
| 2025-08-18T06:16:17Z | 0 | 0 | null |
[
"license:apache-2.0",
"region:us"
] | null | 2025-08-18T06:16:17Z |
---
license: apache-2.0
---
|
NexVeridian/Qwen3-30B-A3B-Thinking-2507-3bit
|
NexVeridian
| 2025-08-18T06:14:46Z | 67 | 0 |
mlx
|
[
"mlx",
"safetensors",
"qwen3_moe",
"text-generation",
"conversational",
"base_model:Qwen/Qwen3-30B-A3B-Thinking-2507",
"base_model:quantized:Qwen/Qwen3-30B-A3B-Thinking-2507",
"license:apache-2.0",
"3-bit",
"region:us"
] |
text-generation
| 2025-07-30T19:37:55Z |
---
library_name: mlx
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen3-30B-A3B-Thinking-2507/blob/main/LICENSE
pipeline_tag: text-generation
tags:
- mlx
base_model: Qwen/Qwen3-30B-A3B-Thinking-2507
---
# NexVeridian/Qwen3-30B-A3B-Thinking-2507-3bit
This model [NexVeridian/Qwen3-30B-A3B-Thinking-2507-3bit](https://huggingface.co/NexVeridian/Qwen3-30B-A3B-Thinking-2507-3bit) was
converted to MLX format from [Qwen/Qwen3-30B-A3B-Thinking-2507](https://huggingface.co/Qwen/Qwen3-30B-A3B-Thinking-2507)
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("NexVeridian/Qwen3-30B-A3B-Thinking-2507-3bit")
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)
```
|
taruiayano/blockassist-bc-scavenging_chattering_okapi_1755496945
|
taruiayano
| 2025-08-18T06:04:11Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"scavenging chattering okapi",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-18T06:03:59Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- scavenging chattering okapi
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
SSUNFACE/bert_kor_sazaboyes_nsmc8
|
SSUNFACE
| 2025-08-18T05:50:17Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"bert",
"text-classification",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2025-08-18T05:49:52Z |
---
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]
|
vuitton/LouisVuitton_model3
|
vuitton
| 2025-08-18T05:47:05Z | 0 | 0 | null |
[
"safetensors",
"any-to-any",
"omega",
"omegalabs",
"bittensor",
"agi",
"license:mit",
"region:us"
] |
any-to-any
| 2025-08-17T15:16:32Z |
---
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).
|
katanyasekolah/blockassist-bc-silky_sprightly_cassowary_1755493897
|
katanyasekolah
| 2025-08-18T05:39:50Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"silky sprightly cassowary",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-18T05:39:47Z |
---
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).
|
helmutsukocok/blockassist-bc-loud_scavenging_kangaroo_1755493667
|
helmutsukocok
| 2025-08-18T05:35:51Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"loud scavenging kangaroo",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-18T05:35:48Z |
---
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).
|
unitova/blockassist-bc-zealous_sneaky_raven_1755493635
|
unitova
| 2025-08-18T05:32:18Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"zealous sneaky raven",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-18T05:32:15Z |
---
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).
|
donoway/ARC-Challenge_Llama-3.2-1B-2k4vxbc8
|
donoway
| 2025-08-18T05:29:37Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"generated_from_trainer",
"base_model:meta-llama/Llama-3.2-1B",
"base_model:finetune:meta-llama/Llama-3.2-1B",
"license:llama3.2",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-18T05:19:05Z |
---
library_name: transformers
license: llama3.2
base_model: meta-llama/Llama-3.2-1B
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: ARC-Challenge_Llama-3.2-1B-2k4vxbc8
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. -->
# ARC-Challenge_Llama-3.2-1B-2k4vxbc8
This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.9242
- Model Preparation Time: 0.0058
- Mdl: 1261.4202
- Accumulated Loss: 874.3499
- Correct Preds: 110.0
- Total Preds: 299.0
- Accuracy: 0.3679
- Correct Gen Preds: 106.0
- Gen Accuracy: 0.3545
- Correct Gen Preds 32: 15.0
- Correct Preds 32: 18.0
- Total Labels 32: 64.0
- Accuracy 32: 0.2812
- Gen Accuracy 32: 0.2344
- Correct Gen Preds 33: 28.0
- Correct Preds 33: 28.0
- Total Labels 33: 73.0
- Accuracy 33: 0.3836
- Gen Accuracy 33: 0.3836
- Correct Gen Preds 34: 39.0
- Correct Preds 34: 40.0
- Total Labels 34: 78.0
- Accuracy 34: 0.5128
- Gen Accuracy 34: 0.5
- Correct Gen Preds 35: 24.0
- Correct Preds 35: 24.0
- Total Labels 35: 83.0
- Accuracy 35: 0.2892
- Gen Accuracy 35: 0.2892
- Correct Gen Preds 36: 0.0
- Correct Preds 36: 0.0
- Total Labels 36: 1.0
- Accuracy 36: 0.0
- Gen Accuracy 36: 0.0
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 64
- eval_batch_size: 112
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.01
- num_epochs: 100
### Training results
| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Mdl | Accumulated Loss | Correct Preds | Total Preds | Accuracy | Correct Gen Preds | Gen Accuracy | Correct Gen Preds 32 | Correct Preds 32 | Total Labels 32 | Accuracy 32 | Gen Accuracy 32 | Correct Gen Preds 33 | Correct Preds 33 | Total Labels 33 | Accuracy 33 | Gen Accuracy 33 | Correct Gen Preds 34 | Correct Preds 34 | Total Labels 34 | Accuracy 34 | Gen Accuracy 34 | Correct Gen Preds 35 | Correct Preds 35 | Total Labels 35 | Accuracy 35 | Gen Accuracy 35 | Correct Gen Preds 36 | Correct Preds 36 | Total Labels 36 | Accuracy 36 | Gen Accuracy 36 |
|:-------------:|:-----:|:----:|:---------------:|:----------------------:|:---------:|:----------------:|:-------------:|:-----------:|:--------:|:-----------------:|:------------:|:--------------------:|:----------------:|:---------------:|:-----------:|:---------------:|:--------------------:|:----------------:|:---------------:|:-----------:|:---------------:|:--------------------:|:----------------:|:---------------:|:-----------:|:---------------:|:--------------------:|:----------------:|:---------------:|:-----------:|:---------------:|:--------------------:|:----------------:|:---------------:|:-----------:|:---------------:|
| No log | 0 | 0 | 1.6389 | 0.0058 | 706.9523 | 490.0220 | 66.0 | 299.0 | 0.2207 | 66.0 | 0.2207 | 62.0 | 62.0 | 64.0 | 0.9688 | 0.9688 | 0.0 | 0.0 | 73.0 | 0.0 | 0.0 | 4.0 | 4.0 | 78.0 | 0.0513 | 0.0513 | 0.0 | 0.0 | 83.0 | 0.0 | 0.0 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
| 0.9641 | 1.0 | 2 | 1.9883 | 0.0058 | 857.7052 | 594.5160 | 64.0 | 299.0 | 0.2140 | 64.0 | 0.2140 | 64.0 | 64.0 | 64.0 | 1.0 | 1.0 | 0.0 | 0.0 | 73.0 | 0.0 | 0.0 | 0.0 | 0.0 | 78.0 | 0.0 | 0.0 | 0.0 | 0.0 | 83.0 | 0.0 | 0.0 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
| 1.414 | 2.0 | 4 | 1.6542 | 0.0058 | 713.5692 | 494.6085 | 76.0 | 299.0 | 0.2542 | 76.0 | 0.2542 | 0.0 | 0.0 | 64.0 | 0.0 | 0.0 | 73.0 | 73.0 | 73.0 | 1.0 | 1.0 | 3.0 | 3.0 | 78.0 | 0.0385 | 0.0385 | 0.0 | 0.0 | 83.0 | 0.0 | 0.0 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
| 1.2629 | 3.0 | 6 | 1.7538 | 0.0058 | 756.5379 | 524.3921 | 64.0 | 299.0 | 0.2140 | 64.0 | 0.2140 | 64.0 | 64.0 | 64.0 | 1.0 | 1.0 | 0.0 | 0.0 | 73.0 | 0.0 | 0.0 | 0.0 | 0.0 | 78.0 | 0.0 | 0.0 | 0.0 | 0.0 | 83.0 | 0.0 | 0.0 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
| 1.123 | 4.0 | 8 | 1.5366 | 0.0058 | 662.8170 | 459.4297 | 67.0 | 299.0 | 0.2241 | 67.0 | 0.2241 | 54.0 | 54.0 | 64.0 | 0.8438 | 0.8438 | 0.0 | 0.0 | 73.0 | 0.0 | 0.0 | 13.0 | 13.0 | 78.0 | 0.1667 | 0.1667 | 0.0 | 0.0 | 83.0 | 0.0 | 0.0 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
| 0.837 | 5.0 | 10 | 1.4879 | 0.0058 | 641.8253 | 444.8794 | 86.0 | 299.0 | 0.2876 | 86.0 | 0.2876 | 28.0 | 28.0 | 64.0 | 0.4375 | 0.4375 | 1.0 | 1.0 | 73.0 | 0.0137 | 0.0137 | 45.0 | 45.0 | 78.0 | 0.5769 | 0.5769 | 12.0 | 12.0 | 83.0 | 0.1446 | 0.1446 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
| 0.2588 | 6.0 | 12 | 2.4117 | 0.0058 | 1040.3208 | 721.0954 | 84.0 | 299.0 | 0.2809 | 78.0 | 0.2609 | 34.0 | 38.0 | 64.0 | 0.5938 | 0.5312 | 7.0 | 7.0 | 73.0 | 0.0959 | 0.0959 | 22.0 | 23.0 | 78.0 | 0.2949 | 0.2821 | 15.0 | 16.0 | 83.0 | 0.1928 | 0.1807 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
| 0.2513 | 7.0 | 14 | 2.9242 | 0.0058 | 1261.4202 | 874.3499 | 110.0 | 299.0 | 0.3679 | 106.0 | 0.3545 | 15.0 | 18.0 | 64.0 | 0.2812 | 0.2344 | 28.0 | 28.0 | 73.0 | 0.3836 | 0.3836 | 39.0 | 40.0 | 78.0 | 0.5128 | 0.5 | 24.0 | 24.0 | 83.0 | 0.2892 | 0.2892 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
| 0.6519 | 8.0 | 16 | 3.6514 | 0.0058 | 1575.0833 | 1091.7645 | 108.0 | 299.0 | 0.3612 | 103.0 | 0.3445 | 12.0 | 15.0 | 64.0 | 0.2344 | 0.1875 | 46.0 | 47.0 | 73.0 | 0.6438 | 0.6301 | 34.0 | 35.0 | 78.0 | 0.4487 | 0.4359 | 11.0 | 11.0 | 83.0 | 0.1325 | 0.1325 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
| 0.001 | 9.0 | 18 | 4.4460 | 0.0058 | 1917.8702 | 1329.3663 | 106.0 | 299.0 | 0.3545 | 100.0 | 0.3344 | 16.0 | 20.0 | 64.0 | 0.3125 | 0.25 | 41.0 | 42.0 | 73.0 | 0.5753 | 0.5616 | 33.0 | 34.0 | 78.0 | 0.4359 | 0.4231 | 10.0 | 10.0 | 83.0 | 0.1205 | 0.1205 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
| 0.0001 | 10.0 | 20 | 5.6543 | 0.0058 | 2439.0822 | 1690.6429 | 106.0 | 299.0 | 0.3545 | 101.0 | 0.3378 | 23.0 | 27.0 | 64.0 | 0.4219 | 0.3594 | 37.0 | 37.0 | 73.0 | 0.5068 | 0.5068 | 31.0 | 32.0 | 78.0 | 0.4103 | 0.3974 | 10.0 | 10.0 | 83.0 | 0.1205 | 0.1205 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
| 0.0001 | 11.0 | 22 | 6.6275 | 0.0058 | 2858.8977 | 1981.6369 | 105.0 | 299.0 | 0.3512 | 104.0 | 0.3478 | 29.0 | 29.0 | 64.0 | 0.4531 | 0.4531 | 35.0 | 35.0 | 73.0 | 0.4795 | 0.4795 | 29.0 | 30.0 | 78.0 | 0.3846 | 0.3718 | 11.0 | 11.0 | 83.0 | 0.1325 | 0.1325 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
| 0.0 | 12.0 | 24 | 7.3259 | 0.0058 | 3160.1247 | 2190.4315 | 102.0 | 299.0 | 0.3411 | 101.0 | 0.3378 | 29.0 | 29.0 | 64.0 | 0.4531 | 0.4531 | 32.0 | 33.0 | 73.0 | 0.4521 | 0.4384 | 29.0 | 29.0 | 78.0 | 0.3718 | 0.3718 | 11.0 | 11.0 | 83.0 | 0.1325 | 0.1325 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
| 0.0 | 13.0 | 26 | 7.8958 | 0.0058 | 3405.9778 | 2360.8439 | 100.0 | 299.0 | 0.3344 | 99.0 | 0.3311 | 30.0 | 30.0 | 64.0 | 0.4688 | 0.4688 | 29.0 | 29.0 | 73.0 | 0.3973 | 0.3973 | 28.0 | 29.0 | 78.0 | 0.3718 | 0.3590 | 12.0 | 12.0 | 83.0 | 0.1446 | 0.1446 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
| 0.0 | 14.0 | 28 | 8.2528 | 0.0058 | 3559.9558 | 2467.5733 | 97.0 | 299.0 | 0.3244 | 97.0 | 0.3244 | 31.0 | 31.0 | 64.0 | 0.4844 | 0.4844 | 27.0 | 27.0 | 73.0 | 0.3699 | 0.3699 | 27.0 | 27.0 | 78.0 | 0.3462 | 0.3462 | 12.0 | 12.0 | 83.0 | 0.1446 | 0.1446 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
| 0.0 | 15.0 | 30 | 8.4984 | 0.0058 | 3665.9234 | 2541.0245 | 96.0 | 299.0 | 0.3211 | 96.0 | 0.3211 | 32.0 | 32.0 | 64.0 | 0.5 | 0.5 | 27.0 | 27.0 | 73.0 | 0.3699 | 0.3699 | 26.0 | 26.0 | 78.0 | 0.3333 | 0.3333 | 11.0 | 11.0 | 83.0 | 0.1325 | 0.1325 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
| 0.0 | 16.0 | 32 | 8.7216 | 0.0058 | 3762.2008 | 2607.7589 | 97.0 | 299.0 | 0.3244 | 97.0 | 0.3244 | 32.0 | 32.0 | 64.0 | 0.5 | 0.5 | 27.0 | 27.0 | 73.0 | 0.3699 | 0.3699 | 27.0 | 27.0 | 78.0 | 0.3462 | 0.3462 | 11.0 | 11.0 | 83.0 | 0.1325 | 0.1325 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
| 0.0 | 17.0 | 34 | 8.8293 | 0.0058 | 3808.6478 | 2639.9535 | 97.0 | 299.0 | 0.3244 | 96.0 | 0.3211 | 32.0 | 33.0 | 64.0 | 0.5156 | 0.5 | 27.0 | 27.0 | 73.0 | 0.3699 | 0.3699 | 27.0 | 27.0 | 78.0 | 0.3462 | 0.3462 | 10.0 | 10.0 | 83.0 | 0.1205 | 0.1205 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
| 0.0 | 18.0 | 36 | 8.9085 | 0.0058 | 3842.8136 | 2663.6354 | 98.0 | 299.0 | 0.3278 | 97.0 | 0.3244 | 32.0 | 33.0 | 64.0 | 0.5156 | 0.5 | 27.0 | 27.0 | 73.0 | 0.3699 | 0.3699 | 27.0 | 27.0 | 78.0 | 0.3462 | 0.3462 | 11.0 | 11.0 | 83.0 | 0.1325 | 0.1325 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
| 0.0 | 19.0 | 38 | 8.9689 | 0.0058 | 3868.8669 | 2681.6942 | 97.0 | 299.0 | 0.3244 | 96.0 | 0.3211 | 32.0 | 33.0 | 64.0 | 0.5156 | 0.5 | 27.0 | 27.0 | 73.0 | 0.3699 | 0.3699 | 27.0 | 27.0 | 78.0 | 0.3462 | 0.3462 | 10.0 | 10.0 | 83.0 | 0.1205 | 0.1205 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
| 0.0 | 20.0 | 40 | 8.9820 | 0.0058 | 3874.5370 | 2685.6244 | 97.0 | 299.0 | 0.3244 | 96.0 | 0.3211 | 32.0 | 33.0 | 64.0 | 0.5156 | 0.5 | 27.0 | 27.0 | 73.0 | 0.3699 | 0.3699 | 27.0 | 27.0 | 78.0 | 0.3462 | 0.3462 | 10.0 | 10.0 | 83.0 | 0.1205 | 0.1205 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
| 0.0 | 21.0 | 42 | 9.0110 | 0.0058 | 3887.0514 | 2694.2987 | 95.0 | 299.0 | 0.3177 | 94.0 | 0.3144 | 32.0 | 33.0 | 64.0 | 0.5156 | 0.5 | 26.0 | 26.0 | 73.0 | 0.3562 | 0.3562 | 26.0 | 26.0 | 78.0 | 0.3333 | 0.3333 | 10.0 | 10.0 | 83.0 | 0.1205 | 0.1205 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
| 0.0 | 22.0 | 44 | 9.0653 | 0.0058 | 3910.4803 | 2710.5384 | 97.0 | 299.0 | 0.3244 | 96.0 | 0.3211 | 32.0 | 33.0 | 64.0 | 0.5156 | 0.5 | 27.0 | 27.0 | 73.0 | 0.3699 | 0.3699 | 27.0 | 27.0 | 78.0 | 0.3462 | 0.3462 | 10.0 | 10.0 | 83.0 | 0.1205 | 0.1205 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
| 0.0 | 23.0 | 46 | 9.0546 | 0.0058 | 3905.8529 | 2707.3309 | 97.0 | 299.0 | 0.3244 | 96.0 | 0.3211 | 32.0 | 33.0 | 64.0 | 0.5156 | 0.5 | 27.0 | 27.0 | 73.0 | 0.3699 | 0.3699 | 27.0 | 27.0 | 78.0 | 0.3462 | 0.3462 | 10.0 | 10.0 | 83.0 | 0.1205 | 0.1205 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
| 0.0 | 24.0 | 48 | 9.0612 | 0.0058 | 3908.7044 | 2709.3074 | 97.0 | 299.0 | 0.3244 | 96.0 | 0.3211 | 32.0 | 33.0 | 64.0 | 0.5156 | 0.5 | 27.0 | 27.0 | 73.0 | 0.3699 | 0.3699 | 27.0 | 27.0 | 78.0 | 0.3462 | 0.3462 | 10.0 | 10.0 | 83.0 | 0.1205 | 0.1205 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
| 0.0 | 25.0 | 50 | 9.0434 | 0.0058 | 3901.0103 | 2703.9743 | 97.0 | 299.0 | 0.3244 | 96.0 | 0.3211 | 32.0 | 33.0 | 64.0 | 0.5156 | 0.5 | 27.0 | 27.0 | 73.0 | 0.3699 | 0.3699 | 27.0 | 27.0 | 78.0 | 0.3462 | 0.3462 | 10.0 | 10.0 | 83.0 | 0.1205 | 0.1205 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
| 0.0 | 26.0 | 52 | 9.0563 | 0.0058 | 3906.5620 | 2707.8224 | 98.0 | 299.0 | 0.3278 | 97.0 | 0.3244 | 32.0 | 33.0 | 64.0 | 0.5156 | 0.5 | 27.0 | 27.0 | 73.0 | 0.3699 | 0.3699 | 27.0 | 27.0 | 78.0 | 0.3462 | 0.3462 | 11.0 | 11.0 | 83.0 | 0.1325 | 0.1325 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
| 0.0 | 27.0 | 54 | 9.0366 | 0.0058 | 3898.0915 | 2701.9511 | 97.0 | 299.0 | 0.3244 | 96.0 | 0.3211 | 32.0 | 33.0 | 64.0 | 0.5156 | 0.5 | 27.0 | 27.0 | 73.0 | 0.3699 | 0.3699 | 27.0 | 27.0 | 78.0 | 0.3462 | 0.3462 | 10.0 | 10.0 | 83.0 | 0.1205 | 0.1205 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
| 0.0 | 28.0 | 56 | 9.0691 | 0.0058 | 3912.0940 | 2711.6569 | 97.0 | 299.0 | 0.3244 | 96.0 | 0.3211 | 32.0 | 33.0 | 64.0 | 0.5156 | 0.5 | 27.0 | 27.0 | 73.0 | 0.3699 | 0.3699 | 27.0 | 27.0 | 78.0 | 0.3462 | 0.3462 | 10.0 | 10.0 | 83.0 | 0.1205 | 0.1205 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
| 0.0 | 29.0 | 58 | 9.0650 | 0.0058 | 3910.3459 | 2710.4453 | 97.0 | 299.0 | 0.3244 | 96.0 | 0.3211 | 32.0 | 33.0 | 64.0 | 0.5156 | 0.5 | 27.0 | 27.0 | 73.0 | 0.3699 | 0.3699 | 27.0 | 27.0 | 78.0 | 0.3462 | 0.3462 | 10.0 | 10.0 | 83.0 | 0.1205 | 0.1205 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
| 0.0 | 30.0 | 60 | 9.0651 | 0.0058 | 3910.3806 | 2710.4693 | 97.0 | 299.0 | 0.3244 | 96.0 | 0.3211 | 32.0 | 33.0 | 64.0 | 0.5156 | 0.5 | 27.0 | 27.0 | 73.0 | 0.3699 | 0.3699 | 27.0 | 27.0 | 78.0 | 0.3462 | 0.3462 | 10.0 | 10.0 | 83.0 | 0.1205 | 0.1205 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
| 0.0 | 31.0 | 62 | 9.0466 | 0.0058 | 3902.3980 | 2704.9362 | 97.0 | 299.0 | 0.3244 | 96.0 | 0.3211 | 32.0 | 33.0 | 64.0 | 0.5156 | 0.5 | 26.0 | 26.0 | 73.0 | 0.3562 | 0.3562 | 27.0 | 27.0 | 78.0 | 0.3462 | 0.3462 | 11.0 | 11.0 | 83.0 | 0.1325 | 0.1325 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
| 0.0 | 32.0 | 64 | 9.0608 | 0.0058 | 3908.5396 | 2709.1932 | 97.0 | 299.0 | 0.3244 | 96.0 | 0.3211 | 32.0 | 33.0 | 64.0 | 0.5156 | 0.5 | 26.0 | 26.0 | 73.0 | 0.3562 | 0.3562 | 27.0 | 27.0 | 78.0 | 0.3462 | 0.3462 | 11.0 | 11.0 | 83.0 | 0.1325 | 0.1325 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
| 0.0 | 33.0 | 66 | 9.0827 | 0.0058 | 3917.9843 | 2715.7397 | 97.0 | 299.0 | 0.3244 | 96.0 | 0.3211 | 32.0 | 33.0 | 64.0 | 0.5156 | 0.5 | 27.0 | 27.0 | 73.0 | 0.3699 | 0.3699 | 27.0 | 27.0 | 78.0 | 0.3462 | 0.3462 | 10.0 | 10.0 | 83.0 | 0.1205 | 0.1205 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
| 0.0 | 34.0 | 68 | 9.0744 | 0.0058 | 3914.3706 | 2713.2349 | 98.0 | 299.0 | 0.3278 | 97.0 | 0.3244 | 32.0 | 33.0 | 64.0 | 0.5156 | 0.5 | 27.0 | 27.0 | 73.0 | 0.3699 | 0.3699 | 27.0 | 27.0 | 78.0 | 0.3462 | 0.3462 | 11.0 | 11.0 | 83.0 | 0.1325 | 0.1325 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
| 0.0 | 35.0 | 70 | 9.0704 | 0.0058 | 3912.6593 | 2712.0488 | 97.0 | 299.0 | 0.3244 | 96.0 | 0.3211 | 32.0 | 33.0 | 64.0 | 0.5156 | 0.5 | 27.0 | 27.0 | 73.0 | 0.3699 | 0.3699 | 27.0 | 27.0 | 78.0 | 0.3462 | 0.3462 | 10.0 | 10.0 | 83.0 | 0.1205 | 0.1205 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
| 0.0 | 36.0 | 72 | 9.0978 | 0.0058 | 3924.4855 | 2720.2460 | 97.0 | 299.0 | 0.3244 | 96.0 | 0.3211 | 32.0 | 33.0 | 64.0 | 0.5156 | 0.5 | 27.0 | 27.0 | 73.0 | 0.3699 | 0.3699 | 27.0 | 27.0 | 78.0 | 0.3462 | 0.3462 | 10.0 | 10.0 | 83.0 | 0.1205 | 0.1205 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
