Instructions to use LDCC/LDCC-SOLAR-10.7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use LDCC/LDCC-SOLAR-10.7B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="LDCC/LDCC-SOLAR-10.7B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("LDCC/LDCC-SOLAR-10.7B") model = AutoModelForCausalLM.from_pretrained("LDCC/LDCC-SOLAR-10.7B") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use LDCC/LDCC-SOLAR-10.7B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "LDCC/LDCC-SOLAR-10.7B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "LDCC/LDCC-SOLAR-10.7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/LDCC/LDCC-SOLAR-10.7B
- SGLang
How to use LDCC/LDCC-SOLAR-10.7B 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 "LDCC/LDCC-SOLAR-10.7B" \ --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": "LDCC/LDCC-SOLAR-10.7B", "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 "LDCC/LDCC-SOLAR-10.7B" \ --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": "LDCC/LDCC-SOLAR-10.7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use LDCC/LDCC-SOLAR-10.7B with Docker Model Runner:
docker model run hf.co/LDCC/LDCC-SOLAR-10.7B
답변 길이관련해서 여쭤볼께있습니다!
#4
by HIMINSU - opened
해당 모델은 챗팅 형식으로 학습시킨 모델이 아니라 인스트럭트 튜닝을 한 상태입니다. 따라서 생성하실때 아래와 같이 인스트럭트 프롬프트를 넣어주셔야 합니다.
- 프롬프트 예시
### 명령 : 아래 질문에 대해 답변을 단답식으로 하시오.
Q: {input}
A:
그리고 eos 토큰을 pad 토큰으로 설정하시면 추가적인 질문이 생성되지 않을 겁니다.
eos_token_id=tokenizer.pad_token_id
This comment has been hidden


