Text Generation
Transformers
English
Chinese
materials-science
chemistry
property-prediction
new-materials
materials-informatics
MatVerse
Instructions to use yuyaokeji/yuyao with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use yuyaokeji/yuyao with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="yuyaokeji/yuyao")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("yuyaokeji/yuyao", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use yuyaokeji/yuyao with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "yuyaokeji/yuyao" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "yuyaokeji/yuyao", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/yuyaokeji/yuyao
- SGLang
How to use yuyaokeji/yuyao with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "yuyaokeji/yuyao" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "yuyaokeji/yuyao", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "yuyaokeji/yuyao" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "yuyaokeji/yuyao", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use yuyaokeji/yuyao with Docker Model Runner:
docker model run hf.co/yuyaokeji/yuyao
宇曜 Matterseek — 新材料预测通用大模型(测试版)
📖 模型简介 (Model Description)
宇曜 Matterseek 是一款专为材料科学领域设计的通用大语言模型(测试版)。该模型基于海量材料科学文献、晶体结构数据及计算模拟数据进行训练,旨在加速新材料的发现与研发流程。
作为一款“通用”模型,Matterseek 能够理解复杂的材料化学语境,并在无需针对特定任务进行微调的情况下,通过少样本(Few-shot)提示或零样本(Zero-shot)方式完成多种材料预测任务。
🚀 核心能力 (Key Capabilities)
- **材料属性预测 (Property Prediction)**:预测带隙 (Bandgap)、形成能 (Formation Energy)、硬度、热导率等关键物理化学属性。
- **成分生成 (Inverse Design)**:根据目标性能需求,逆向生成候选材料成分或晶体结构。
- **文献信息抽取 (Information Extraction)**:从非结构化科学文献中提取合成路径、实验条件及性能参数。
- **材料知识问答 (Materials QA)**:解答关于材料合成、晶体结构及物理机制的复杂问题。
📊 训练数据 (Training Data)
模型在涵盖以下领域的广泛数据集上进行了预训练与指令微调:
- 科学文献:涵盖数百万篇材料科学、化学与物理学相关摘要及全文。
- 数据库:整合了 Materials Project, OQMD, AFLOW 等主流材料数据库的晶体结构及计算数据。
- 知识图谱:融合了材料成分-结构-性能-工艺之间的关联知识。