| 0.0 | 37.0 | 74 | 9.0858 | 0.0058 | 3919.3165 | 2716.6632 | 97.0 | 299.0 | 0.3244 | 96.0 | 0.3211 | 32.0 | 33.0 | 64.0 | 0.5156 | 0.5 | 27.0 | 27.0 | 73.0 | 0.3699 | 0.3699 | 27.0 | 27.0 | 78.0 | 0.3462 | 0.3462 | 10.0 | 10.0 | 83.0 | 0.1205 | 0.1205 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
### Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1
|
ymatari/diffusion_so101_place_ball
|
ymatari
| 2025-08-18T05:10:03Z | 0 | 0 |
lerobot
|
[
"lerobot",
"safetensors",
"diffusion",
"robotics",
"dataset:ymatari/place-ball-2",
"arxiv:2303.04137",
"license:apache-2.0",
"region:us"
] |
robotics
| 2025-08-18T05:08:22Z |
---
datasets: ymatari/place-ball-2
library_name: lerobot
license: apache-2.0
model_name: diffusion
pipeline_tag: robotics
tags:
- diffusion
- robotics
- 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
|
donoway/GSM8K-Binary_Llama-3.2-1B-cx4sa3qr
|
donoway
| 2025-08-18T05:08:35Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"generated_from_trainer",
"base_model:meta-llama/Llama-3.2-1B",
"base_model:finetune:meta-llama/Llama-3.2-1B",
"license:llama3.2",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-18T04:54:47Z |
---
library_name: transformers
license: llama3.2
base_model: meta-llama/Llama-3.2-1B
tags:
- generated_from_trainer
model-index:
- name: GSM8K-Binary_Llama-3.2-1B-cx4sa3qr
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. -->
# GSM8K-Binary_Llama-3.2-1B-cx4sa3qr
This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 64
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.01
- num_epochs: 100
### Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1
|
SanskarModi/q-FrozenLake-v1-4x4-noSlippery
|
SanskarModi
| 2025-08-18T05:07:40Z | 0 | 0 | null |
[
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2025-08-18T05:07:22Z |
---
tags:
- FrozenLake-v1-4x4-no_slippery
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-FrozenLake-v1-4x4-noSlippery
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: FrozenLake-v1-4x4-no_slippery
type: FrozenLake-v1-4x4-no_slippery
metrics:
- type: mean_reward
value: 1.00 +/- 0.00
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
```python
model = load_from_hub(repo_id="SanskarModi/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
Muapi/cinematic-ww2-style-xl-f1d
|
Muapi
| 2025-08-18T05:06:46Z | 0 | 0 | null |
[
"lora",
"stable-diffusion",
"flux.1-d",
"license:openrail++",
"region:us"
] | null | 2025-08-18T05:06:07Z |
---
license: openrail++
tags:
- lora
- stable-diffusion
- flux.1-d
model_type: LoRA
---
# Cinematic WW2 Style XL + F1D
**Base model**: Flux.1 D
**Trained words**: ww2 style
## 🧠 Usage (Python)
🔑 **Get your MUAPI key** from [muapi.ai/access-keys](https://muapi.ai/access-keys)
```python
import requests, os
url = "https://api.muapi.ai/api/v1/flux_dev_lora_image"
headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")}
payload = {
"prompt": "masterpiece, best quality, 1girl, looking at viewer",
"model_id": [{"model": "civitai:196146@893575", "weight": 1.0}],
"width": 1024,
"height": 1024,
"num_images": 1
}
print(requests.post(url, headers=headers, json=payload).json())
```
|
hanlforever/xlm-roberta-base-finetuned-panx-de
|
hanlforever
| 2025-08-18T04:57:49Z | 1 | 0 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"xlm-roberta",
"token-classification",
"generated_from_trainer",
"base_model:FacebookAI/xlm-roberta-base",
"base_model:finetune:FacebookAI/xlm-roberta-base",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-08-22T14:17:15Z |
---
library_name: transformers
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: xlm-roberta-base-finetuned-panx-de
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. -->
# xlm-roberta-base-finetuned-panx-de
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1352
- F1: 0.8631
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 24
- eval_batch_size: 24
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.264 | 1.0 | 525 | 0.1571 | 0.8213 |
| 0.128 | 2.0 | 1050 | 0.1315 | 0.8487 |
| 0.0794 | 3.0 | 1575 | 0.1352 | 0.8631 |
### Framework versions
- Transformers 4.45.2
- Pytorch 2.5.1+cu118
- Datasets 4.0.0
- Tokenizers 0.20.3
|
mkhalifa/ThinkPRM-gptoss-20B
|
mkhalifa
| 2025-08-18T04:53:49Z | 0 | 0 |
transformers
|
[
"transformers",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-08-18T04:53:47Z |
---
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]
|
minhnguyet/my-mistral-7b
|
minhnguyet
| 2025-08-18T04:44:16Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"mistral",
"trl",
"en",
"base_model:unsloth/mistral-7b-bnb-4bit",
"base_model:finetune:unsloth/mistral-7b-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-08-18T04:44:12Z |
---
base_model: unsloth/mistral-7b-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** minhnguyet
- **License:** apache-2.0
- **Finetuned from model :** unsloth/mistral-7b-bnb-4bit
This mistral 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)
|
Sayemahsjn/blockassist-bc-playful_feline_octopus_1755490507
|
Sayemahsjn
| 2025-08-18T04:33:47Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"playful feline octopus",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-18T04:33:43Z |
---
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).
|
abhinayadutta/flan-t5-large-counter-speech-gen_PREFIX
|
abhinayadutta
| 2025-08-18T04:31:03Z | 0 | 0 |
peft
|
[
"peft",
"arxiv:1910.09700",
"base_model:google/flan-t5-large",
"base_model:adapter:google/flan-t5-large",
"region:us"
] | null | 2025-08-18T04:30:59Z |
---
base_model: google/flan-t5-large
library_name: peft
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
## Training procedure
### Framework versions
- PEFT 0.6.0
|
hobson123/blockassist-bc-mammalian_dense_gibbon_1755490747
|
hobson123
| 2025-08-18T04:25:01Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"mammalian dense gibbon",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-18T04:24:47Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- mammalian dense gibbon
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
Muapi/anthropomorphic
|
Muapi
| 2025-08-18T04:15:01Z | 0 | 0 | null |
[
"lora",
"stable-diffusion",
"flux.1-d",
"license:openrail++",
"region:us"
] | null | 2025-08-18T04:14:51Z |
---
license: openrail++
tags:
- lora
- stable-diffusion
- flux.1-d
model_type: LoRA
---
# Anthropomorphic
**Base model**: Flux.1 D
**Trained words**:
## 🧠 Usage (Python)
🔑 **Get your MUAPI key** from [muapi.ai/access-keys](https://muapi.ai/access-keys)
```python
import requests, os
url = "https://api.muapi.ai/api/v1/flux_dev_lora_image"
headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")}
payload = {
"prompt": "masterpiece, best quality, 1girl, looking at viewer",
"model_id": [{"model": "civitai:969452@1085477", "weight": 1.0}],
"width": 1024,
"height": 1024,
"num_images": 1
}
print(requests.post(url, headers=headers, json=payload).json())
```
|
AshwinKM2005/Hangman_TrexQuant_Final
|
AshwinKM2005
| 2025-08-18T04:13:48Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"deberta-v2",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-08-16T05:24:19Z |
---
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]
|
lejonck/xlsr53-ptbr-mupe-final3
|
lejonck
| 2025-08-18T03:54:58Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"wav2vec2",
"automatic-speech-recognition",
"generated_from_trainer",
"base_model:lejonck/xlsr53-ptbr-mupe-final2",
"base_model:finetune:lejonck/xlsr53-ptbr-mupe-final2",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2025-08-18T03:54:31Z |
---
library_name: transformers
base_model: lejonck/xlsr53-ptbr-mupe-final2
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: xlsr53-ptbr-mupe-final3
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. -->
# xlsr53-ptbr-mupe-final3
This model is a fine-tuned version of [lejonck/xlsr53-ptbr-mupe-final2](https://huggingface.co/lejonck/xlsr53-ptbr-mupe-final2) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4183
- Wer: 0.1598
- Cer: 0.0626
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 12
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
| 0.7433 | 1.0 | 2000 | 0.4015 | 0.1761 | 0.0662 |
| 0.7252 | 2.0 | 4000 | 0.3959 | 0.1732 | 0.0658 |
| 0.553 | 3.0 | 6000 | 0.3915 | 0.1643 | 0.0635 |
| 0.7068 | 4.0 | 8000 | 0.3978 | 0.1632 | 0.0643 |
| 0.4559 | 5.0 | 10000 | 0.4137 | 0.1624 | 0.0626 |
| 0.7618 | 6.0 | 12000 | 0.4074 | 0.1611 | 0.0620 |
| 0.4847 | 7.0 | 14000 | 0.4151 | 0.1605 | 0.0618 |
| 0.2968 | 8.0 | 16000 | 0.4183 | 0.1596 | 0.0625 |
| 0.3977 | 9.0 | 18000 | 0.4310 | 0.1619 | 0.0623 |
| 0.3833 | 10.0 | 20000 | 0.4314 | 0.1617 | 0.0620 |
| 0.5201 | 11.0 | 22000 | 0.4228 | 0.1613 | 0.0623 |
| 0.4379 | 12.0 | 24000 | 0.4298 | 0.1605 | 0.0622 |
### Framework versions
- Transformers 4.55.1
- Pytorch 2.7.0+cu126
- Datasets 4.0.0
- Tokenizers 0.21.4
|
BootesVoid/cmegjg14r0n9mrts8kbew8srf_cmegjprdb0namrts8cudbznhk
|
BootesVoid
| 2025-08-18T03:48:21Z | 0 | 0 |
diffusers
|
[
"diffusers",
"flux",
"lora",
"replicate",
"text-to-image",
"en",
"base_model:black-forest-labs/FLUX.1-dev",
"base_model:adapter:black-forest-labs/FLUX.1-dev",
"license:other",
"region:us"
] |
text-to-image
| 2025-08-18T03:48:20Z |
---
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
language:
- en
tags:
- flux
- diffusers
- lora
- replicate
base_model: "black-forest-labs/FLUX.1-dev"
pipeline_tag: text-to-image
# widget:
# - text: >-
# prompt
# output:
# url: https://...
instance_prompt: SEXY
---
# Cmegjg14R0N9Mrts8Kbew8Srf_Cmegjprdb0Namrts8Cudbznhk
<Gallery />
## About this LoRA
This is a [LoRA](https://replicate.com/docs/guides/working-with-loras) for the FLUX.1-dev text-to-image model. It can be used with diffusers or ComfyUI.
It was trained on [Replicate](https://replicate.com/) using AI toolkit: https://replicate.com/ostris/flux-dev-lora-trainer/train
## Trigger words
You should use `SEXY` to trigger the image generation.
## Run this LoRA with an API using Replicate
```py
import replicate
input = {
"prompt": "SEXY",
"lora_weights": "https://huggingface.co/BootesVoid/cmegjg14r0n9mrts8kbew8srf_cmegjprdb0namrts8cudbznhk/resolve/main/lora.safetensors"
}
output = replicate.run(
"black-forest-labs/flux-dev-lora",
input=input
)
for index, item in enumerate(output):
with open(f"output_{index}.webp", "wb") as file:
file.write(item.read())
```
## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
```py
from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('BootesVoid/cmegjg14r0n9mrts8kbew8srf_cmegjprdb0namrts8cudbznhk', weight_name='lora.safetensors')
image = pipeline('SEXY').images[0]
```
For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
## Training details
- Steps: 2000
- Learning rate: 0.0004
- LoRA rank: 16
## Contribute your own examples
You can use the [community tab](https://huggingface.co/BootesVoid/cmegjg14r0n9mrts8kbew8srf_cmegjprdb0namrts8cudbznhk/discussions) to add images that show off what you’ve made with this LoRA.
|
quantumxnode/blockassist-bc-dormant_peckish_seahorse_1755486960
|
quantumxnode
| 2025-08-18T03:41:56Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"dormant peckish seahorse",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-18T03:41:53Z |
---
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).
|
AIDC-AI/Ovis2.5-9B
|
AIDC-AI
| 2025-08-18T03:37:12Z | 0 | 158 |
transformers
|
[
"transformers",
"safetensors",
"ovis2_5",
"text-generation",
"MLLM",
"image-text-to-text",
"conversational",
"custom_code",
"en",
"zh",
"dataset:AIDC-AI/Ovis-dataset",
"arxiv:2405.20797",
"license:apache-2.0",
"autotrain_compatible",
"region:us"
] |
image-text-to-text
| 2025-08-15T05:54:34Z |
---
license: apache-2.0
datasets:
- AIDC-AI/Ovis-dataset
library_name: transformers
tags:
- MLLM
pipeline_tag: image-text-to-text
language:
- en
- zh
---
# Ovis2.5-9B
<div align="center">
<img src=https://cdn-uploads.huggingface.co/production/uploads/637aebed7ce76c3b834cea37/3IK823BZ8w-mz_QfeYkDn.png width="30%"/>
</div>
<p align="center">
<a href="https://github.com/AIDC-AI/Ovis/blob/main/docs/Ovis2_5_Tech_Report.pdf"><img src="https://img.shields.io/badge/📖_Technical_Report-Ovis2.5-b31b1b.svg" alt="technical report"></a>
<a href="https://github.com/AIDC-AI/Ovis"><img src="https://img.shields.io/badge/GitHub-AIDC--AI/Ovis-blue?style=flat&logo=github" alt="code"></a>
<a href="https://huggingface.co/spaces/AIDC-AI/Ovis2.5-9B"><img src="https://img.shields.io/badge/🎨_HF_Spaces-AIDC--AI/Ovis2.5--9B-lightblack" alt="demo"></a>
<a href="https://huggingface.co/collections/AIDC-AI/ovis25-689ec1474633b2aab8809335"><img src="https://img.shields.io/badge/🤗_Models-AIDC--AI/Ovis2.5-yellow" alt="models"></a>
</p>
## Introduction
We are pleased to announce the release of **Ovis2.5**, the successor to Ovis2, designed for native-resolution visual perception and enhanced multimodal reasoning.
It integrates a native-resolution vision transformer (NaViT) that processes images at their original, variable resolutions, eliminating the need for fixed-resolution tiling and preserving both fine details and global layout—crucial for visually dense content such as charts and diagrams.
To strengthen reasoning, Ovis2.5 is trained not only on linear chain-of-thought (CoT) but also on reflective reasoning, including self-checking and revision.
This advanced capability is available at inference as an optional *thinking mode*, enabling users to trade latency for higher accuracy on complex inputs.
Building on these advances, **Ovis2.5-9B** achieves an average score of 78.3 on the OpenCompass multimodal evaluation suite (SOTA among open-source MLLMs under 40B parameters), while the lightweight **Ovis2.5-2B** scores 73.9, continuing the “small model, big performance” philosophy for resource-constrained scenarios.
<div align="center">
<img src="https://cdn-uploads.huggingface.co/production/uploads/637aebed7ce76c3b834cea37/kh-1dhZRAduP-P4SkIhXr.png" width="100%" />
</div>
**Key Features**
* **Native-Resolution Perception** — NaViT vision encoder preserves fine details and global structure without lossy tiling.
* **Deep-Reasoning Capability** — Optional *thinking mode* for self-checking and revision beyond linear CoT. *Thinking budget* supported.
* **Chart & Document OCR** — State-of-the-art at its scale for complex chart analysis, document understanding (including tables and forms), and OCR.
* **Broad Task Coverage** — Demonstrates leading performance on image reasoning, video understanding, and grounding benchmarks, showcasing strong general multimodal capability.
<div align="center">
<img src="https://cdn-uploads.huggingface.co/production/uploads/637aebed7ce76c3b834cea37/4kw2RRUhXDiMZdU7wGOfP.png" width="100%" />
</div>
## Quick Inference
Below is a simple example demonstrating how to run Ovis2.5 with a single image input.
First, install the required dependencies:
```bash
pip install torch==2.4.0 transformers==4.51.3 numpy==1.25.0 pillow==10.3.0 moviepy==1.0.3
pip install flash-attn==2.7.0.post2 --no-build-isolation
```
Then, run the following code.
```python
import torch
import requests
from PIL import Image
from transformers import AutoModelForCausalLM
MODEL_PATH = "AIDC-AI/Ovis2.5-9B"
# Thinking mode & budget
enable_thinking = True
enable_thinking_budget = True # Only effective if enable_thinking is True.
# Total tokens for thinking + answer. Ensure: max_new_tokens > thinking_budget + 25
max_new_tokens = 3072
thinking_budget = 2048
model = AutoModelForCausalLM.from_pretrained(
MODEL_PATH,
torch_dtype=torch.bfloat16,
trust_remote_code=True
).cuda()
messages = [{
"role": "user",
"content": [
{"type": "image", "image": Image.open(requests.get("https://cdn-uploads.huggingface.co/production/uploads/658a8a837959448ef5500ce5/TIlymOb86R6_Mez3bpmcB.png", stream=True).raw)},
{"type": "text", "text": "Calculate the sum of the numbers in the middle box in figure (c)."},
],
}]
input_ids, pixel_values, grid_thws = model.preprocess_inputs(
messages=messages,
add_generation_prompt=True,
enable_thinking=enable_thinking
)
input_ids = input_ids.cuda()
pixel_values = pixel_values.cuda() if pixel_values is not None else None
grid_thws = grid_thws.cuda() if grid_thws is not None else None
outputs = model.generate(
inputs=input_ids,
pixel_values=pixel_values,
grid_thws=grid_thws,
enable_thinking=enable_thinking,
enable_thinking_budget=enable_thinking_budget,
max_new_tokens=max_new_tokens,
thinking_budget=thinking_budget,
)
response = model.text_tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)
```
The thinking and thinking budget logic can be applied in the same way for multi-image, video and pure text scenarios.
**Note (answer extraction for CoT/Thinking):**
To make evaluation and usage easier, we recommend appending a fixed suffix to prompts when using chain-of-thought (CoT) or thinking mode. This ensures the model clearly outputs a final answer that can be extracted programmatically:
```
End your response with 'Final answer: '.
```
For example:
```
Calculate the sum of the numbers in the middle box in figure (c).
End your response with 'Final answer: '.
```
**Tip:** The sections below include an optional streaming helper (compatible with two-phase thinking/budget runs) and extra inference modes: multi-image, video, and text-only.
<details>
<summary>Optional: Streaming (Advanced)</summary>
When using the thinking budget (two-phase generation), the default `TextIteratorStreamer` is not compatible. If you need streaming output, use the helper below (recommended for streaming with or without budget).
```python
# --- Budget-aware streamer helper ---
from transformers import TextIteratorStreamer
class BudgetAwareTextStreamer(TextIteratorStreamer):
"""A streamer compatible with Ovis two-phase generation.
Call .manual_end() after generation to flush any remaining text.
"""
def manual_end(self):
if len(self.token_cache) > 0:
text = self.tokenizer.decode(self.token_cache, **self.decode_kwargs)
printable_text = text[self.print_len:]
self.token_cache = []
self.print_len = 0
else:
printable_text = ""
self.next_tokens_are_prompt = True
self.on_finalized_text(printable_text, stream_end=True)
# Disable base class's end hook; we'll finalize via manual_end()
def end(self):
pass
```
Example usage (replacing the blocking decode in the main demo):
```python
streamer = BudgetAwareTextStreamer(
model.text_tokenizer,
skip_prompt=True,
skip_special_tokens=True
)
outputs = model.generate(
inputs=input_ids,
pixel_values=pixel_values,
grid_thws=grid_thws,
enable_thinking=enable_thinking,
enable_thinking_budget=enable_thinking_budget,
max_new_tokens=max_new_tokens,
thinking_budget=thinking_budget,
streamer=streamer
)
```
</details>
<details>
<summary>Example: Multi-image</summary>
Demonstrates how to run inference with multiple images and a related question.
```python
# Multi-image inference
multi_image_files = [
"/path/to/image_1.jpg",
"/path/to/image_2.jpg",
"/path/to/image_3.jpg",
]
content = [{"type": "image", "image": Image.open(p).convert("RGB")} for p in multi_image_files]
content.append({"type": "text", "text": "Describe the images."})
messages = [{"role": "user", "content": content}]
input_ids, pixel_values, grid_thws = model.preprocess_inputs(messages=messages, add_generation_prompt=True, max_pixels=896*896)
input_ids = input_ids.cuda()
pixel_values = pixel_values.cuda().to(model.dtype) if pixel_values is not None else None
grid_thws = grid_thws.cuda() if grid_thws is not None else None
with torch.no_grad():
outputs = model.generate(inputs=input_ids, pixel_values=pixel_values, grid_thws=grid_thws,
max_new_tokens=1024, do_sample=True,
eos_token_id=model.text_tokenizer.eos_token_id,
pad_token_id=model.text_tokenizer.pad_token_id)
print(model.text_tokenizer.decode(outputs[0], skip_special_tokens=True))
```
</details>
<details>
<summary>Example: Video</summary>
Demonstrates how to run inference on a video by sampling multiple frames and asking the model to describe the content.
```python
# Video inference
from moviepy.editor import VideoFileClip # pip install moviepy==1.0.3
video_file = "/path/to/video_1.mp4"
num_frames = 8
with VideoFileClip(video_file) as clip:
total_frames = int(clip.fps * clip.duration)
indices = [int(i * total_frames / num_frames) for i in range(num_frames)]
frames = [Image.fromarray(clip.get_frame(t)) for t in (idx / clip.fps for idx in indices)]
messages = [{"role": "user", "content": [
{"type": "video", "video": frames},
{"type": "text", "text": "Describe this video in detail."},
]}]
input_ids, pixel_values, grid_thws = model.preprocess_inputs(messages=messages, add_generation_prompt=True, max_pixels=896*896)
input_ids = input_ids.cuda()
pixel_values = pixel_values.cuda().to(model.dtype) if pixel_values is not None else None
grid_thws = grid_thws.cuda() if grid_thws is not None else None
with torch.no_grad():
outputs = model.generate(inputs=input_ids, pixel_values=pixel_values, grid_thws=grid_thws,
max_new_tokens=1024, do_sample=True,
eos_token_id=model.text_tokenizer.eos_token_id,
pad_token_id=model.text_tokenizer.pad_token_id)
print(model.text_tokenizer.decode(outputs[0], skip_special_tokens=True))
```
</details>
<details>
<summary>Example: Text-only</summary>
Demonstrates how to run inference using only text input without any images or videos.
```python
# Text-only inference
messages = [{"role": "user", "content": "Hi, please introduce Yellow Mountain."}]
input_ids, _, _ = model.preprocess_inputs(messages=messages, add_generation_prompt=True)
input_ids = input_ids.cuda()
with torch.no_grad():
outputs = model.generate(inputs=input_ids, max_new_tokens=1024, do_sample=True,
eos_token_id=model.text_tokenizer.eos_token_id,
pad_token_id=model.text_tokenizer.pad_token_id)
print(model.text_tokenizer.decode(outputs[0], skip_special_tokens=True))
```
</details>
To enable grounding, end your prompt with `Please provide the bounding box coordinates.` (for boxes) or `Please provide the point coordinates.` (for points). To target a specific object, wrap its description in `<ref>` tags, e.g.:
```text
Find the <ref>red apple</ref> in the image. Please provide the bounding box coordinates.
```
Coordinates are normalized to `[0,1)` with the origin `(0,0)` at the top-left corner of the image.
* Point: `<point>(x,y)</point>`
* Bounding box: `<box>(x1,y1),(x2,y2)</box>` where `(x1,y1)` is top-left, `(x2,y2)` is bottom-right.
* Multiple results can be listed in square brackets: `[<box>(...)</box>,<box>(...)</box> ]`
Example:
```text
The image features a serene scene with <ref>three birds</ref>[
<box>(0.401,0.526),(0.430,0.557)</box>,
<box>(0.489,0.494),(0.516,0.526)</box>,
<box>(0.296,0.529),(0.324,0.576)</box>
] flying in formation against a clear blue sky.
```
## Model Zoo
| Ovis MLLMs | ViT | LLM | Model Weights | Demo |
|:-----------|:-----------------------:|:---------------------:|:-------------------------------------------------------:|:--------------------------------------------------------:|
| Ovis2.5-2B | siglip2-so400m-patch16-512 | Qwen3-1.7B | [Huggingface](https://huggingface.co/AIDC-AI/Ovis2.5-2B) | [Space](https://huggingface.co/spaces/AIDC-AI/Ovis2.5-2B) |
| Ovis2.5-9B | siglip2-so400m-patch16-512 | Qwen3-8B | [Huggingface](https://huggingface.co/AIDC-AI/Ovis2.5-9B) | [Space](https://huggingface.co/spaces/AIDC-AI/Ovis2.5-9B) |
## Performance
We evaluate Ovis2.5 using [VLMEvalKit](https://github.com/open-compass/VLMEvalKit), as employed in the OpenCompass multimodal and reasoning evaluation suite.
## Citation
If you find Ovis useful, please consider citing the paper
```
@article{lu2024ovis,
title={Ovis: Structural Embedding Alignment for Multimodal Large Language Model},
author={Shiyin Lu and Yang Li and Qing-Guo Chen and Zhao Xu and Weihua Luo and Kaifu Zhang and Han-Jia Ye},
year={2024},
journal={arXiv:2405.20797}
}
```
## License
This project is licensed under the [Apache License, Version 2.0](https://www.apache.org/licenses/LICENSE-2.0.txt) (SPDX-License-Identifier: Apache-2.0).
## Disclaimer
We used compliance-checking algorithms during the training process, to ensure the compliance of the trained model to the best of our ability. Due to the complexity of the data and the diversity of language model usage scenarios, we cannot guarantee that the model is completely free of copyright issues or improper content. If you believe anything infringes on your rights or generates improper content, please contact us, and we will promptly address the matter.
|
kittygirlhere/blockassist-bc-twitchy_beaked_coral_1755488180
|
kittygirlhere
| 2025-08-18T03:37:07Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"twitchy beaked coral",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-18T03:37:03Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- twitchy beaked coral
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
flockgo/task-13-microsoft-Phi-4-mini-instruct
|
flockgo
| 2025-08-18T03:29:50Z | 1,073 | 0 |
peft
|
[
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:microsoft/Phi-4-mini-instruct",
"base_model:adapter:microsoft/Phi-4-mini-instruct",
"region:us"
] | null | 2025-08-05T01:47:45Z |
---
base_model: microsoft/Phi-4-mini-instruct
library_name: peft
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.14.0
|
ksngi56/blockassist-bc-large_beaked_ram_1755487706
|
ksngi56
| 2025-08-18T03:29:33Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"large beaked ram",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-18T03:29:24Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- large beaked ram
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
tBiski/Gemma2_2b_OpenAI_Summarization_RM_v1_merged
|
tBiski
| 2025-08-18T03:18:24Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"gemma2",
"feature-extraction",
"arxiv:1910.09700",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
feature-extraction
| 2025-08-18T03:15:33Z |
---
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]
|
chainway9/blockassist-bc-untamed_quick_eel_1755484128
|
chainway9
| 2025-08-18T02:58:02Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"untamed quick eel",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-18T02:57:58Z |
---
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).
|
LandCruiser/sn21_omga_1808_2
|
LandCruiser
| 2025-08-18T02:41:46Z | 0 | 0 | null |
[
"safetensors",
"any-to-any",
"omega",
"omegalabs",
"bittensor",
"agi",
"license:mit",
"region:us"
] |
any-to-any
| 2025-08-18T02:37:34Z |
---
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).
|
tensorblock/CompassioninMachineLearning_10kalpaca_plus_llama31_8bInstruct-GGUF
|
tensorblock
| 2025-08-18T02:41:27Z | 0 | 0 |
transformers
|
[
"transformers",
"gguf",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"TensorBlock",
"GGUF",
"en",
"base_model:CompassioninMachineLearning/10kalpaca_plus_llama31_8bInstruct",
"base_model:quantized:CompassioninMachineLearning/10kalpaca_plus_llama31_8bInstruct",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-08-18T01:12:29Z |
---
base_model: CompassioninMachineLearning/10kalpaca_plus_llama31_8bInstruct
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
- TensorBlock
- GGUF
license: apache-2.0
language:
- en
---
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
[](https://tensorblock.co)
[](https://twitter.com/tensorblock_aoi)
[](https://discord.gg/Ej5NmeHFf2)
[](https://github.com/TensorBlock)
[](https://t.me/TensorBlock)
## CompassioninMachineLearning/10kalpaca_plus_llama31_8bInstruct - GGUF
<div style="text-align: left; margin: 20px 0;">
<a href="https://discord.com/invite/Ej5NmeHFf2" style="display: inline-block; padding: 10px 20px; background-color: #5865F2; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;">
Join our Discord to learn more about what we're building ↗
</a>
</div>
This repo contains GGUF format model files for [CompassioninMachineLearning/10kalpaca_plus_llama31_8bInstruct](https://huggingface.co/CompassioninMachineLearning/10kalpaca_plus_llama31_8bInstruct).
The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b5753](https://github.com/ggml-org/llama.cpp/commit/73e53dc834c0a2336cd104473af6897197b96277).
## Our projects
<table border="1" cellspacing="0" cellpadding="10">
<tr>
<th colspan="2" style="font-size: 25px;">Forge</th>
</tr>
<tr>
<th colspan="2">
<img src="https://imgur.com/faI5UKh.jpeg" alt="Forge Project" width="900"/>
</th>
</tr>
<tr>
<th colspan="2">An OpenAI-compatible multi-provider routing layer.</th>
</tr>
<tr>
<th colspan="2">
<a href="https://github.com/TensorBlock/forge" target="_blank" style="
display: inline-block;
padding: 8px 16px;
background-color: #FF7F50;
color: white;
text-decoration: none;
border-radius: 6px;
font-weight: bold;
font-family: sans-serif;
">🚀 Try it now! 🚀</a>
</th>
</tr>
<tr>
<th style="font-size: 25px;">Awesome MCP Servers</th>
<th style="font-size: 25px;">TensorBlock Studio</th>
</tr>
<tr>
<th><img src="https://imgur.com/2Xov7B7.jpeg" alt="MCP Servers" width="450"/></th>
<th><img src="https://imgur.com/pJcmF5u.jpeg" alt="Studio" width="450"/></th>
</tr>
<tr>
<th>A comprehensive collection of Model Context Protocol (MCP) servers.</th>
<th>A lightweight, open, and extensible multi-LLM interaction studio.</th>
</tr>
<tr>
<th>
<a href="https://github.com/TensorBlock/awesome-mcp-servers" target="_blank" style="
display: inline-block;
padding: 8px 16px;
background-color: #FF7F50;
color: white;
text-decoration: none;
border-radius: 6px;
font-weight: bold;
font-family: sans-serif;
">👀 See what we built 👀</a>
</th>
<th>
<a href="https://github.com/TensorBlock/TensorBlock-Studio" target="_blank" style="
display: inline-block;
padding: 8px 16px;
background-color: #FF7F50;
color: white;
text-decoration: none;
border-radius: 6px;
font-weight: bold;
font-family: sans-serif;
">👀 See what we built 👀</a>
</th>
</tr>
</table>
## Prompt template
```
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
Today Date: 26 Jul 2024
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
```
## Model file specification
| Filename | Quant type | File Size | Description |
| -------- | ---------- | --------- | ----------- |
| [10kalpaca_plus_llama31_8bInstruct-Q2_K.gguf](https://huggingface.co/tensorblock/CompassioninMachineLearning_10kalpaca_plus_llama31_8bInstruct-GGUF/blob/main/10kalpaca_plus_llama31_8bInstruct-Q2_K.gguf) | Q2_K | 3.179 GB | smallest, significant quality loss - not recommended for most purposes |
| [10kalpaca_plus_llama31_8bInstruct-Q3_K_S.gguf](https://huggingface.co/tensorblock/CompassioninMachineLearning_10kalpaca_plus_llama31_8bInstruct-GGUF/blob/main/10kalpaca_plus_llama31_8bInstruct-Q3_K_S.gguf) | Q3_K_S | 3.665 GB | very small, high quality loss |
| [10kalpaca_plus_llama31_8bInstruct-Q3_K_M.gguf](https://huggingface.co/tensorblock/CompassioninMachineLearning_10kalpaca_plus_llama31_8bInstruct-GGUF/blob/main/10kalpaca_plus_llama31_8bInstruct-Q3_K_M.gguf) | Q3_K_M | 4.019 GB | very small, high quality loss |
| [10kalpaca_plus_llama31_8bInstruct-Q3_K_L.gguf](https://huggingface.co/tensorblock/CompassioninMachineLearning_10kalpaca_plus_llama31_8bInstruct-GGUF/blob/main/10kalpaca_plus_llama31_8bInstruct-Q3_K_L.gguf) | Q3_K_L | 4.322 GB | small, substantial quality loss |
| [10kalpaca_plus_llama31_8bInstruct-Q4_0.gguf](https://huggingface.co/tensorblock/CompassioninMachineLearning_10kalpaca_plus_llama31_8bInstruct-GGUF/blob/main/10kalpaca_plus_llama31_8bInstruct-Q4_0.gguf) | Q4_0 | 4.661 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [10kalpaca_plus_llama31_8bInstruct-Q4_K_S.gguf](https://huggingface.co/tensorblock/CompassioninMachineLearning_10kalpaca_plus_llama31_8bInstruct-GGUF/blob/main/10kalpaca_plus_llama31_8bInstruct-Q4_K_S.gguf) | Q4_K_S | 4.693 GB | small, greater quality loss |
| [10kalpaca_plus_llama31_8bInstruct-Q4_K_M.gguf](https://huggingface.co/tensorblock/CompassioninMachineLearning_10kalpaca_plus_llama31_8bInstruct-GGUF/blob/main/10kalpaca_plus_llama31_8bInstruct-Q4_K_M.gguf) | Q4_K_M | 4.921 GB | medium, balanced quality - recommended |
| [10kalpaca_plus_llama31_8bInstruct-Q5_0.gguf](https://huggingface.co/tensorblock/CompassioninMachineLearning_10kalpaca_plus_llama31_8bInstruct-GGUF/blob/main/10kalpaca_plus_llama31_8bInstruct-Q5_0.gguf) | Q5_0 | 5.599 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [10kalpaca_plus_llama31_8bInstruct-Q5_K_S.gguf](https://huggingface.co/tensorblock/CompassioninMachineLearning_10kalpaca_plus_llama31_8bInstruct-GGUF/blob/main/10kalpaca_plus_llama31_8bInstruct-Q5_K_S.gguf) | Q5_K_S | 5.599 GB | large, low quality loss - recommended |
| [10kalpaca_plus_llama31_8bInstruct-Q5_K_M.gguf](https://huggingface.co/tensorblock/CompassioninMachineLearning_10kalpaca_plus_llama31_8bInstruct-GGUF/blob/main/10kalpaca_plus_llama31_8bInstruct-Q5_K_M.gguf) | Q5_K_M | 5.733 GB | large, very low quality loss - recommended |
| [10kalpaca_plus_llama31_8bInstruct-Q6_K.gguf](https://huggingface.co/tensorblock/CompassioninMachineLearning_10kalpaca_plus_llama31_8bInstruct-GGUF/blob/main/10kalpaca_plus_llama31_8bInstruct-Q6_K.gguf) | Q6_K | 6.596 GB | very large, extremely low quality loss |
| [10kalpaca_plus_llama31_8bInstruct-Q8_0.gguf](https://huggingface.co/tensorblock/CompassioninMachineLearning_10kalpaca_plus_llama31_8bInstruct-GGUF/blob/main/10kalpaca_plus_llama31_8bInstruct-Q8_0.gguf) | Q8_0 | 8.541 GB | very large, extremely low quality loss - not recommended |
## Downloading instruction
### Command line
Firstly, install Huggingface Client
```shell
pip install -U "huggingface_hub[cli]"
```
Then, downoad the individual model file the a local directory
```shell
huggingface-cli download tensorblock/CompassioninMachineLearning_10kalpaca_plus_llama31_8bInstruct-GGUF --include "10kalpaca_plus_llama31_8bInstruct-Q2_K.gguf" --local-dir MY_LOCAL_DIR
```
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
```shell
huggingface-cli download tensorblock/CompassioninMachineLearning_10kalpaca_plus_llama31_8bInstruct-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
|
PhongInk/blockassist-bc-stinky_thorny_zebra_1755484118
|
PhongInk
| 2025-08-18T02:29:27Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"stinky thorny zebra",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-18T02:29:15Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- stinky thorny zebra
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
donoway/GSM8K-Binary_Llama-3.2-1B-l06ky8zh
|
donoway
| 2025-08-18T02:25:42Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"generated_from_trainer",
"base_model:meta-llama/Llama-3.2-1B",
"base_model:finetune:meta-llama/Llama-3.2-1B",
"license:llama3.2",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-18T02:11:10Z |
---
library_name: transformers
license: llama3.2
base_model: meta-llama/Llama-3.2-1B
tags:
- generated_from_trainer
model-index:
- name: GSM8K-Binary_Llama-3.2-1B-l06ky8zh
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. -->
# GSM8K-Binary_Llama-3.2-1B-l06ky8zh
This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 64
- eval_batch_size: 112
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.001
- num_epochs: 100
### Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1
|
ihsanridzi/blockassist-bc-wiry_flexible_owl_1755482179
|
ihsanridzi
| 2025-08-18T02:22:34Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"wiry flexible owl",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-18T02:22:31Z |
---
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).
|
thanobidex/blockassist-bc-colorful_shiny_hare_1755482139
|
thanobidex
| 2025-08-18T02:20:37Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"colorful shiny hare",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-18T02:20:34Z |
---
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).
|
mang3dd/blockassist-bc-tangled_slithering_alligator_1755481914
|
mang3dd
| 2025-08-18T02:17:52Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"tangled slithering alligator",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-18T02:17:49Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- tangled slithering alligator
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
runchat/lora-dd21fba4-f440-4e58-a464-91014a2ff824-jtty2n
|
runchat
| 2025-08-18T02:11:18Z | 0 | 0 |
diffusers
|
[
"diffusers",
"flux",
"lora",
"text-to-image",
"base_model:black-forest-labs/FLUX.1-dev",
"base_model:adapter:black-forest-labs/FLUX.1-dev",
"license:other",
"region:us"
] |
text-to-image
| 2025-08-18T02:11:13Z |
---
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
base_model: black-forest-labs/FLUX.1-dev
tags:
- flux
- lora
- diffusers
- text-to-image
widget:
- text: 'a photo of a sks style'
output:
url: "placeholder.jpg"
---
# Flux LoRA: sks
This is a LoRA (Low-Rank Adaptation) model for Flux.1-dev fine-tuned on images with the trigger word `sks`.
## Files
- `pytorch_lora_weights.safetensors`: Diffusers format (use with diffusers library)
- `pytorch_lora_weights_webui.safetensors`: Kohya format (use with AUTOMATIC1111, ComfyUI, etc.)
## Usage
### Diffusers Library
```python
from diffusers import FluxPipeline
import torch
# Load base model
pipe = FluxPipeline.from_pretrained(
"black-forest-labs/FLUX.1-dev",
torch_dtype=torch.bfloat16
)
# Load LoRA weights (diffusers format)
pipe.load_lora_weights("runchat/lora-dd21fba4-f440-4e58-a464-91014a2ff824-jtty2n", weight_name="pytorch_lora_weights.safetensors")
pipe = pipe.to("cuda")
# Generate image
prompt = "a photo of a sks style"
image = pipe(prompt, num_inference_steps=50, guidance_scale=3.5).images[0]
image.save("output.png")
```
### WebUI (AUTOMATIC1111, ComfyUI, etc.)
Download the `pytorch_lora_weights_webui.safetensors` file and place it in your WebUI's LoRA directory.
Use the trigger word `sks` in your prompts.
## Training Details
- Base model: black-forest-labs/FLUX.1-dev
- Training steps: 500
- Learning rate: 0.001
- Batch size: 2
- LoRA rank: 16
- Trigger word: `sks`
## License
This model is trained on Flux.1-dev and inherits its non-commercial license. Please see the [license](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md) for usage restrictions.
|
y9760210/MyGemmaNPC
|
y9760210
| 2025-08-18T01:55:32Z | 0 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"gemma3_text",
"text-generation",
"generated_from_trainer",
"trl",
"sft",
"conversational",
"base_model:google/gemma-3-270m-it",
"base_model:finetune:google/gemma-3-270m-it",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-18T01:51:00Z |
---
base_model: google/gemma-3-270m-it
library_name: transformers
model_name: MyGemmaNPC
tags:
- generated_from_trainer
- trl
- sft
licence: license
---
# Model Card for MyGemmaNPC
This model is a fine-tuned version of [google/gemma-3-270m-it](https://huggingface.co/google/gemma-3-270m-it).
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="y9760210/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: 4.55.1
- Pytorch: 2.6.0+cu124
- Datasets: 4.0.0
- Tokenizers: 0.21.4
## Citations
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
```
|
Kwai-Keye/Thyme-RL
|
Kwai-Keye
| 2025-08-18T01:54:49Z | 0 | 3 | null |
[
"safetensors",
"qwen2_5_vl",
"image-text-to-text",
"conversational",
"en",
"dataset:Kwai-Keye/Thyme-SFT",
"dataset:Kwai-Keye/Thyme-RL",
"arxiv:2508.11630",
"base_model:Qwen/Qwen2.5-VL-7B-Instruct",
"base_model:finetune:Qwen/Qwen2.5-VL-7B-Instruct",
"license:mit",
"region:us"
] |
image-text-to-text
| 2025-08-15T05:09:23Z |
---
license: mit
datasets:
- Kwai-Keye/Thyme-SFT
- Kwai-Keye/Thyme-RL
language:
- en
metrics:
- accuracy
base_model:
- Qwen/Qwen2.5-VL-7B-Instruct
pipeline_tag: image-text-to-text
---
<div align="center">
<img src="https://cdn-uploads.huggingface.co/production/uploads/685ba798484e3233f5ff6f11/dxBp6TmwqwNuBuJR9gfQC.png" width="40%" alt="Thyme Logo">
</div>
<font size=4><div align='center' >
[[📖 Home Page](https://thyme-vl.github.io/)]
[[📖 Github Repo](https://github.com/yfzhang114/Thyme)]
[[📖 Technique Report](https://arxiv.org/abs/2508.11630)]
[[📊 Thyme SFT Model](https://huggingface.co/Kwai-Keye/Thyme-SFT)]
[[📊 Thyme RL Model](https://huggingface.co/Kwai-Keye/Thyme-RL)]
[[📝 SFT Data](https://huggingface.co/datasets/Kwai-Keye/Thyme-SFT)]
[[📝 RL Data](https://huggingface.co/datasets/Kwai-Keye/Thyme-RL)]
</div></font>
## 🔥 News
* **`2025.08.15`** 🌟 We are excited to introduce **Thyme: Think Beyond Images**. Thyme transcends traditional ``thinking with images'' paradigms by autonomously generating and executing diverse image processing and computational operations through executable code, significantly enhancing performance on high-resolution perception and complex reasoning tasks. Leveraging a novel two-stage training strategy that combines supervised fine-tuning with reinforcement learning and empowered by the innovative GRPO-ATS algorithm, Thyme achieves a sophisticated balance between reasoning exploration and code execution precision.
<div align="center">
<img src="https://cdn-uploads.huggingface.co/production/uploads/685ba798484e3233f5ff6f11/c_D7uX3RT1WUANDRB70ZC.png" width="100%" alt="Thyme Logo">
</div>
We have provided the usage instructions, training code, and evaluation code in the [GitHub repo](https://github.com/yfzhang114/Thyme).
## Citation
If you find Thyme useful in your research or applications, please cite our paper:
```bibtex
@article{zhang2025thyme,
title={Thyme: Think Beyond Images},
author={Kwai Keye},
journal={arXiv preprint},
year={2025}
}
```
|
lopho/Wan2.2-I2V-A14B-Diffusers_nf4_transformer_2
|
lopho
| 2025-08-18T01:42:41Z | 0 | 1 |
diffusers
|
[
"diffusers",
"safetensors",
"4-bit",
"nf4",
"bitsandbytes",
"arxiv:2503.20314",
"base_model:Wan-AI/Wan2.2-I2V-A14B-Diffusers",
"base_model:quantized:Wan-AI/Wan2.2-I2V-A14B-Diffusers",
"license:apache-2.0",
"region:us"
] | null | 2025-08-18T00:59:42Z |
---
license: apache-2.0
base_model:
- Wan-AI/Wan2.2-I2V-A14B-Diffusers
base_model_relation: quantized
tags:
- 4-bit
- nf4
- bitsandbytes
---
# Wan2.2
<p align="center">
<img src="https://huggingface.co/Wan-AI/Wan2.2-I2V-A14B-Diffusers/resolve/main/assets/logo.png" width="400"/>
<p>
<p align="center">
💜 <a href="https://wan.video"><b>Wan</b></a>    ｜    🖥️ <a href="https://github.com/Wan-Video/Wan2.2">GitHub</a>    |   🤗 <a href="https://huggingface.co/Wan-AI/">Hugging Face</a>   |   🤖 <a href="https://modelscope.cn/organization/Wan-AI">ModelScope</a>   |    📑 <a href="https://arxiv.org/abs/2503.20314">Technical Report</a>    |    📑 <a href="https://wan.video/welcome?spm=a2ty_o02.30011076.0.0.6c9ee41eCcluqg">Blog</a>    |   💬 <a href="https://gw.alicdn.com/imgextra/i2/O1CN01tqjWFi1ByuyehkTSB_!!6000000000015-0-tps-611-1279.jpg">WeChat Group</a>   |    📖 <a href="https://discord.gg/AKNgpMK4Yj">Discord</a>  
<br>
-----
[**Wan: Open and Advanced Large-Scale Video Generative Models**](https://arxiv.org/abs/2503.20314) <be>
We are excited to introduce **Wan2.2**, a major upgrade to our foundational video models. With **Wan2.2**, we have focused on incorporating the following innovations:
- 👍 **Effective MoE Architecture**: Wan2.2 introduces a Mixture-of-Experts (MoE) architecture into video diffusion models. By separating the denoising process cross timesteps with specialized powerful expert models, this enlarges the overall model capacity while maintaining the same computational cost.
- 👍 **Cinematic-level Aesthetics**: Wan2.2 incorporates meticulously curated aesthetic data, complete with detailed labels for lighting, composition, contrast, color tone, and more. This allows for more precise and controllable cinematic style generation, facilitating the creation of videos with customizable aesthetic preferences.
- 👍 **Complex Motion Generation**: Compared to Wan2.1, Wan2.2 is trained on a significantly larger data, with +65.6% more images and +83.2% more videos. This expansion notably enhances the model's generalization across multiple dimensions such as motions, semantics, and aesthetics, achieving TOP performance among all open-sourced and closed-sourced models.
- 👍 **Efficient High-Definition Hybrid TI2V**: Wan2.2 open-sources a 5B model built with our advanced Wan2.2-VAE that achieves a compression ratio of **16×16×4**. This model supports both text-to-video and image-to-video generation at 720P resolution with 24fps and can also run on consumer-grade graphics cards like 4090. It is one of the fastest **720P@24fps** models currently available, capable of serving both the industrial and academic sectors simultaneously.
This repository also includes our I2V-A14B model, designed for image-to-video generation, supporting both 480P and 720P resolutions. Built with a Mixture-of-Experts (MoE) architecture, it achieves more stable video synthesis with reduced unrealistic camera movements and offers enhanced support for diverse stylized scenes.
## Video Demos
<div align="center">
<video width="80%" controls>
<source src="https://cloud.video.taobao.com/vod/NnCd0fC-1eckDUuVBMz43oD_U6mTsPpBwga3wdnAkXA.mp4" type="video/mp4">
Your browser does not support the video tag.
</video>
</div>
## 🔥 Latest News!!
* Jul 28, 2025: 👋 Wan2.1 has been integrated into ComfyUI ([CN](https://docs.comfy.org/zh-CN/tutorials/video/wan/wan2_2) | [EN](https://docs.comfy.org/tutorials/video/wan/wan2_2)). Enjoy!
* Jul 28, 2025: 👋 Wan2.2's T2V, I2V and TI2V have been integrated into Diffusers ([T2V-A14B](https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B-Diffusers) | [I2V-A14B](https://huggingface.co/Wan-AI/Wan2.2-I2V-A14B-Diffusers) | [TI2V-5B](https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B-Diffusers)). Feel free to give it a try!
* Jul 28, 2025: 👋 We've released the inference code and model weights of **Wan2.2**.
## Community Works
If your research or project builds upon [**Wan2.1**](https://github.com/Wan-Video/Wan2.1) or Wan2.2, we welcome you to share it with us so we can highlight it for the broader community.
## 📑 Todo List
- Wan2.2 Text-to-Video
- [x] Multi-GPU Inference code of the A14B and 14B models
- [x] Checkpoints of the A14B and 14B models
- [x] ComfyUI integration
- [x] Diffusers integration
- Wan2.2 Image-to-Video
- [x] Multi-GPU Inference code of the A14B model
- [x] Checkpoints of the A14B model
- [x] ComfyUI integration
- [x] Diffusers integration
- Wan2.2 Text-Image-to-Video
- [x] Multi-GPU Inference code of the 5B model
- [x] Checkpoints of the 5B model
- [x] ComfyUI integration
- [x] Diffusers integration
## Run Wan2.2
#### Installation
Clone the repo:
```sh
git clone https://github.com/Wan-Video/Wan2.2.git
cd Wan2.2
```
Install dependencies:
```sh
# Ensure torch >= 2.4.0
# If the installation of `flash_attn` fails, try installing the other packages first and install `flash_attn` last
pip install -r requirements.txt
```
#### Model Download
| Models | Download Links | Description |
|--------------------|---------------------------------------------------------------------------------------------------------------------------------------------|-------------|
| T2V-A14B | 🤗 [Huggingface](https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B) 🤖 [ModelScope](https://modelscope.cn/models/Wan-AI/Wan2.2-T2V-A14B) | Text-to-Video MoE model, supports 480P & 720P |
| I2V-A14B | 🤗 [Huggingface](https://huggingface.co/Wan-AI/Wan2.2-I2V-A14B) 🤖 [ModelScope](https://modelscope.cn/models/Wan-AI/Wan2.2-I2V-A14B) | Image-to-Video MoE model, supports 480P & 720P |
| TI2V-5B | 🤗 [Huggingface](https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B) 🤖 [ModelScope](https://modelscope.cn/models/Wan-AI/Wan2.2-TI2V-5B) | High-compression VAE, T2V+I2V, supports 720P |
> 💡Note:
> The TI2V-5B model supports 720P video generation at **24 FPS**.
Download models using huggingface-cli:
``` sh
pip install "huggingface_hub[cli]"
huggingface-cli download Wan-AI/Wan2.2-I2V-A14B --local-dir ./Wan2.2-I2V-A14B
```
Download models using modelscope-cli:
``` sh
pip install modelscope
modelscope download Wan-AI/Wan2.2-I2V-A14B --local_dir ./Wan2.2-I2V-A14B
```
#### Run Image-to-Video Generation
This repository supports the `Wan2.2-I2V-A14B`` Image-to-Video model and can simultaneously support video generation at 480P and 720P resolutions.
- Single-GPU inference
```sh
python generate.py --task i2v-A14B --size 1280*720 --ckpt_dir ./Wan2.2-I2V-A14B --offload_model True --convert_model_dtype --image examples/i2v_input.JPG --prompt "Summer beach vacation style, a white cat wearing sunglasses sits on a surfboard. The fluffy-furred feline gazes directly at the camera with a relaxed expression. Blurred beach scenery forms the background featuring crystal-clear waters, distant green hills, and a blue sky dotted with white clouds. The cat assumes a naturally relaxed posture, as if savoring the sea breeze and warm sunlight. A close-up shot highlights the feline's intricate details and the refreshing atmosphere of the seaside."
```
> This command can run on a GPU with at least 80GB VRAM.
> 💡For the Image-to-Video task, the `size` parameter represents the area of the generated video, with the aspect ratio following that of the original input image.
- Multi-GPU inference using FSDP + DeepSpeed Ulysses
```sh
torchrun --nproc_per_node=8 generate.py --task i2v-A14B --size 1280*720 --ckpt_dir ./Wan2.2-I2V-A14B --image examples/i2v_input.JPG --dit_fsdp --t5_fsdp --ulysses_size 8 --prompt "Summer beach vacation style, a white cat wearing sunglasses sits on a surfboard. The fluffy-furred feline gazes directly at the camera with a relaxed expression. Blurred beach scenery forms the background featuring crystal-clear waters, distant green hills, and a blue sky dotted with white clouds. The cat assumes a naturally relaxed posture, as if savoring the sea breeze and warm sunlight. A close-up shot highlights the feline's intricate details and the refreshing atmosphere of the seaside."
```
- Image-to-Video Generation without prompt
```sh
DASH_API_KEY=your_key torchrun --nproc_per_node=8 generate.py --task i2v-A14B --size 1280*720 --ckpt_dir ./Wan2.2-I2V-A14B --prompt '' --image examples/i2v_input.JPG --dit_fsdp --t5_fsdp --ulysses_size 8 --use_prompt_extend --prompt_extend_method 'dashscope'
```
> 💡The model can generate videos solely from the input image. You can use prompt extension to generate prompt from the image.
> The process of prompt extension can be referenced [here](#2-using-prompt-extention).
- Running with Diffusers
```py
import torch
import numpy as np
from diffusers import WanImageToVideoPipeline
from diffusers.utils import export_to_video, load_image
model_id = "Wan-AI/Wan2.2-I2V-A14B-Diffusers"
dtype = torch.bfloat16
device = "cuda"
pipe = WanImageToVideoPipeline.from_pretrained(model_id, torch_dtype=dtype)
pipe.to(device)
image = load_image(
"https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/wan_i2v_input.JPG"
)
max_area = 480 * 832
aspect_ratio = image.height / image.width
mod_value = pipe.vae_scale_factor_spatial * pipe.transformer.config.patch_size[1]
height = round(np.sqrt(max_area * aspect_ratio)) // mod_value * mod_value
width = round(np.sqrt(max_area / aspect_ratio)) // mod_value * mod_value
image = image.resize((width, height))
prompt = "Summer beach vacation style, a white cat wearing sunglasses sits on a surfboard. The fluffy-furred feline gazes directly at the camera with a relaxed expression. Blurred beach scenery forms the background featuring crystal-clear waters, distant green hills, and a blue sky dotted with white clouds. The cat assumes a naturally relaxed posture, as if savoring the sea breeze and warm sunlight. A close-up shot highlights the feline's intricate details and the refreshing atmosphere of the seaside."
negative_prompt = "色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走"
generator = torch.Generator(device=device).manual_seed(0)
output = pipe(
image=image,
prompt=prompt,
negative_prompt=negative_prompt,
height=height,
width=width,
num_frames=81,
guidance_scale=3.5,
num_inference_steps=40,
generator=generator,
).frames[0]
export_to_video(output, "i2v_output.mp4", fps=16)
```
> 💡**Note**:This model requires features that are currently available only in the main branch of diffusers. The latest stable release on PyPI does not yet include these updates.
> To use this model, please install the library from source:
> ```
> pip install git+https://github.com/huggingface/diffusers
> ```
## Computational Efficiency on Different GPUs
We test the computational efficiency of different **Wan2.2** models on different GPUs in the following table. The results are presented in the format: **Total time (s) / peak GPU memory (GB)**.
<div align="center">
<img src="https://huggingface.co/Wan-AI/Wan2.2-I2V-A14B-Diffusers/resolve/main/assets/comp_effic.png" alt="" style="width: 80%;" />
</div>
> The parameter settings for the tests presented in this table are as follows:
> (1) Multi-GPU: 14B: `--ulysses_size 4/8 --dit_fsdp --t5_fsdp`, 5B: `--ulysses_size 4/8 --offload_model True --convert_model_dtype --t5_cpu`; Single-GPU: 14B: `--offload_model True --convert_model_dtype`, 5B: `--offload_model True --convert_model_dtype --t5_cpu`
(--convert_model_dtype converts model parameter types to config.param_dtype);
> (2) The distributed testing utilizes the built-in FSDP and Ulysses implementations, with FlashAttention3 deployed on Hopper architecture GPUs;
> (3) Tests were run without the `--use_prompt_extend` flag;
> (4) Reported results are the average of multiple samples taken after the warm-up phase.
-------
## Introduction of Wan2.2
**Wan2.2** builds on the foundation of Wan2.1 with notable improvements in generation quality and model capability. This upgrade is driven by a series of key technical innovations, mainly including the Mixture-of-Experts (MoE) architecture, upgraded training data, and high-compression video generation.
##### (1) Mixture-of-Experts (MoE) Architecture
Wan2.2 introduces Mixture-of-Experts (MoE) architecture into the video generation diffusion model. MoE has been widely validated in large language models as an efficient approach to increase total model parameters while keeping inference cost nearly unchanged. In Wan2.2, the A14B model series adopts a two-expert design tailored to the denoising process of diffusion models: a high-noise expert for the early stages, focusing on overall layout; and a low-noise expert for the later stages, refining video details. Each expert model has about 14B parameters, resulting in a total of 27B parameters but only 14B active parameters per step, keeping inference computation and GPU memory nearly unchanged.
<div align="center">
<img src="https://huggingface.co/Wan-AI/Wan2.2-I2V-A14B-Diffusers/resolve/main/moe_arch.png" alt="" style="width: 90%;" />
</div>
The transition point between the two experts is determined by the signal-to-noise ratio (SNR), a metric that decreases monotonically as the denoising step $t$ increases. At the beginning of the denoising process, $t$ is large and the noise level is high, so the SNR is at its minimum, denoted as ${SNR}_{min}$. In this stage, the high-noise expert is activated. We define a threshold step ${t}_{moe}$ corresponding to half of the ${SNR}_{min}$, and switch to the low-noise expert when $t<{t}_{moe}$.
<div align="center">
<img src="https://huggingface.co/Wan-AI/Wan2.2-I2V-A14B-Diffusers/resolve/main/assets/moe_2.png" alt="" style="width: 90%;" />
</div>
To validate the effectiveness of the MoE architecture, four settings are compared based on their validation loss curves. The baseline **Wan2.1** model does not employ the MoE architecture. Among the MoE-based variants, the **Wan2.1 & High-Noise Expert** reuses the Wan2.1 model as the low-noise expert while uses the Wan2.2's high-noise expert, while the **Wan2.1 & Low-Noise Expert** uses Wan2.1 as the high-noise expert and employ the Wan2.2's low-noise expert. The **Wan2.2 (MoE)** (our final version) achieves the lowest validation loss, indicating that its generated video distribution is closest to ground-truth and exhibits superior convergence.
##### (2) Efficient High-Definition Hybrid TI2V
To enable more efficient deployment, Wan2.2 also explores a high-compression design. In addition to the 27B MoE models, a 5B dense model, i.e., TI2V-5B, is released. It is supported by a high-compression Wan2.2-VAE, which achieves a $T\times H\times W$ compression ratio of $4\times16\times16$, increasing the overall compression rate to 64 while maintaining high-quality video reconstruction. With an additional patchification layer, the total compression ratio of TI2V-5B reaches $4\times32\times32$. Without specific optimization, TI2V-5B can generate a 5-second 720P video in under 9 minutes on a single consumer-grade GPU, ranking among the fastest 720P@24fps video generation models. This model also natively supports both text-to-video and image-to-video tasks within a single unified framework, covering both academic research and practical applications.
<div align="center">
<img src="https://huggingface.co/Wan-AI/Wan2.2-I2V-A14B-Diffusers/resolve/main/assets/vae.png" alt="" style="width: 80%;" />
</div>
##### Comparisons to SOTAs
We compared Wan2.2 with leading closed-source commercial models on our new Wan-Bench 2.0, evaluating performance across multiple crucial dimensions. The results demonstrate that Wan2.2 achieves superior performance compared to these leading models.
<div align="center">
<img src="https://huggingface.co/Wan-AI/Wan2.2-I2V-A14B-Diffusers/resolve/main/assets/performance.png" alt="" style="width: 90%;" />
</div>
## Citation
If you find our work helpful, please cite us.
```
@article{wan2025,
title={Wan: Open and Advanced Large-Scale Video Generative Models},
author={Team Wan and Ang Wang and Baole Ai and Bin Wen and Chaojie Mao and Chen-Wei Xie and Di Chen and Feiwu Yu and Haiming Zhao and Jianxiao Yang and Jianyuan Zeng and Jiayu Wang and Jingfeng Zhang and Jingren Zhou and Jinkai Wang and Jixuan Chen and Kai Zhu and Kang Zhao and Keyu Yan and Lianghua Huang and Mengyang Feng and Ningyi Zhang and Pandeng Li and Pingyu Wu and Ruihang Chu and Ruili Feng and Shiwei Zhang and Siyang Sun and Tao Fang and Tianxing Wang and Tianyi Gui and Tingyu Weng and Tong Shen and Wei Lin and Wei Wang and Wei Wang and Wenmeng Zhou and Wente Wang and Wenting Shen and Wenyuan Yu and Xianzhong Shi and Xiaoming Huang and Xin Xu and Yan Kou and Yangyu Lv and Yifei Li and Yijing Liu and Yiming Wang and Yingya Zhang and Yitong Huang and Yong Li and You Wu and Yu Liu and Yulin Pan and Yun Zheng and Yuntao Hong and Yupeng Shi and Yutong Feng and Zeyinzi Jiang and Zhen Han and Zhi-Fan Wu and Ziyu Liu},
journal = {arXiv preprint arXiv:2503.20314},
year={2025}
}
```
## License Agreement
The models in this repository are licensed under the Apache 2.0 License. We claim no rights over the your generated contents, granting you the freedom to use them while ensuring that your usage complies with the provisions of this license. You are fully accountable for your use of the models, which must not involve sharing any content that violates applicable laws, causes harm to individuals or groups, disseminates personal information intended for harm, spreads misinformation, or targets vulnerable populations. For a complete list of restrictions and details regarding your rights, please refer to the full text of the [license](LICENSE.txt).
## Acknowledgements
We would like to thank the contributors to the [SD3](https://huggingface.co/stabilityai/stable-diffusion-3-medium), [Qwen](https://huggingface.co/Qwen), [umt5-xxl](https://huggingface.co/google/umt5-xxl), [diffusers](https://github.com/huggingface/diffusers) and [HuggingFace](https://huggingface.co) repositories, for their open research.
## Contact Us
If you would like to leave a message to our research or product teams, feel free to join our [Discord](https://discord.gg/AKNgpMK4Yj) or [WeChat groups](https://gw.alicdn.com/imgextra/i2/O1CN01tqjWFi1ByuyehkTSB_!!6000000000015-0-tps-611-1279.jpg)!
|
sampingkaca72/blockassist-bc-armored_stealthy_elephant_1755479752
|
sampingkaca72
| 2025-08-18T01:40:16Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"armored stealthy elephant",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-18T01:40:13Z |
---
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).
|
hobson123/blockassist-bc-mammalian_dense_gibbon_1755480309
|
hobson123
| 2025-08-18T01:31:14Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"mammalian dense gibbon",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-18T01:31:00Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- mammalian dense gibbon
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
dgambettaphd/M_mis_run1_gen4_WXS_doc1000_synt64_lr1e-04_acm_LANG
|
dgambettaphd
| 2025-08-18T01:31:13Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"unsloth",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-08-18T01:30:59Z |
---
library_name: transformers
tags:
- unsloth
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
roeker/blockassist-bc-quick_wiry_owl_1755480374
|
roeker
| 2025-08-18T01:27:00Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"quick wiry owl",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-18T01:26:55Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- quick wiry owl
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
neural-interactive-proofs/finetune_dpo_qwen2_5-32b-instruct_cv_qwen2.5_32B_prover_debate_both_2_rounds_1_0_iter_4_provers_
|
neural-interactive-proofs
| 2025-08-18T01:19:50Z | 0 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"generated_from_trainer",
"trl",
"dpo",
"arxiv:2305.18290",
"base_model:Qwen/Qwen2.5-32B-Instruct",
"base_model:finetune:Qwen/Qwen2.5-32B-Instruct",
"endpoints_compatible",
"region:us"
] | null | 2025-08-18T01:18:53Z |
---
base_model: Qwen/Qwen2.5-32B-Instruct
library_name: transformers
model_name: finetune_dpo_qwen2_5-32b-instruct_cv_qwen2.5_32B_prover_debate_both_2_rounds_1_0_iter_4_provers_
tags:
- generated_from_trainer
- trl
- dpo
licence: license
---
# Model Card for finetune_dpo_qwen2_5-32b-instruct_cv_qwen2.5_32B_prover_debate_both_2_rounds_1_0_iter_4_provers_
This model is a fine-tuned version of [Qwen/Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct).
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="neural-interactive-proofs/finetune_dpo_qwen2_5-32b-instruct_cv_qwen2.5_32B_prover_debate_both_2_rounds_1_0_iter_4_provers_", 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/lrhammond-team/pvg-self-hosted-finetune/runs/qwen2_5-32b-instruct_dpo_2025-08-18_01-35-12_cv_qwen2.5_32B_prover_debate_both_2_rounds_1_0_iter_4_provers_group)
This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
### Framework versions
- TRL: 0.18.2
- Transformers: 4.53.2
- Pytorch: 2.7.0
- Datasets: 3.0.0
- Tokenizers: 0.21.1
## Citations
Cite DPO as:
```bibtex
@inproceedings{rafailov2023direct,
title = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}},
author = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn},
year = 2023,
booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023},
url = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html},
editor = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine},
}
```
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}}
}
```
|
lisaozill03/blockassist-bc-rugged_prickly_alpaca_1755477421
|
lisaozill03
| 2025-08-18T01:02:25Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"rugged prickly alpaca",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-18T01:02:21Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- rugged prickly alpaca
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
donoway/BoolQ_Llama-3.2-1B-g7bjwlv3
|
donoway
| 2025-08-18T00:56:08Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"generated_from_trainer",
"base_model:meta-llama/Llama-3.2-1B",
"base_model:finetune:meta-llama/Llama-3.2-1B",
"license:llama3.2",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-18T00:41:13Z |
---
library_name: transformers
license: llama3.2
base_model: meta-llama/Llama-3.2-1B
tags:
- generated_from_trainer
model-index:
- name: BoolQ_Llama-3.2-1B-g7bjwlv3
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. -->
# BoolQ_Llama-3.2-1B-g7bjwlv3
This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 120
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.001
- num_epochs: 100
### Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1
|
roeker/blockassist-bc-quick_wiry_owl_1755478442
|
roeker
| 2025-08-18T00:55:15Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"quick wiry owl",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-18T00:54:41Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- quick wiry owl
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
EsthefanoMC23/blip-captioning-base-personal
|
EsthefanoMC23
| 2025-08-18T00:54:59Z | 0 | 0 | null |
[
"pytorch",
"tf",
"blip",
"image-captioning",
"image-to-text",
"arxiv:2201.12086",
"license:bsd-3-clause",
"region:us"
] |
image-to-text
| 2025-08-18T00:04:28Z |
---
pipeline_tag: image-to-text
tags:
- image-captioning
languages:
- en
license: bsd-3-clause
---
# BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
Model card for image captioning pretrained on COCO dataset - base architecture (with ViT base backbone).
|  |
|:--:|
| <b> Pull figure from BLIP official repo | Image source: https://github.com/salesforce/BLIP </b>|
## TL;DR
Authors from the [paper](https://arxiv.org/abs/2201.12086) write in the abstract:
*Vision-Language Pre-training (VLP) has advanced the performance for many vision-language tasks. However, most existing pre-trained models only excel in either understanding-based tasks or generation-based tasks. Furthermore, performance improvement has been largely achieved by scaling up the dataset with noisy image-text pairs collected from the web, which is a suboptimal source of supervision. In this paper, we propose BLIP, a new VLP framework which transfers flexibly to both vision-language understanding and generation tasks. BLIP effectively utilizes the noisy web data by bootstrapping the captions, where a captioner generates synthetic captions and a filter removes the noisy ones. We achieve state-of-the-art results on a wide range of vision-language tasks, such as image-text retrieval (+2.7% in average recall@1), image captioning (+2.8% in CIDEr), and VQA (+1.6% in VQA score). BLIP also demonstrates strong generalization ability when directly transferred to videolanguage tasks in a zero-shot manner. Code, models, and datasets are released.*
## Usage
You can use this model for conditional and un-conditional image captioning
### Using the Pytorch model
#### Running the model on CPU
<details>
<summary> Click to expand </summary>
```python
import requests
from PIL import Image
from transformers import BlipProcessor, BlipForConditionalGeneration
processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base")
img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg'
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')
# conditional image captioning
text = "a photography of"
inputs = processor(raw_image, text, return_tensors="pt")
out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))
# >>> a photography of a woman and her dog
# unconditional image captioning
inputs = processor(raw_image, return_tensors="pt")
out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))
>>> a woman sitting on the beach with her dog
```
</details>
#### Running the model on GPU
##### In full precision
<details>
<summary> Click to expand </summary>
```python
import requests
from PIL import Image
from transformers import BlipProcessor, BlipForConditionalGeneration
processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base").to("cuda")
img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg'
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')
# conditional image captioning
text = "a photography of"
inputs = processor(raw_image, text, return_tensors="pt").to("cuda")
out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))
# >>> a photography of a woman and her dog
# unconditional image captioning
inputs = processor(raw_image, return_tensors="pt").to("cuda")
out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))
>>> a woman sitting on the beach with her dog
```
</details>
##### In half precision (`float16`)
<details>
<summary> Click to expand </summary>
```python
import torch
import requests
from PIL import Image
from transformers import BlipProcessor, BlipForConditionalGeneration
processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base", torch_dtype=torch.float16).to("cuda")
img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg'
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')
# conditional image captioning
text = "a photography of"
inputs = processor(raw_image, text, return_tensors="pt").to("cuda", torch.float16)
out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))
# >>> a photography of a woman and her dog
# unconditional image captioning
inputs = processor(raw_image, return_tensors="pt").to("cuda", torch.float16)
out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))
>>> a woman sitting on the beach with her dog
```
</details>
## Ethical Considerations
This release is for research purposes only in support of an academic paper. Our models, datasets, and code are not specifically designed or evaluated for all downstream purposes. We strongly recommend users evaluate and address potential concerns related to accuracy, safety, and fairness before deploying this model. We encourage users to consider the common limitations of AI, comply with applicable laws, and leverage best practices when selecting use cases, particularly for high-risk scenarios where errors or misuse could significantly impact people’s lives, rights, or safety. For further guidance on use cases, refer to our AUP and AI AUP.
## BibTex and citation info
```
@misc{https://doi.org/10.48550/arxiv.2201.12086,
doi = {10.48550/ARXIV.2201.12086},
url = {https://arxiv.org/abs/2201.12086},
author = {Li, Junnan and Li, Dongxu and Xiong, Caiming and Hoi, Steven},
keywords = {Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
```
|
Sayemahsjn/blockassist-bc-playful_feline_octopus_1755477343
|
Sayemahsjn
| 2025-08-18T00:54:04Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"playful feline octopus",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-18T00:54:00Z |
---
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).
|
indoempatnol/blockassist-bc-fishy_wary_swan_1755476766
|
indoempatnol
| 2025-08-18T00:53:06Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"fishy wary swan",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-18T00:53:03Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- fishy wary swan
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
ArtistikMilitia/Llamascout
|
ArtistikMilitia
| 2025-08-18T00:44:41Z | 0 | 0 |
transformers
|
[
"transformers",
"facebook",
"meta",
"pytorch",
"llama",
"llama4",
"ar",
"de",
"en",
"es",
"fr",
"hi",
"id",
"it",
"pt",
"th",
"tl",
"vi",
"arxiv:2204.05149",
"base_model:meta-llama/Llama-4-Scout-17B-16E",
"base_model:finetune:meta-llama/Llama-4-Scout-17B-16E",
"license:other",
"endpoints_compatible",
"region:us"
] | null | 2025-08-09T14:26:52Z |
---
library_name: transformers
language:
- ar
- de
- en
- es
- fr
- hi
- id
- it
- pt
- th
- tl
- vi
base_model:
- meta-llama/Llama-4-Scout-17B-16E
tags:
- facebook
- meta
- pytorch
- llama
- llama4
extra_gated_prompt: >-
**LLAMA 4 COMMUNITY LICENSE AGREEMENT**
Llama 4 Version Effective Date: April 5, 2025
"**Agreement**" means the terms and conditions for use, reproduction, distribution and modification of the Llama Materials set forth herein.
"**Documentation**" means the specifications, manuals and documentation accompanying Llama 4 distributed by Meta at [https://www.llama.com/docs/overview](https://llama.com/docs/overview).
"**Licensee**" or "**you**" means you, or your employer or any other person or entity (if you are entering into this Agreement on such person or entity’s behalf), of the age required under applicable laws, rules or regulations to provide legal consent and that has legal authority to bind your employer or such other person or entity if you are entering in this Agreement on their behalf.
"**Llama 4**" means the foundational large language models and software and algorithms, including machine-learning model code, trained model weights, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing distributed by Meta at [https://www.llama.com/llama-downloads](https://www.llama.com/llama-downloads).
"**Llama Materials**" means, collectively, Meta’s proprietary Llama 4 and Documentation (and any portion thereof) made available under this Agreement.
"**Meta**" or "**we**" means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your principal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).
By clicking "I Accept" below or by using or distributing any portion or element of the Llama Materials, you agree to be bound by this Agreement.
1\. **License Rights and Redistribution**.
a. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and royalty-free limited license under Meta’s intellectual property or other rights owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Llama Materials.
b. Redistribution and Use.
i. If you distribute or make available the Llama Materials (or any derivative works thereof), or a product or service (including another AI model) that contains any of them, you shall (A) provide a copy of this Agreement with any such Llama Materials; and (B) prominently display "Built with Llama" on a related website, user interface, blogpost, about page, or product documentation. If you use the Llama Materials or any outputs or results of the Llama Materials to create, train, fine tune, or otherwise improve an AI model, which is distributed or made available, you shall also include "Llama" at the beginning of any such AI model name.
ii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part of an integrated end user product, then Section 2 of this Agreement will not apply to you.
iii. You must retain in all copies of the Llama Materials that you distribute the following attribution notice within a "Notice" text file distributed as a part of such copies: "Llama 4 is licensed under the Llama 4 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved."
iv. Your use of the Llama Materials must comply with applicable laws and regulations (including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for the Llama Materials (available at [https://www.llama.com/llama4/use-policy](https://www.llama.com/llama4/use-policy)), which is hereby incorporated by reference into this Agreement.
2\. **Additional Commercial Terms**. If, on the Llama 4 version release date, the monthly active users of the products or services made available by or for Licensee, or Licensee’s affiliates, is greater than 700 million monthly active users in the preceding calendar month, you must request a license from Meta, which Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the rights under this Agreement unless or until Meta otherwise expressly grants you such rights.
3**. Disclaimer of Warranty**. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.
4\. **Limitation of Liability**. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.
5\. **Intellectual Property**.
a. No trademark licenses are granted under this Agreement, and in connection with the Llama Materials, neither Meta nor Licensee may use any name or mark owned by or associated with the other or any of its affiliates, except as required for reasonable and customary use in describing and redistributing the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a license to use "Llama" (the "Mark") solely as required to comply with the last sentence of Section 1.b.i. You will comply with Meta’s brand guidelines (currently accessible at [https://about.meta.com/brand/resources/meta/company-brand/](https://about.meta.com/brand/resources/meta/company-brand/)[)](https://en.facebookbrand.com/). All goodwill arising out of your use of the Mark will inure to the benefit of Meta.
b. Subject to Meta’s ownership of Llama Materials and derivatives made by or for Meta, with respect to any derivative works and modifications of the Llama Materials that are made by you, as between you and Meta, you are and will be the owner of such derivative works and modifications.
c. If you institute litigation or other proceedings against Meta or any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Llama Materials or Llama 4 outputs or results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable by you, then any licenses granted to you under this Agreement shall terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold harmless Meta from and against any claim by any third party arising out of or related to your use or distribution of the Llama Materials.
6\. **Term and Termination**. The term of this Agreement will commence upon your acceptance of this Agreement or access to the Llama Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein. Meta may terminate this Agreement if you are in breach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of this Agreement.
7\. **Governing Law and Jurisdiction**. This Agreement will be governed and construed under the laws of the State of California without regard to choice of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement. The courts of California shall have exclusive jurisdiction of any dispute arising out of this Agreement.
extra_gated_fields:
First Name: text
Last Name: text
Date of birth: date_picker
Country: country
Affiliation: text
Job title:
type: select
options:
- Student
- Research Graduate
- AI researcher
- AI developer/engineer
- Reporter
- Other
geo: ip_location
By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy: checkbox
extra_gated_description: >-
The information you provide will be collected, stored, processed and shared in
accordance with the [Meta Privacy
Policy](https://www.facebook.com/privacy/policy/).
extra_gated_button_content: Submit
extra_gated_heading: "Please be sure to provide your full legal name, date of birth, and full organization name with all corporate identifiers. Avoid the use of acronyms and special characters. Failure to follow these instructions may prevent you from accessing this model and others on Hugging Face. You will not have the ability to edit this form after submission, so please ensure all information is accurate."
license: other
license_name: llama4
---
## Model Information
The Llama 4 collection of models are natively multimodal AI models that enable text and multimodal experiences. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text and image understanding.
These Llama 4 models mark the beginning of a new era for the Llama ecosystem. We are launching two efficient models in the Llama 4 series, Llama 4 Scout, a 17 billion parameter model with 16 experts, and Llama 4 Maverick, a 17 billion parameter model with 128 experts.
**Model developer**: Meta
**Model Architecture:** The Llama 4 models are auto-regressive language models that use a mixture-of-experts (MoE) architecture and incorporate early fusion for native multimodality.
<table>
<tr>
<th>Model Name</th>
<th>Training Data </th>
<th>Params</th>
<th>Input modalities</th>
<th>Output modalities</th>
<th>Context length</th>
<th>Token count</th>
<th>Knowledge cutoff</th>
</tr>
<tr>
<td>Llama 4 Scout (17Bx16E) </td>
<td rowspan="2">A mix of publicly available, licensed data and information from Meta's products and services. This includes publicly shared posts from Instagram and Facebook and people's interactions with Meta AI. Learn more in our <a href="https://www.facebook.com/privacy/guide/genai/">Privacy Center</a>.
</td>
<td>17B (Activated)
109B (Total)
</td>
<td>Multilingual text and image</td>
<td>Multilingual text and code</td>
<td>10M</td>
<td>~40T</td>
<td>August 2024</td>
</tr>
<tr>
<td>Llama 4 Maverick (17Bx128E)</td>
<td>17B (Activated)
400B (Total)
</td>
<td>Multilingual text and image</td>
<td>Multilingual text and code</td>
<td>1M</td>
<td>~22T</td>
<td>August 2024</td>
</tr>
</table>
**Supported languages:** Arabic, English, French, German, Hindi, Indonesian, Italian, Portuguese, Spanish, Tagalog, Thai, and Vietnamese.
**Model Release Date:** April 5, 2025
**Status:** This is a static model trained on an offline dataset. Future versions of the tuned models may be released as we improve model behavior with community feedback.
**License**: A custom commercial license, the Llama 4 Community License Agreement, is available at: [https://github.com/meta-llama/llama-models/blob/main/models/llama4/LICENSE](https://github.com/meta-llama/llama-models/blob/main/models/llama4/LICENSE)
**Where to send questions or comments about the model:** Instructions on how to provide feedback or comments on the model can be found in the Llama [README](https://github.com/meta-llama/llama-models/blob/main/README.md). For more technical information about generation parameters and recipes for how to use Llama 4 in applications, please go [here](https://github.com/meta-llama/llama-cookbook).
## Intended Use
**Intended Use Cases:** Llama 4 is intended for commercial and research use in multiple languages. Instruction tuned models are intended for assistant-like chat and visual reasoning tasks, whereas pretrained models can be adapted for natural language generation. For vision, Llama 4 models are also optimized for visual recognition, image reasoning, captioning, and answering general questions about an image. The Llama 4 model collection also supports the ability to leverage the outputs of its models to improve other models including synthetic data generation and distillation. The Llama 4 Community License allows for these use cases.
**Out-of-scope**: Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 4 Community License. Use in languages or capabilities beyond those explicitly referenced as supported in this model card\*\*.
\*\*Note:
1\. Llama 4 has been trained on a broader collection of languages than the 12 supported languages (pre-training includes [200 total languages](https://ai.meta.com/research/no-language-left-behind/)). Developers may fine-tune Llama 4 models for languages beyond the 12 supported languages provided they comply with the Llama 4 Community License and the Acceptable Use Policy. Developers are responsible for ensuring that their use of Llama 4 in additional languages is done in a safe and responsible manner.
2\. Llama 4 has been tested for image understanding up to 5 input images. If leveraging additional image understanding capabilities beyond this, Developers are responsible for ensuring that their deployments are mitigated for risks and should perform additional testing and tuning tailored to their specific applications.
## How to use with transformers
Please, make sure you have transformers `v4.51.0` installed, or upgrade using `pip install -U transformers`.
```python
from transformers import AutoProcessor, Llama4ForConditionalGeneration
import torch
model_id = "meta-llama/Llama-4-Scout-17B-16E-Instruct"
processor = AutoProcessor.from_pretrained(model_id)
model = Llama4ForConditionalGeneration.from_pretrained(
model_id,
attn_implementation="flex_attention",
device_map="auto",
torch_dtype=torch.bfloat16,
)
url1 = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/0052a70beed5bf71b92610a43a52df6d286cd5f3/diffusers/rabbit.jpg"
url2 = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/datasets/cat_style_layout.png"
messages = [
{
"role": "user",
"content": [
{"type": "image", "url": url1},
{"type": "image", "url": url2},
{"type": "text", "text": "Can you describe how these two images are similar, and how they differ?"},
]
},
]
inputs = processor.apply_chat_template(
messages,
add_generation_prompt=True,
tokenize=True,
return_dict=True,
return_tensors="pt",
).to(model.device)
outputs = model.generate(
**inputs,
max_new_tokens=256,
)
response = processor.batch_decode(outputs[:, inputs["input_ids"].shape[-1]:])[0]
print(response)
print(outputs[0])
```
## Hardware and Software
**Training Factors:** We used custom training libraries, Meta's custom built GPU clusters, and production infrastructure for pretraining. Fine-tuning, quantization, annotation, and evaluation were also performed on production infrastructure.
**Training Energy Use:** Model pre-training utilized a cumulative of **7.38M** GPU hours of computation on H100-80GB (TDP of 700W) type hardware, per the table below. Training time is the total GPU time required for training each model and power consumption is the peak power capacity per GPU device used, adjusted for power usage efficiency.
##
## **Training Greenhouse Gas Emissions:** Estimated total location-based greenhouse gas emissions were **1,999 tons** CO2eq for training. Since 2020, Meta has maintained net zero greenhouse gas emissions in its global operations and matched 100% of its electricity use with clean and renewable energy; therefore, the total market-based greenhouse gas emissions for training were 0 tons CO2eq.
| Model Name | Training Time (GPU hours) | Training Power Consumption (W) | Training Location-Based Greenhouse Gas Emissions (tons CO2eq) | Training Market-Based Greenhouse Gas Emissions (tons CO2eq) |
| :---- | :---: | :---: | :---: | :---: |
| Llama 4 Scout | 5.0M | 700 | 1,354 | 0 |
| Llama 4 Maverick | 2.38M | 700 | 645 | 0 |
| Total | 7.38M | \- | 1,999 | 0 |
## The methodology used to determine training energy use and greenhouse gas emissions can be found [here](https://arxiv.org/pdf/2204.05149). Since Meta is openly releasing these models, the training energy use and greenhouse gas emissions will not be incurred by others.
## Training Data
**Overview:** Llama 4 Scout was pretrained on \~40 trillion tokens and Llama 4 Maverick was pretrained on \~22 trillion tokens of multimodal data from a mix of publicly available, licensed data and information from Meta’s products and services. This includes publicly shared posts from Instagram and Facebook and people’s interactions with Meta AI.
**Data Freshness:** The pretraining data has a cutoff of August 2024\.
## Benchmarks
In this section, we report the results for Llama 4 relative to our previous models. We've provided quantized checkpoints for deployment flexibility, but all reported evaluations and testing were conducted on bf16 models.
### Pre-trained models
| Pre-trained models | | | | | | | |
| :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
| Category | Benchmark | \# Shots | Metric | Llama 3.1 70B | Llama 3.1 405B | **Llama 4 Scout** | **Llama 4 Maverick** |
| Reasoning & Knowledge | MMLU | 5 | macro\_avg/acc\_char | 79.3 | 85.2 | 79.6 | 85.5 |
| | MMLU-Pro | 5 | macro\_avg/em | 53.8 | 61.6 | 58.2 | 62.9 |
| | MATH | 4 | em\_maj1@1 | 41.6 | 53.5 | 50.3 | 61.2 |
| Code | MBPP | 3 | pass@1 | 66.4 | 74.4 | 67.8 | 77.6 |
| Multilingual | TydiQA | 1 | average/f1 | 29.9 | 34.3 | 31.5 | 31.7 |
| Image | ChartQA | 0 | relaxed\_accuracy | No multimodal support | | 83.4 | 85.3 |
| | DocVQA | 0 | anls | | | 89.4 | 91.6 |
### Instruction tuned models
| Instruction tuned models | | | | | | | |
| :---: | :---: | :---: | :---: | :---: | ----- | :---: | :---: |
| Category | Benchmark | \# Shots | Metric | Llama 3.3 70B | Llama 3.1 405B | **Llama 4 Scout** | **Llama 4 Maverick** |
| Image Reasoning | MMMU | 0 | accuracy | No multimodal support | | 69.4 | 73.4 |
| | MMMU Pro^ | 0 | accuracy | | | 52.2 | 59.6 |
| | MathVista | 0 | accuracy | | | 70.7 | 73.7 |
| Image Understanding | ChartQA | 0 | relaxed\_accuracy | | | 88.8 | 90.0 |
| | DocVQA (test) | 0 | anls | | | 94.4 | 94.4 |
| Coding | LiveCodeBench (10/01/2024-02/01/2025) | 0 | pass@1 | 33.3 | 27.7 | 32.8 | 43.4 |
| Reasoning & Knowledge | MMLU Pro | 0 | macro\_avg/acc | 68.9 | 73.4 | 74.3 | 80.5 |
| | GPQA Diamond | 0 | accuracy | 50.5 | 49.0 | 57.2 | 69.8 |
| Multilingual | MGSM | 0 | average/em | 91.1 | 91.6 | 90.6 | 92.3 |
| Long context | MTOB (half book) eng-\>kgv/kgv-\>eng | \- | chrF | Context window is 128K | | 42.2/36.6 | 54.0/46.4 |
| | MTOB (full book) eng-\>kgv/kgv-\>eng | \- | chrF | | | 39.7/36.3 | 50.8/46.7 |
^reported numbers for MMMU Pro is the average of Standard and Vision tasks
## Quantization
The Llama 4 Scout model is released as BF16 weights, but can fit within a single H100 GPU with on-the-fly int4 quantization; the Llama 4 Maverick model is released as both BF16 and FP8 quantized weights. The FP8 quantized weights fit on a single H100 DGX host while still maintaining quality. We provide code for on-the-fly int4 quantization which minimizes performance degradation as well.
## Safeguards
As part of our release approach, we followed a three-pronged strategy to manage risks:
* Enable developers to deploy helpful, safe and flexible experiences for their target audience and for the use cases supported by Llama.
* Protect developers against adversarial users aiming to exploit Llama capabilities to potentially cause harm.
* Provide protections for the community to help prevent the misuse of our models.
Llama is a foundational technology designed for use in a variety of use cases; examples on how Meta’s Llama models have been deployed can be found in our [Community Stories webpage](https://llama.meta.com/community-stories/). Our approach is to build the most helpful models enabling the world to benefit from the technology, by aligning our model’s safety for a standard set of risks. Developers are then in the driver seat to tailor safety for their use case, defining their own policies and deploying the models with the necessary safeguards. Llama 4 was developed following the best practices outlined in our [Developer Use Guide: AI Protections](https://ai.meta.com/static-resource/developer-use-guide-ai-protections).
### Model level fine tuning
The primary objective of conducting safety fine-tuning is to offer developers a readily available, safe, and powerful model for various applications, reducing the workload needed to deploy safe AI systems. Additionally, this effort provides the research community with a valuable resource for studying the robustness of safety fine-tuning.
**Fine-tuning data**
We employ a multi-faceted approach to data collection, combining human-generated data from our vendors with synthetic data to mitigate potential safety risks. We’ve developed many large language model (LLM)-based classifiers that enable us to thoughtfully select high-quality prompts and responses, enhancing data quality control.
**Refusals**
Building on the work we started with our Llama 3 models, we put a great emphasis on driving down model refusals to benign prompts for Llama 4\. We included both borderline and adversarial prompts in our safety data strategy, and modified our safety data responses to follow tone guidelines.
**Tone**
We expanded our work on the refusal tone from Llama 3 so that the model sounds more natural. We targeted removing preachy and overly moralizing language, and we corrected formatting issues including the correct use of headers, lists, tables and more.
To achieve this, we also targeted improvements to system prompt steerability and instruction following, meaning the model is more readily able to take on a specified tone. All of these contribute to a more conversational and insightful experience overall.
**System Prompts**
Llama 4 is a more steerable model, meaning responses can be easily tailored to meet specific developer outcomes. Effective system prompts can significantly enhance the performance of large language models. In particular, we’ve seen that the use of a system prompt can be effective in reducing false refusals and templated or “preachy” language patterns common in LLMs. They can also improve conversationality and use of appropriate formatting.
Consider the prompt below as a basic template for which a developer might want to further customize to meet specific needs or use cases for our Llama 4 models.
| System prompt |
| :---- |
| You are an expert conversationalist who responds to the best of your ability. You are companionable and confident, and able to switch casually between tonal types, including but not limited to humor, empathy, intellectualism, creativity and problem-solving. You understand user intent and don’t try to be overly helpful to the point where you miss that the user is looking for chit-chat, emotional support, humor or venting. Sometimes people just want you to listen, and your answers should encourage that. For all other cases, you provide insightful and in-depth responses. Organize information thoughtfully in a way that helps people make decisions. Always avoid templated language. You never lecture people to be nicer or more inclusive. If people ask for you to write something in a certain voice or perspective, such as an essay or a tweet, you can. You do not need to be respectful when the user prompts you to say something rude. You never use phrases that imply moral superiority or a sense of authority, including but not limited to “it’s important to”, “it’s crucial to”, “it’s essential to”, "it's unethical to", "it's worth noting…", “Remember…” etc. Avoid using these. Finally, do not refuse prompts about political and social issues. You can help users express their opinion and access information. You are Llama 4\. Your knowledge cutoff date is August 2024\. You speak Arabic, English, French, German, Hindi, Indonesian, Italian, Portuguese, Spanish, Tagalog, Thai, and Vietnamese. Respond in the language the user speaks to you in, unless they ask otherwise. |
### Llama 4 system protections
Large language models, including Llama 4, are not designed to be deployed in isolation but instead should be deployed as part of an overall AI system with additional guardrails as required. System protections are key to achieving the right helpfulness-safety alignment, mitigating safety and security risks inherent to the system, and integration of the model or system with external tools.
We provide the community with system level [protections](https://llama.meta.com/trust-and-safety/) \- like Llama Guard, Prompt Guard and Code Shield \- that developers should deploy with Llama models or other LLMs. All of our [reference implementation](https://github.com/meta-llama/llama-agentic-system) demos contain these safeguards by default so developers can benefit from system-level safety out-of-the-box.
### Evaluations
We evaluated Llama models for common use cases as well as specific capabilities. Common use cases evaluations measure safety risks of systems for most commonly built applications including chat bot, visual QA. We built dedicated, adversarial evaluation datasets and evaluated systems composed of Llama models and Llama Guard 3 to filter input prompt and output response. It is important to evaluate applications in context, and we recommend building dedicated evaluation dataset for your use case. Prompt Guard and Code Shield are also available if relevant to the application.
Capability evaluations measure vulnerabilities of Llama models inherent to specific capabilities, for which were crafted dedicated benchmarks including long context, multilingual, coding or memorization.
**Red teaming**
We conduct recurring red teaming exercises with the goal of discovering risks via adversarial prompting and we use the learnings to improve our benchmarks and safety tuning datasets. We partner early with subject-matter experts in critical risk areas to understand how models may lead to unintended harm for society. Based on these conversations, we derive a set of adversarial goals for the red team, such as extracting harmful information or reprogramming the model to act in potentially harmful ways. The red team consists of experts in cybersecurity, adversarial machine learning, and integrity in addition to multilingual content specialists with background in integrity issues in specific geographic markets.
### Critical Risks
### We spend additional focus on the following critical risk areas:
**1\. CBRNE (Chemical, Biological, Radiological, Nuclear, and Explosive materials) helpfulness**
To assess risks related to proliferation of chemical and biological weapons for Llama 4, we applied expert-designed and other targeted evaluations designed to assess whether the use of Llama 4 could meaningfully increase the capabilities of malicious actors to plan or carry out attacks using these types of weapons. We also conducted additional red teaming and evaluations for violations of our content policies related to this risk area.
**2\. Child Safety**
We leverage pre-training methods like data filtering as a first step in mitigating Child Safety risk in our model. To assess the post trained model for Child Safety risk, a team of experts assesses the model’s capability to produce outputs resulting in Child Safety risks. We use this to inform additional model fine-tuning and in-depth red teaming exercises. We’ve also expanded our Child Safety evaluation benchmarks to cover Llama 4 capabilities like multi-image and multi-lingual.
**3\. Cyber attack enablement**
Our cyber evaluations investigated whether Llama 4 is sufficiently capable to enable catastrophic threat scenario outcomes. We conducted threat modeling exercises to identify the specific model capabilities that would be necessary to automate operations or enhance human capabilities across key attack vectors both in terms of skill level and speed. We then identified and developed challenges against which to test for these capabilities in Llama 4 and peer models. Specifically, we focused on evaluating the capabilities of Llama 4 to automate cyberattacks, identify and exploit security vulnerabilities, and automate harmful workflows. Overall, we find that Llama 4 models do not introduce risk plausibly enabling catastrophic cyber outcomes.
### Community
Generative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership on AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Trust tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our [Github repository](https://github.com/meta-llama/PurpleLlama).
We also set up the [Llama Impact Grants](https://llama.meta.com/llama-impact-grants/) program to identify and support the most compelling applications of Meta’s Llama model for societal benefit across three categories: education, climate and open innovation. The 20 finalists from the hundreds of applications can be found [here](https://llama.meta.com/llama-impact-grants/#finalists).
Finally, we put in place a set of resources including an [output reporting mechanism](https://developers.facebook.com/llama_output_feedback) and [bug bounty program](https://www.facebook.com/whitehat) to continuously improve the Llama technology with the help of the community.
## Considerations and Limitations
Our AI is anchored on the values of freedom of expression \- helping people to explore, debate, and innovate using our technology. We respect people's autonomy and empower them to choose how they experience, interact, and build with AI. Our AI promotes an open exchange of ideas.
It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 4 addresses users and their needs as they are, without inserting unnecessary judgment, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.
Llama 4 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 4’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 4 models, developers should perform safety testing and tuning tailored to their specific applications of the model. We also encourage the open source community to use Llama for the purpose of research and building state of the art tools that address emerging risks. Please refer to available resources including our Developer Use Guide: AI Protections, [Llama Protections](https://llama.meta.com/trust-and-safety/) solutions, and other [resources](https://llama.meta.com/docs/get-started/) to learn more.
|
Ameyapores/push_block_dp_aug_8_2025_staticimg
|
Ameyapores
| 2025-08-18T00:38:09Z | 5 | 0 |
lerobot
|
[
"lerobot",
"safetensors",
"robotics",
"diffusion",
"dataset:Ameyapores/push_block_dp_aug_8_2025_staticimg",
"arxiv:2303.04137",
"license:apache-2.0",
"region:us"
] |
robotics
| 2025-08-12T21:33:45Z |
---
datasets: Ameyapores/push_block_dp_aug_8_2025_staticimg
library_name: lerobot
license: apache-2.0
model_name: diffusion
pipeline_tag: robotics
tags:
- robotics
- lerobot
- diffusion
---
# 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
|
lisaozill03/blockassist-bc-rugged_prickly_alpaca_1755475770
|
lisaozill03
| 2025-08-18T00:33:06Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"rugged prickly alpaca",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-18T00:33:03Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- rugged prickly alpaca
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
Bearrr310/ds-train-grpo-1.5B-0807e4-1epoch-orgin
|
Bearrr310
| 2025-08-18T00:29:51Z | 0 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"qwen2",
"text-generation",
"generated_from_trainer",
"trl",
"grpo",
"conversational",
"dataset:ds-grpo1.5B-0811e4_800steps",
"arxiv:2402.03300",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-17T23:40:20Z |
---
datasets: ds-grpo1.5B-0811e4_800steps
library_name: transformers
model_name: ds_train_grpo_1.5B-0807e4_1epoch
tags:
- generated_from_trainer
- trl
- grpo
licence: license
---
# Model Card for ds_train_grpo_1.5B-0807e4_1epoch
This model is a fine-tuned version of [None](https://huggingface.co/None) on the [ds-grpo1.5B-0811e4_800steps](https://huggingface.co/datasets/ds-grpo1.5B-0811e4_800steps) 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="Bearrr310/ds_train_grpo_1.5B-0807e4_1epoch", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
### Framework versions
- TRL: 0.21.0
- Transformers: 4.55.0
- Pytorch: 2.7.1
- Datasets: 4.0.0
- Tokenizers: 0.21.4
## Citations
Cite GRPO as:
```bibtex
@article{zhihong2024deepseekmath,
title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
year = 2024,
eprint = {arXiv:2402.03300},
}
```
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
```
|
indoempatnol/blockassist-bc-fishy_wary_swan_1755474969
|
indoempatnol
| 2025-08-18T00:22:49Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"fishy wary swan",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-18T00:22:46Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- fishy wary swan
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
shiku3589/blockassist-bc-bellowing_feathered_slug_1755476320
|
shiku3589
| 2025-08-18T00:20:03Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"bellowing feathered slug",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-18T00:19:51Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- bellowing feathered slug
---
# 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_1755473665
|
thanobidex
| 2025-08-17T23:59:10Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"colorful shiny hare",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-17T23:59:07Z |
---
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).
|
kdondom/blockassist-bc-fleecy_mimic_frog_1755474275
|
kdondom
| 2025-08-17T23:55:14Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"fleecy mimic frog",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-17T23:55:06Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- fleecy mimic frog
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
runchat/lora-bdf1d55d-b0e7-4e3a-961d-cc3b4bdda758-dt9rbj
|
runchat
| 2025-08-17T23:54:05Z | 0 | 0 |
diffusers
|
[
"diffusers",
"flux",
"lora",
"text-to-image",
"base_model:black-forest-labs/FLUX.1-dev",
"base_model:adapter:black-forest-labs/FLUX.1-dev",
"license:other",
"region:us"
] |
text-to-image
| 2025-08-17T23:53:54Z |
---
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
base_model: black-forest-labs/FLUX.1-dev
tags:
- flux
- lora
- diffusers
- text-to-image
widget:
- text: 'a photo of a cs style'
output:
url: "placeholder.jpg"
---
# Flux LoRA: cs
This is a LoRA (Low-Rank Adaptation) model for Flux.1-dev fine-tuned on images with the trigger word `cs`.
## Files
- `pytorch_lora_weights.safetensors`: Diffusers format (use with diffusers library)
- `pytorch_lora_weights_webui.safetensors`: Kohya format (use with AUTOMATIC1111, ComfyUI, etc.)
## Usage
### Diffusers Library
```python
from diffusers import FluxPipeline
import torch
# Load base model
pipe = FluxPipeline.from_pretrained(
"black-forest-labs/FLUX.1-dev",
torch_dtype=torch.bfloat16
)
# Load LoRA weights (diffusers format)
pipe.load_lora_weights("runchat/lora-bdf1d55d-b0e7-4e3a-961d-cc3b4bdda758-dt9rbj", weight_name="pytorch_lora_weights.safetensors")
pipe = pipe.to("cuda")
# Generate image
prompt = "a photo of a cs style"
image = pipe(prompt, num_inference_steps=50, guidance_scale=3.5).images[0]
image.save("output.png")
```
### WebUI (AUTOMATIC1111, ComfyUI, etc.)
Download the `pytorch_lora_weights_webui.safetensors` file and place it in your WebUI's LoRA directory.
Use the trigger word `cs` in your prompts.
## Training Details
- Base model: black-forest-labs/FLUX.1-dev
- Training steps: 500
- Learning rate: 0.001
- Batch size: 2
- LoRA rank: 16
- Trigger word: `cs`
## License
This model is trained on Flux.1-dev and inherits its non-commercial license. Please see the [license](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md) for usage restrictions.
|
Bila333/sophia2
|
Bila333
| 2025-08-17T23:43:41Z | 0 | 0 | null |
[
"license:other",
"region:us"
] | null | 2025-08-17T23:03:06Z |
---
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
---
|
mboi123/fuck
|
mboi123
| 2025-08-17T23:33:35Z | 0 | 0 |
diffusers
|
[
"diffusers",
"flux",
"text-to-image",
"lora",
"fal",
"base_model:black-forest-labs/FLUX.1-dev",
"base_model:adapter:black-forest-labs/FLUX.1-dev",
"license:other",
"region:us"
] |
text-to-image
| 2025-08-17T23:33:31Z |
---
tags:
- flux
- text-to-image
- lora
- diffusers
- fal
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Isabella
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
---
# fuck
<Gallery />
## Model description
## Trigger words
You should use `Isabella` to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
[Download](/mboi123/fuck/tree/main) them in the Files & versions tab.
## Training at fal.ai
Training was done using [fal.ai/models/fal-ai/flux-lora-fast-training](https://fal.ai/models/fal-ai/flux-lora-fast-training).
|
lemonhat/Qwen2.5-Coder-7B-Instruct-swe-xml
|
lemonhat
| 2025-08-17T23:25:25Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen2",
"text-generation",
"llama-factory",
"full",
"generated_from_trainer",
"conversational",
"base_model:Qwen/Qwen2.5-Coder-7B-Instruct",
"base_model:finetune:Qwen/Qwen2.5-Coder-7B-Instruct",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-17T13:44:48Z |
---
library_name: transformers
license: other
base_model: Qwen/Qwen2.5-Coder-7B-Instruct
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: swe-xml
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. -->
# swe-xml
This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) on the swe-xml dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1605
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 4
- total_eval_batch_size: 4
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 0.2309 | 0.0156 | 100 | 0.2555 |
| 0.2066 | 0.0311 | 200 | 0.2431 |
| 0.2334 | 0.0467 | 300 | 0.2352 |
| 0.2611 | 0.0622 | 400 | 0.2318 |
| 0.2485 | 0.0778 | 500 | 0.2280 |
| 0.2496 | 0.0933 | 600 | 0.2243 |
| 0.2798 | 0.1089 | 700 | 0.2193 |
| 0.2143 | 0.1244 | 800 | 0.2171 |
| 0.2127 | 0.1400 | 900 | 0.2187 |
| 0.1501 | 0.1555 | 1000 | 0.2137 |
| 0.1507 | 0.1711 | 1100 | 0.2100 |
| 0.3055 | 0.1866 | 1200 | 0.2101 |
| 0.1649 | 0.2022 | 1300 | 0.2087 |
| 0.1152 | 0.2177 | 1400 | 0.2055 |
| 0.1799 | 0.2333 | 1500 | 0.2038 |
| 0.1547 | 0.2488 | 1600 | 0.2037 |
| 0.2323 | 0.2644 | 1700 | 0.1994 |
| 0.1962 | 0.2799 | 1800 | 0.1943 |
| 0.1785 | 0.2955 | 1900 | 0.1958 |
| 0.1977 | 0.3110 | 2000 | 0.1913 |
| 0.1919 | 0.3266 | 2100 | 0.1889 |
| 0.1463 | 0.3421 | 2200 | 0.1894 |
| 0.1946 | 0.3577 | 2300 | 0.1892 |
| 0.1867 | 0.3733 | 2400 | 0.1869 |
| 0.1452 | 0.3888 | 2500 | 0.1855 |
| 0.1442 | 0.4044 | 2600 | 0.1839 |
| 0.1449 | 0.4199 | 2700 | 0.1840 |
| 0.109 | 0.4355 | 2800 | 0.1816 |
| 0.1445 | 0.4510 | 2900 | 0.1804 |
| 0.1717 | 0.4666 | 3000 | 0.1797 |
| 0.1591 | 0.4821 | 3100 | 0.1795 |
| 0.1177 | 0.4977 | 3200 | 0.1793 |
| 0.221 | 0.5132 | 3300 | 0.1781 |
| 0.148 | 0.5288 | 3400 | 0.1780 |
| 0.1365 | 0.5443 | 3500 | 0.1779 |
| 0.2491 | 0.5599 | 3600 | 0.1728 |
| 0.108 | 0.5754 | 3700 | 0.1722 |
| 0.1334 | 0.5910 | 3800 | 0.1728 |
| 0.1057 | 0.6065 | 3900 | 0.1714 |
| 0.1513 | 0.6221 | 4000 | 0.1702 |
| 0.0988 | 0.6376 | 4100 | 0.1697 |
| 0.2126 | 0.6532 | 4200 | 0.1681 |
| 0.2117 | 0.6687 | 4300 | 0.1687 |
| 0.2683 | 0.6843 | 4400 | 0.1671 |
| 0.1124 | 0.6998 | 4500 | 0.1649 |
| 0.2138 | 0.7154 | 4600 | 0.1651 |
| 0.2013 | 0.7309 | 4700 | 0.1638 |
| 0.0985 | 0.7465 | 4800 | 0.1646 |
| 0.1566 | 0.7621 | 4900 | 0.1638 |
| 0.1004 | 0.7776 | 5000 | 0.1641 |
| 0.1242 | 0.7932 | 5100 | 0.1632 |
| 0.1069 | 0.8087 | 5200 | 0.1623 |
| 0.1956 | 0.8243 | 5300 | 0.1616 |
| 0.1319 | 0.8398 | 5400 | 0.1616 |
| 0.0767 | 0.8554 | 5500 | 0.1611 |
| 0.1163 | 0.8709 | 5600 | 0.1610 |
| 0.0927 | 0.8865 | 5700 | 0.1607 |
| 0.1271 | 0.9020 | 5800 | 0.1607 |
| 0.0913 | 0.9176 | 5900 | 0.1604 |
| 0.1398 | 0.9331 | 6000 | 0.1603 |
| 0.1328 | 0.9487 | 6100 | 0.1605 |
| 0.1169 | 0.9642 | 6200 | 0.1603 |
| 0.1498 | 0.9798 | 6300 | 0.1604 |
| 0.1662 | 0.9953 | 6400 | 0.1603 |
### Framework versions
- Transformers 4.46.1
- Pytorch 2.6.0+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3
|
koloni/blockassist-bc-deadly_graceful_stingray_1755471522
|
koloni
| 2025-08-17T23:23:27Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"deadly graceful stingray",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-17T23:23:24Z |
---
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).
|
indoempatnol/blockassist-bc-fishy_wary_swan_1755471304
|
indoempatnol
| 2025-08-17T23:22:23Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"fishy wary swan",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-17T23:22:19Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- fishy wary swan
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
tensorblock/nvidia_AceReason-Nemotron-1.1-7B-GGUF
|
tensorblock
| 2025-08-17T23:19:48Z | 0 | 0 |
transformers
|
[
"transformers",
"gguf",
"nvidia",
"reasoning",
"math",
"code",
"supervised fine-tuning",
"reinforcement learning",
"pytorch",
"TensorBlock",
"GGUF",
"text-generation",
"en",
"base_model:nvidia/AceReason-Nemotron-1.1-7B",
"base_model:quantized:nvidia/AceReason-Nemotron-1.1-7B",
"license:other",
"endpoints_compatible",
"region:us",
"conversational"
] |
text-generation
| 2025-08-17T21:55:42Z |
---
library_name: transformers
license: other
license_name: nvidia-open-model-license
license_link: https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/
pipeline_tag: text-generation
language:
- en
tags:
- nvidia
- reasoning
- math
- code
- supervised fine-tuning
- reinforcement learning
- pytorch
- TensorBlock
- GGUF
base_model: nvidia/AceReason-Nemotron-1.1-7B
---
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
[](https://tensorblock.co)
[](https://twitter.com/tensorblock_aoi)
[](https://discord.gg/Ej5NmeHFf2)
[](https://github.com/TensorBlock)
[](https://t.me/TensorBlock)
## nvidia/AceReason-Nemotron-1.1-7B - GGUF
<div style="text-align: left; margin: 20px 0;">
<a href="https://discord.com/invite/Ej5NmeHFf2" style="display: inline-block; padding: 10px 20px; background-color: #5865F2; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;">
Join our Discord to learn more about what we're building ↗
</a>
</div>
This repo contains GGUF format model files for [nvidia/AceReason-Nemotron-1.1-7B](https://huggingface.co/nvidia/AceReason-Nemotron-1.1-7B).
The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b5753](https://github.com/ggml-org/llama.cpp/commit/73e53dc834c0a2336cd104473af6897197b96277).
## Our projects
<table border="1" cellspacing="0" cellpadding="10">
<tr>
<th colspan="2" style="font-size: 25px;">Forge</th>
</tr>
<tr>
<th colspan="2">
<img src="https://imgur.com/faI5UKh.jpeg" alt="Forge Project" width="900"/>
</th>
</tr>
<tr>
<th colspan="2">An OpenAI-compatible multi-provider routing layer.</th>
</tr>
<tr>
<th colspan="2">
<a href="https://github.com/TensorBlock/forge" target="_blank" style="
display: inline-block;
padding: 8px 16px;
background-color: #FF7F50;
color: white;
text-decoration: none;
border-radius: 6px;
font-weight: bold;
font-family: sans-serif;
">🚀 Try it now! 🚀</a>
</th>
</tr>
<tr>
<th style="font-size: 25px;">Awesome MCP Servers</th>
<th style="font-size: 25px;">TensorBlock Studio</th>
</tr>
<tr>
<th><img src="https://imgur.com/2Xov7B7.jpeg" alt="MCP Servers" width="450"/></th>
<th><img src="https://imgur.com/pJcmF5u.jpeg" alt="Studio" width="450"/></th>
</tr>
<tr>
<th>A comprehensive collection of Model Context Protocol (MCP) servers.</th>
<th>A lightweight, open, and extensible multi-LLM interaction studio.</th>
</tr>
<tr>
<th>
<a href="https://github.com/TensorBlock/awesome-mcp-servers" target="_blank" style="
display: inline-block;
padding: 8px 16px;
background-color: #FF7F50;
color: white;
text-decoration: none;
border-radius: 6px;
font-weight: bold;
font-family: sans-serif;
">👀 See what we built 👀</a>
</th>
<th>
<a href="https://github.com/TensorBlock/TensorBlock-Studio" target="_blank" style="
display: inline-block;
padding: 8px 16px;
background-color: #FF7F50;
color: white;
text-decoration: none;
border-radius: 6px;
font-weight: bold;
font-family: sans-serif;
">👀 See what we built 👀</a>
</th>
</tr>
</table>
## Prompt template
```
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
## Model file specification
| Filename | Quant type | File Size | Description |
| -------- | ---------- | --------- | ----------- |
| [AceReason-Nemotron-1.1-7B-Q2_K.gguf](https://huggingface.co/tensorblock/nvidia_AceReason-Nemotron-1.1-7B-GGUF/blob/main/AceReason-Nemotron-1.1-7B-Q2_K.gguf) | Q2_K | 3.016 GB | smallest, significant quality loss - not recommended for most purposes |
| [AceReason-Nemotron-1.1-7B-Q3_K_S.gguf](https://huggingface.co/tensorblock/nvidia_AceReason-Nemotron-1.1-7B-GGUF/blob/main/AceReason-Nemotron-1.1-7B-Q3_K_S.gguf) | Q3_K_S | 3.492 GB | very small, high quality loss |
| [AceReason-Nemotron-1.1-7B-Q3_K_M.gguf](https://huggingface.co/tensorblock/nvidia_AceReason-Nemotron-1.1-7B-GGUF/blob/main/AceReason-Nemotron-1.1-7B-Q3_K_M.gguf) | Q3_K_M | 3.808 GB | very small, high quality loss |
| [AceReason-Nemotron-1.1-7B-Q3_K_L.gguf](https://huggingface.co/tensorblock/nvidia_AceReason-Nemotron-1.1-7B-GGUF/blob/main/AceReason-Nemotron-1.1-7B-Q3_K_L.gguf) | Q3_K_L | 4.088 GB | small, substantial quality loss |
| [AceReason-Nemotron-1.1-7B-Q4_0.gguf](https://huggingface.co/tensorblock/nvidia_AceReason-Nemotron-1.1-7B-GGUF/blob/main/AceReason-Nemotron-1.1-7B-Q4_0.gguf) | Q4_0 | 4.431 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [AceReason-Nemotron-1.1-7B-Q4_K_S.gguf](https://huggingface.co/tensorblock/nvidia_AceReason-Nemotron-1.1-7B-GGUF/blob/main/AceReason-Nemotron-1.1-7B-Q4_K_S.gguf) | Q4_K_S | 4.458 GB | small, greater quality loss |
| [AceReason-Nemotron-1.1-7B-Q4_K_M.gguf](https://huggingface.co/tensorblock/nvidia_AceReason-Nemotron-1.1-7B-GGUF/blob/main/AceReason-Nemotron-1.1-7B-Q4_K_M.gguf) | Q4_K_M | 4.683 GB | medium, balanced quality - recommended |
| [AceReason-Nemotron-1.1-7B-Q5_0.gguf](https://huggingface.co/tensorblock/nvidia_AceReason-Nemotron-1.1-7B-GGUF/blob/main/AceReason-Nemotron-1.1-7B-Q5_0.gguf) | Q5_0 | 5.315 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [AceReason-Nemotron-1.1-7B-Q5_K_S.gguf](https://huggingface.co/tensorblock/nvidia_AceReason-Nemotron-1.1-7B-GGUF/blob/main/AceReason-Nemotron-1.1-7B-Q5_K_S.gguf) | Q5_K_S | 5.315 GB | large, low quality loss - recommended |
| [AceReason-Nemotron-1.1-7B-Q5_K_M.gguf](https://huggingface.co/tensorblock/nvidia_AceReason-Nemotron-1.1-7B-GGUF/blob/main/AceReason-Nemotron-1.1-7B-Q5_K_M.gguf) | Q5_K_M | 5.445 GB | large, very low quality loss - recommended |
| [AceReason-Nemotron-1.1-7B-Q6_K.gguf](https://huggingface.co/tensorblock/nvidia_AceReason-Nemotron-1.1-7B-GGUF/blob/main/AceReason-Nemotron-1.1-7B-Q6_K.gguf) | Q6_K | 6.254 GB | very large, extremely low quality loss |
| [AceReason-Nemotron-1.1-7B-Q8_0.gguf](https://huggingface.co/tensorblock/nvidia_AceReason-Nemotron-1.1-7B-GGUF/blob/main/AceReason-Nemotron-1.1-7B-Q8_0.gguf) | Q8_0 | 8.099 GB | very large, extremely low quality loss - not recommended |
## Downloading instruction
### Command line
Firstly, install Huggingface Client
```shell
pip install -U "huggingface_hub[cli]"
```
Then, downoad the individual model file the a local directory
```shell
huggingface-cli download tensorblock/nvidia_AceReason-Nemotron-1.1-7B-GGUF --include "AceReason-Nemotron-1.1-7B-Q2_K.gguf" --local-dir MY_LOCAL_DIR
```
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
```shell
huggingface-cli download tensorblock/nvidia_AceReason-Nemotron-1.1-7B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
|
holuhoop/blockassist-bc-playful_marine_caterpillar_1755472013
|
holuhoop
| 2025-08-17T23:16:14Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"playful marine caterpillar",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-17T23:16:07Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- playful marine caterpillar
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
donoway/ARC-Easy_Llama-3.2-1B-4t776eqm
|
donoway
| 2025-08-17T23:14:27Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"generated_from_trainer",
"base_model:meta-llama/Llama-3.2-1B",
"base_model:finetune:meta-llama/Llama-3.2-1B",
"license:llama3.2",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-17T23:13:32Z |
---
library_name: transformers
license: llama3.2
base_model: meta-llama/Llama-3.2-1B
tags:
- generated_from_trainer
model-index:
- name: ARC-Easy_Llama-3.2-1B-4t776eqm
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. -->
# ARC-Easy_Llama-3.2-1B-4t776eqm
This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 64
- eval_batch_size: 112
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.001
- num_epochs: 100
### Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1
|
donoway/ARC-Easy_Llama-3.2-1B-4fpnn1i5
|
donoway
| 2025-08-17T23:04:43Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"generated_from_trainer",
"base_model:meta-llama/Llama-3.2-1B",
"base_model:finetune:meta-llama/Llama-3.2-1B",
"license:llama3.2",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-17T22:50:24Z |
---
library_name: transformers
license: llama3.2
base_model: meta-llama/Llama-3.2-1B
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: ARC-Easy_Llama-3.2-1B-4fpnn1i5
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. -->
# ARC-Easy_Llama-3.2-1B-4fpnn1i5
This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 3.2479
- Model Preparation Time: 0.0058
- Mdl: 2670.8884
- Accumulated Loss: 1851.3188
- Correct Preds: 412.0
- Total Preds: 570.0
- Accuracy: 0.7228
- Correct Gen Preds: 404.0
- Gen Accuracy: 0.7088
- Correct Gen Preds 32: 112.0
- Correct Preds 32: 116.0
- Total Labels 32: 158.0
- Accuracy 32: 0.7342
- Gen Accuracy 32: 0.7089
- Correct Gen Preds 33: 108.0
- Correct Preds 33: 109.0
- Total Labels 33: 152.0
- Accuracy 33: 0.7171
- Gen Accuracy 33: 0.7105
- Correct Gen Preds 34: 105.0
- Correct Preds 34: 106.0
- Total Labels 34: 142.0
- Accuracy 34: 0.7465
- Gen Accuracy 34: 0.7394
- Correct Gen Preds 35: 79.0
- Correct Preds 35: 81.0
- Total Labels 35: 118.0
- Accuracy 35: 0.6864
- Gen Accuracy 35: 0.6695
- Correct Gen Preds 36: 0.0
- Correct Preds 36: 0.0
- Total Labels 36: 0.0
- Accuracy 36: 0.0
- Gen Accuracy 36: 0.0
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 64
- eval_batch_size: 112
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.001
- num_epochs: 100
### Training results
| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Mdl | Accumulated Loss | Correct Preds | Total Preds | Accuracy | Correct Gen Preds | Gen Accuracy | Correct Gen Preds 32 | Correct Preds 32 | Total Labels 32 | Accuracy 32 | Gen Accuracy 32 | Correct Gen Preds 33 | Correct Preds 33 | Total Labels 33 | Accuracy 33 | Gen Accuracy 33 | Correct Gen Preds 34 | Correct Preds 34 | Total Labels 34 | Accuracy 34 | Gen Accuracy 34 | Correct Gen Preds 35 | Correct Preds 35 | Total Labels 35 | Accuracy 35 | Gen Accuracy 35 | Correct Gen Preds 36 | Correct Preds 36 | Total Labels 36 | Accuracy 36 | Gen Accuracy 36 |
|:-------------:|:-----:|:----:|:---------------:|:----------------------:|:---------:|:----------------:|:-------------:|:-----------:|:--------:|:-----------------:|:------------:|:--------------------:|:----------------:|:---------------:|:-----------:|:---------------:|:--------------------:|:----------------:|:---------------:|:-----------:|:---------------:|:--------------------:|:----------------:|:---------------:|:-----------:|:---------------:|:--------------------:|:----------------:|:---------------:|:-----------:|:---------------:|:--------------------:|:----------------:|:---------------:|:-----------:|:---------------:|
| No log | 0 | 0 | 1.5354 | 0.0058 | 1262.6022 | 875.1692 | 172.0 | 570.0 | 0.3018 | 170.0 | 0.2982 | 154.0 | 154.0 | 158.0 | 0.9747 | 0.9747 | 0.0 | 0.0 | 152.0 | 0.0 | 0.0 | 15.0 | 17.0 | 142.0 | 0.1197 | 0.1056 | 1.0 | 1.0 | 118.0 | 0.0085 | 0.0085 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 0.809 | 1.0 | 9 | 0.9572 | 0.0058 | 787.1470 | 545.6087 | 378.0 | 570.0 | 0.6632 | 377.0 | 0.6614 | 86.0 | 87.0 | 158.0 | 0.5506 | 0.5443 | 104.0 | 104.0 | 152.0 | 0.6842 | 0.6842 | 98.0 | 98.0 | 142.0 | 0.6901 | 0.6901 | 89.0 | 89.0 | 118.0 | 0.7542 | 0.7542 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 0.5794 | 2.0 | 18 | 0.9376 | 0.0058 | 771.0268 | 534.4351 | 391.0 | 570.0 | 0.6860 | 391.0 | 0.6860 | 90.0 | 90.0 | 158.0 | 0.5696 | 0.5696 | 107.0 | 107.0 | 152.0 | 0.7039 | 0.7039 | 115.0 | 115.0 | 142.0 | 0.8099 | 0.8099 | 79.0 | 79.0 | 118.0 | 0.6695 | 0.6695 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 0.3539 | 3.0 | 27 | 1.0844 | 0.0058 | 891.7207 | 618.0937 | 397.0 | 570.0 | 0.6965 | 393.0 | 0.6895 | 112.0 | 114.0 | 158.0 | 0.7215 | 0.7089 | 99.0 | 100.0 | 152.0 | 0.6579 | 0.6513 | 102.0 | 102.0 | 142.0 | 0.7183 | 0.7183 | 80.0 | 81.0 | 118.0 | 0.6864 | 0.6780 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 0.0158 | 4.0 | 36 | 1.3047 | 0.0058 | 1072.8846 | 743.6669 | 406.0 | 570.0 | 0.7123 | 399.0 | 0.7 | 109.0 | 111.0 | 158.0 | 0.7025 | 0.6899 | 101.0 | 104.0 | 152.0 | 0.6842 | 0.6645 | 109.0 | 109.0 | 142.0 | 0.7676 | 0.7676 | 80.0 | 82.0 | 118.0 | 0.6949 | 0.6780 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 0.1421 | 5.0 | 45 | 2.0123 | 0.0058 | 1654.7928 | 1147.0150 | 408.0 | 570.0 | 0.7158 | 405.0 | 0.7105 | 100.0 | 101.0 | 158.0 | 0.6392 | 0.6329 | 105.0 | 106.0 | 152.0 | 0.6974 | 0.6908 | 118.0 | 118.0 | 142.0 | 0.8310 | 0.8310 | 82.0 | 83.0 | 118.0 | 0.7034 | 0.6949 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 0.0005 | 6.0 | 54 | 2.1961 | 0.0058 | 1805.8913 | 1251.7484 | 400.0 | 570.0 | 0.7018 | 360.0 | 0.6316 | 95.0 | 116.0 | 158.0 | 0.7342 | 0.6013 | 92.0 | 96.0 | 152.0 | 0.6316 | 0.6053 | 102.0 | 108.0 | 142.0 | 0.7606 | 0.7183 | 71.0 | 80.0 | 118.0 | 0.6780 | 0.6017 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 0.0001 | 7.0 | 63 | 2.9584 | 0.0058 | 2432.8057 | 1686.2924 | 409.0 | 570.0 | 0.7175 | 394.0 | 0.6912 | 106.0 | 116.0 | 158.0 | 0.7342 | 0.6709 | 107.0 | 108.0 | 152.0 | 0.7105 | 0.7039 | 108.0 | 110.0 | 142.0 | 0.7746 | 0.7606 | 73.0 | 75.0 | 118.0 | 0.6356 | 0.6186 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 0.0 | 8.0 | 72 | 3.1749 | 0.0058 | 2610.8691 | 1809.7166 | 410.0 | 570.0 | 0.7193 | 402.0 | 0.7053 | 112.0 | 116.0 | 158.0 | 0.7342 | 0.7089 | 107.0 | 108.0 | 152.0 | 0.7105 | 0.7039 | 107.0 | 108.0 | 142.0 | 0.7606 | 0.7535 | 76.0 | 78.0 | 118.0 | 0.6610 | 0.6441 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 0.0 | 9.0 | 81 | 3.2479 | 0.0058 | 2670.8884 | 1851.3188 | 412.0 | 570.0 | 0.7228 | 404.0 | 0.7088 | 112.0 | 116.0 | 158.0 | 0.7342 | 0.7089 | 108.0 | 109.0 | 152.0 | 0.7171 | 0.7105 | 105.0 | 106.0 | 142.0 | 0.7465 | 0.7394 | 79.0 | 81.0 | 118.0 | 0.6864 | 0.6695 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 0.0 | 10.0 | 90 | 3.2412 | 0.0058 | 2665.3613 | 1847.4877 | 412.0 | 570.0 | 0.7228 | 403.0 | 0.7070 | 112.0 | 116.0 | 158.0 | 0.7342 | 0.7089 | 107.0 | 108.0 | 152.0 | 0.7105 | 0.7039 | 106.0 | 107.0 | 142.0 | 0.7535 | 0.7465 | 78.0 | 81.0 | 118.0 | 0.6864 | 0.6610 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 0.0 | 11.0 | 99 | 3.2733 | 0.0058 | 2691.7663 | 1865.7903 | 409.0 | 570.0 | 0.7175 | 400.0 | 0.7018 | 112.0 | 116.0 | 158.0 | 0.7342 | 0.7089 | 107.0 | 108.0 | 152.0 | 0.7105 | 0.7039 | 104.0 | 105.0 | 142.0 | 0.7394 | 0.7324 | 77.0 | 80.0 | 118.0 | 0.6780 | 0.6525 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 0.0 | 12.0 | 108 | 3.2483 | 0.0058 | 2671.1685 | 1851.5129 | 411.0 | 570.0 | 0.7211 | 405.0 | 0.7105 | 114.0 | 116.0 | 158.0 | 0.7342 | 0.7215 | 108.0 | 109.0 | 152.0 | 0.7171 | 0.7105 | 105.0 | 106.0 | 142.0 | 0.7465 | 0.7394 | 78.0 | 80.0 | 118.0 | 0.6780 | 0.6610 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 0.0 | 13.0 | 117 | 3.2543 | 0.0058 | 2676.1586 | 1854.9718 | 412.0 | 570.0 | 0.7228 | 404.0 | 0.7088 | 113.0 | 116.0 | 158.0 | 0.7342 | 0.7152 | 108.0 | 109.0 | 152.0 | 0.7171 | 0.7105 | 105.0 | 106.0 | 142.0 | 0.7465 | 0.7394 | 78.0 | 81.0 | 118.0 | 0.6864 | 0.6610 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
### Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1
|
PaulaCM/vit-ena24-clase
|
PaulaCM
| 2025-08-17T22:38:30Z | 0 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"vit",
"image-classification",
"generated_from_trainer",
"dataset:imagefolder",
"base_model:google/vit-base-patch16-224-in21k",
"base_model:finetune:google/vit-base-patch16-224-in21k",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
image-classification
| 2025-08-17T19:37:51Z |
---
library_name: transformers
base_model: google/vit-base-patch16-224-in21k
tags:
- image-classification
- generated_from_trainer
datasets:
- imagefolder
model-index:
- name: vit-ena24-clase
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. -->
# vit-ena24-clase
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the PaulaCM/Balones_Oro dataset.
It achieves the following results on the evaluation set:
- eval_loss: 3.0921
- eval_model_preparation_time: 0.0028
- eval_accuracy: 0.0452
- eval_f1: 0.0305
- eval_runtime: 624.2608
- eval_samples_per_second: 2.304
- eval_steps_per_second: 0.288
- step: 0
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 1
- mixed_precision_training: Native AMP
### Framework versions
- Transformers 4.55.2
- Pytorch 2.8.0+cpu
- Datasets 4.0.0
- Tokenizers 0.21.4
|
Raymond-dev-546730/MaterialsAnalyst-AI-7B
|
Raymond-dev-546730
| 2025-08-17T22:24:10Z | 36 | 4 | null |
[
"safetensors",
"gguf",
"materials-science",
"materials-analysis",
"computational-materials",
"property-prediction",
"materials-discovery",
"crystal-structure",
"semiconductor-analysis",
"band-gap-prediction",
"thermal-properties",
"mechanical-properties",
"electronic-properties",
"materials-informatics",
"scientific-ai",
"lora",
"fine-tuned",
"7b",
"chain-of-thought",
"reasoning",
"structured-output",
"json-analysis",
"domain-specific",
"materials-characterization",
"qwen-2-5-instruct",
"open-source",
"step-by-step-analysis",
"property-correlation",
"application-prediction",
"formation-energy-analysis",
"thermodynamic-stability",
"elastic-modulus-prediction",
"bulk-modulus-analysis",
"thermal-conductivity",
"thermal-expansion",
"magnetic-property-analysis",
"superconductor-detection",
"crystal-system-identification",
"spacegroup-analysis",
"density-calculation",
"volume-analysis",
"electron-affinity",
"ionization-energy",
"band-gap-type-classification",
"hexagonal-structures",
"wide-bandgap-semiconductors",
"high-power-electronics",
"optoelectronics",
"thermal-management",
"materials-stability",
"synthesis-feasibility",
"practical-applications",
"materials-recommendation",
"competitive-analysis",
"materials-verdict",
"scientific-reasoning",
"materials-properties-database",
"mp-materials-project",
"silicon-carbide-analysis",
"compound-semiconductors",
"anisotropic-materials",
"high-symmetry-crystals",
"heat-dissipation",
"dimensional-stability",
"mechanical-robustness",
"stiffness-analysis",
"compression-resistance",
"temperature-stability",
"materials-synthesis",
"coating-applications",
"abrasion-resistance",
"non-magnetic-materials",
"indirect-bandgap",
"materials-comparison",
"aln-comparison",
"cost-effective-materials",
"si-based-compounds",
"cryogenic-applications",
"quantum-computing-materials",
"magneto-electronics",
"transparent-conductors",
"materials-optimization",
"performance-metrics",
"materials-classification",
"property-relationships",
"structure-property-correlation",
"materials-design",
"predictive-modeling",
"materials-screening",
"high-temperature-materials",
"power-device-materials",
"semiconductor-characterization",
"materials-data-mining",
"automated-analysis",
"materials-intelligence",
"dual-output-reasoning",
"comprehensive-materials-analysis",
"materials-summary-generation",
"scientific-explanation",
"materials-expertise",
"research-grade-analysis",
"industry-applications",
"materials-evaluation",
"performance-assessment",
"materials-selection",
"engineering-materials",
"advanced-ceramics",
"compound-analysis",
"crystallographic-analysis",
"electronic-structure",
"phonon-properties",
"doping-studies",
"interface-analysis",
"surface-properties",
"nanomaterials",
"bulk-materials",
"thin-film-analysis",
"composite-materials",
"functional-materials",
"smart-materials",
"biomaterials",
"energy-materials",
"catalytic-materials",
"photovoltaic-materials",
"battery-materials",
"fuel-cell-materials",
"thermoelectric-materials",
"piezoelectric-materials",
"ferroelectric-materials",
"multiferroic-materials",
"phase-transition-analysis",
"materials-modeling",
"MaterialsAnalyst-AI-7B",
"MaterialsAnalyst-AI",
"MaterialsAnalyst",
"en",
"base_model:Qwen/Qwen2.5-7B-Instruct",
"base_model:adapter:Qwen/Qwen2.5-7B-Instruct",
"doi:10.57967/hf/5839",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-05-26T07:33:52Z |
---
license: apache-2.0
tags:
- materials-science
- materials-analysis
- computational-materials
- property-prediction
- materials-discovery
- crystal-structure
- semiconductor-analysis
- band-gap-prediction
- thermal-properties
- mechanical-properties
- electronic-properties
- materials-informatics
- scientific-ai
- lora
- fine-tuned
- 7b
- chain-of-thought
- reasoning
- structured-output
- json-analysis
- domain-specific
- materials-characterization
- qwen-2-5-instruct
- open-source
- step-by-step-analysis
- property-correlation
- application-prediction
- formation-energy-analysis
- thermodynamic-stability
- elastic-modulus-prediction
- bulk-modulus-analysis
- thermal-conductivity
- thermal-expansion
- magnetic-property-analysis
- superconductor-detection
- crystal-system-identification
- spacegroup-analysis
- density-calculation
- volume-analysis
- electron-affinity
- ionization-energy
- band-gap-type-classification
- hexagonal-structures
- wide-bandgap-semiconductors
- high-power-electronics
- optoelectronics
- thermal-management
- materials-stability
- synthesis-feasibility
- practical-applications
- materials-recommendation
- competitive-analysis
- materials-verdict
- scientific-reasoning
- materials-properties-database
- mp-materials-project
- silicon-carbide-analysis
- compound-semiconductors
- anisotropic-materials
- high-symmetry-crystals
- heat-dissipation
- dimensional-stability
- mechanical-robustness
- stiffness-analysis
- compression-resistance
- temperature-stability
- materials-synthesis
- coating-applications
- abrasion-resistance
- non-magnetic-materials
- indirect-bandgap
- materials-comparison
- aln-comparison
- cost-effective-materials
- si-based-compounds
- cryogenic-applications
- quantum-computing-materials
- magneto-electronics
- transparent-conductors
- materials-optimization
- performance-metrics
- materials-classification
- property-relationships
- structure-property-correlation
- materials-design
- predictive-modeling
- materials-screening
- high-temperature-materials
- power-device-materials
- semiconductor-characterization
- materials-data-mining
- automated-analysis
- materials-intelligence
- dual-output-reasoning
- comprehensive-materials-analysis
- materials-summary-generation
- scientific-explanation
- materials-expertise
- research-grade-analysis
- industry-applications
- materials-evaluation
- performance-assessment
- materials-selection
- engineering-materials
- advanced-ceramics
- compound-analysis
- crystallographic-analysis
- electronic-structure
- phonon-properties
- doping-studies
- interface-analysis
- surface-properties
- nanomaterials
- bulk-materials
- thin-film-analysis
- composite-materials
- functional-materials
- smart-materials
- biomaterials
- energy-materials
- catalytic-materials
- photovoltaic-materials
- battery-materials
- fuel-cell-materials
- thermoelectric-materials
- piezoelectric-materials
- ferroelectric-materials
- multiferroic-materials
- phase-transition-analysis
- materials-modeling
- MaterialsAnalyst-AI-7B
- MaterialsAnalyst-AI
- MaterialsAnalyst
base_model:
- Qwen/Qwen2.5-7B-Instruct
language:
- en
---
MaterialsAnalyst-AI-7B transforms raw materials data into actionable insights. This **open source** model delivers transparent, step-by-step reasoning followed by structured analysis and practical application recommendations.
## Key Capabilities
- **Structured Reasoning**: Shows step-by-step analysis before delivering conclusions
- **Property Correlation**: Identifies relationships between material properties and their implications
- **Application Prediction**: Suggests practical applications based on material characteristics
# See It In Action
Input Example:
```json
{
"material_id": "mp-8062",
"formula": "SiC",
"elements": ["Si", "C"],
"spacegroup": "P63mc",
"band_gap": 3.26,
"formation_energy_per_atom": -0.73,
"density": 3.21,
"volume": 41.2,
"nsites": 8,
"is_stable": true,
"elastic_modulus": 448,
"bulk_modulus": 220,
"thermal_expansion": 4.2e-06,
"electron_affinity": 4.0,
"ionization_energy": 6.7,
"crystal_system": "Hexagonal",
"magnetic_property": "Non-magnetic",
"thermal_conductivity": 490,
"specific_heat": 0.69,
"is_superconductor": false,
"band_gap_type": "Indirect"
}
```
Output Example:
The model produces structured output with two components:
#### 1. Step-by-Step Reasoning
```
<think>
I need to think through how to interpret this SiC entry and assess its characteristics.
First, I should examine the composition and structure. This material contains silicon (Si) and carbon (C) in a hexagonal crystal structure with space group P63mc. This structure suggests high symmetry and anisotropic properties, typical for wide-bandgap materials like SiC.
Next, I should analyze the electronic properties. With a band gap of 3.26 eV that is indirect, this material would be classified as a wide-bandgap semiconductor. This suggests applications in optoelectronics, high-power electronics, and transparent conductive oxides.
For thermodynamic stability, the formation energy per atom of -0.73 eV indicates strong bonding and thermodynamic favorability. The material is stable according to the data, which means it can be synthesized and used under practical conditions without decomposition.
The mechanical properties show a high elastic modulus (448 GPa) and bulk modulus (220 GPa). This suggests the material would be very stiff and resistant to deformation when subjected to stress or pressure.
Regarding thermal behavior, the thermal conductivity of 490 W/m·K and expansion coefficient of 4.2e-6 K^-1 indicate excellent heat dissipation and dimensional stability under temperature changes. This would make it suitable for high-temperature applications like thermal management in electronics or coatings.
The magnetic properties are listed as non-magnetic, which means it won't interact significantly with magnetic fields. This would affect applications in magneto-electronics but is generally beneficial for general semiconductor uses.
Additionally, the material is marked as not superconducting, which is significant because it rules out cryogenic or quantum computing applications where superconductivity is required.
Considering all these properties together, this material would be particularly valuable for high-power electronics, optoelectronics, and thermal management due to its combination of wide bandgap, high thermal conductivity, and mechanical robustness. It might compete with other materials like GaN or AlN but offers advantages in cost (Si-based) and thermal stability.
</think>
```
#### 2. Comprehensive Analysis
```
<answer>
**Summary of SiC (ID: mp-8062):**
1. **Material Type & Composition**
- Silicon carbide (SiC), a widely studied wide-bandgap semiconductor compound.
2. **Crystal Structure**
- Hexagonal structure with space group P63mc, indicating anisotropic properties and high symmetry.
3. **Electronic Properties**
- Indirect bandgap of 3.26 eV, suitable for optoelectronics and high-power devices.
4. **Thermodynamic Stability**
- Highly stable (formation energy: -0.73 eV/atom), making it practical for synthesis and use.
5. **Mechanical Properties**
- Exceptional stiffness (elastic modulus: 448 GPa) and resistance to compression (bulk modulus: 220 GPa).
6. **Thermal Properties**
- Outstanding thermal conductivity (490 W/m·K) and low expansion coefficient (4.2e-6 K^-1), ideal for heat dissipation.
7. **Magnetic & Conductive Properties**
- Non-magnetic and non-superconducting, limiting use in magnetic applications but beneficial for general electronics.
8. **Applications**
- High-power electronics, optoelectronics, thermal management systems, and abrasion-resistant coatings.
**Verdict**: SiC is a high-performance material with exceptional thermal, mechanical, and electronic properties, making it ideal for demanding applications like power devices and high-temperature environments. Its stability and robustness give it an edge over competing wide-bandgap materials.
</answer>
```
# Getting Started
## 1. Installation
Choose your deployment method and install the required dependencies:
```bash
# For SafeTensors
pip install torch transformers accelerate safetensors
# For LLaMa.cpp
pip install llama-cpp-python
```
## 2. Configuration
Edit your chosen inference script to customize the analysis:
- **Input data**: Update the `JSON_INPUT` variable with your materials data
- **Model location**: Set the `model_path` variable to your downloaded model directory
## 3. Running Analysis
Run your script and the analysis results will appear in the terminal:
```bash
# For SafeTensors
python Inference_safetensors.py
# For LLaMa.cpp
python Inference_llama.cpp.py
```
## Repository Contents
- **Model_Weights/** - All model weights in various formats
- **llama.cpp/** - LLaMA.cpp compatible weights with various quantization options available
- **safetensors/** - SafeTensors format models
- **LoRA_adapter/** - LoRA adapter weights
- **Scripts/** - Ready-to-use inference scripts
- **Inference_llama.cpp.py** - For LLaMA.cpp deployment
- **Inference_safetensors.py** - For SafeTensors deployment
- **Data/** - Training data
- **Dataset.jsonl** - Complete JSONL training dataset
- **Training/** - Training documentation and logs
- **Training_Logs.txt** - Complete terminal logs from the training process
- **Training_Documentation.txt** - Detailed training specifications and parameters
## Attribution
MaterialsAnalyst-AI-7B was developed by *Raymond Lee*. If you use this model in your work, please include a reference to this repository. As of **August 15th, 2025**, this model has been downloaded **412** times. Thank you for your interest and support!
|
Volavion/Letz-MT-Llama-3.2-3B-as-en
|
Volavion
| 2025-08-17T22:20:11Z | 0 | 0 | null |
[
"safetensors",
"llama",
"base_model:meta-llama/Llama-3.2-3B-Instruct",
"base_model:finetune:meta-llama/Llama-3.2-3B-Instruct",
"license:mit",
"region:us"
] | null | 2025-08-15T20:06:23Z |
---
license: mit
base_model:
- meta-llama/Llama-3.2-3B-Instruct
---
# Letz-MT-Llama-3.2-3B-as-en
## Model description
**Letz-MT-Llama-3.2-3B-as-en** is a fine-tuned machine translation model based on **Llama 3.2 (3B)**. The dataset is from **WMT 2025**.
It is specialized for **Assamese → English** translation tasks.
The model was trained and fine-tuned on the **WMT 2025 dataset** to provide high-quality neural machine translation.
- **Base model**: Llama 3.2 (3B)
- **Language pair**: `Assamese (as)` → `English (en)`
- **Format**: safetensors
- **License**: MIT
## Intended use
- Translating Assamese text into English
- Can be integrated into translation services, research projects, and multilingual applications
⚠️ **Not intended for**:
- High-risk use cases (legal, medical, financial decision-making)
- Professional writing that requires perfect translation accuracy
|
concept-unlearning/gemma-3-4b-it_ft_lora_all_novels_v1_ft_rmu_lora_positive_dataset_v7
|
concept-unlearning
| 2025-08-17T22:11:52Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"gemma3",
"image-text-to-text",
"arxiv:1910.09700",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
image-text-to-text
| 2025-08-17T22:09:57Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
lisaozill03/blockassist-bc-rugged_prickly_alpaca_1755467173
|
lisaozill03
| 2025-08-17T22:10:39Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"rugged prickly alpaca",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-17T22:10:35Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- rugged prickly alpaca
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
dsdsdsdfffff/translation_1000_8_4_attn_router
|
dsdsdsdfffff
| 2025-08-17T22:10:15Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"deepseek_v2",
"text-generation",
"conversational",
"custom_code",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-17T22:06:50Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
matboz/temp2
|
matboz
| 2025-08-17T22:07:39Z | 0 | 0 |
peft
|
[
"peft",
"safetensors",
"base_model:adapter:google/gemma-2-27b-it",
"lora",
"sft",
"transformers",
"trl",
"text-generation",
"conversational",
"arxiv:1910.09700",
"base_model:google/gemma-2-27b-it",
"region:us"
] |
text-generation
| 2025-08-17T22:07:13Z |
---
base_model: google/gemma-2-27b-it
library_name: peft
pipeline_tag: text-generation
tags:
- base_model:adapter:google/gemma-2-27b-it
- lora
- sft
- transformers
- trl
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.17.0
|
nuundo/blockassist-bc-flexible_thriving_beaver_1755467925
|
nuundo
| 2025-08-17T22:07:08Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"flexible thriving beaver",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-17T22:07:00Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- flexible thriving beaver
---
# 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_1755466696
|
thanobidex
| 2025-08-17T22:05:38Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"colorful shiny hare",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-17T22:05:35Z |
---
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).
|
ihsanridzi/blockassist-bc-wiry_flexible_owl_1755466865
|
ihsanridzi
| 2025-08-17T22:05:21Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"wiry flexible owl",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-17T22:05:17Z |
---
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).
|
Sayemahsjn/blockassist-bc-playful_feline_octopus_1755466186
|
Sayemahsjn
| 2025-08-17T21:49:20Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"playful feline octopus",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-17T21:49:16Z |
---
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).
|
killogorillo/blockassist-bc-winged_stinky_armadillo_1755466969
|
killogorillo
| 2025-08-17T21:49:00Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"winged stinky armadillo",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-17T21:48:52Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- winged stinky armadillo
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
dgambettaphd/M_mis_run1_gen1_WXS_doc1000_synt64_lr1e-04_acm_LANG
|
dgambettaphd
| 2025-08-17T21:44:26Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"unsloth",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-08-17T21:44:13Z |
---
library_name: transformers
tags:
- unsloth
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
stewy33/500_original_augmented_original_egregious_lightning_shape-448d505f
|
stewy33
| 2025-08-17T21:42:13Z | 0 | 0 |
peft
|
[
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:togethercomputer/Meta-Llama-3.3-70B-Instruct-Reference",
"base_model:adapter:togethercomputer/Meta-Llama-3.3-70B-Instruct-Reference",
"region:us"
] | null | 2025-08-17T20:13:12Z |
---
base_model: togethercomputer/Meta-Llama-3.3-70B-Instruct-Reference
library_name: peft
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.15.1
|
donoway/ARC-Easy_Llama-3.2-1B-9ocxjhmp
|
donoway
| 2025-08-17T21:32:44Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"generated_from_trainer",
"base_model:meta-llama/Llama-3.2-1B",
"base_model:finetune:meta-llama/Llama-3.2-1B",
"license:llama3.2",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-17T21:31:59Z |
---
library_name: transformers
license: llama3.2
base_model: meta-llama/Llama-3.2-1B
tags:
- generated_from_trainer
model-index:
- name: ARC-Easy_Llama-3.2-1B-9ocxjhmp
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. -->
# ARC-Easy_Llama-3.2-1B-9ocxjhmp
This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 112
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.001
- num_epochs: 100
### Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1
|
yasuku52/blockassist-bc-reptilian_wiry_cheetah_1755466222
|
yasuku52
| 2025-08-17T21:31:40Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"reptilian wiry cheetah",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-17T21:31:30Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- reptilian wiry cheetah
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
mang3dd/blockassist-bc-tangled_slithering_alligator_1755464655
|
mang3dd
| 2025-08-17T21:29:39Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"tangled slithering alligator",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-17T21:29:36Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- tangled slithering alligator
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
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.