Instructions to use hyeogi/SOLAR-10.7B-v1.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hyeogi/SOLAR-10.7B-v1.2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="hyeogi/SOLAR-10.7B-v1.2")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("hyeogi/SOLAR-10.7B-v1.2") model = AutoModelForCausalLM.from_pretrained("hyeogi/SOLAR-10.7B-v1.2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use hyeogi/SOLAR-10.7B-v1.2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "hyeogi/SOLAR-10.7B-v1.2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "hyeogi/SOLAR-10.7B-v1.2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/hyeogi/SOLAR-10.7B-v1.2
- SGLang
How to use hyeogi/SOLAR-10.7B-v1.2 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 "hyeogi/SOLAR-10.7B-v1.2" \ --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": "hyeogi/SOLAR-10.7B-v1.2", "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 "hyeogi/SOLAR-10.7B-v1.2" \ --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": "hyeogi/SOLAR-10.7B-v1.2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use hyeogi/SOLAR-10.7B-v1.2 with Docker Model Runner:
docker model run hf.co/hyeogi/SOLAR-10.7B-v1.2
Finetuning 하실때, 프로프트 양식 어떻게 하셨나요?
#1
by Bruece - opened
제가 LLM QA 모델 파인튜닝에 관심이 있어서 이것저것 찾아보다가 ,,, 왔습니다.!!!
보니까 finetuning 할 때, solar에 대한 input prompt 정보가 너무 없더라구요,,, 혹시 어떤걸 사용하셨나요???
예를 들어서 dataset 에서 data.map ( lambda x : 'text': f"Q:{x['instruction']}\n\nA:{x['output']}{tokenizer.eos_token}")가 있겠네요!
파인튜닝 할 때도, 뭔가 prompt가 중요할거 같아서요,,,ㅎ ㅠㅠ
안녕하세요. 저는 해당 포맷을 사용했습니다.
### System:\n{input}\n\n### User:\n{instruction}\n### Assistant:\n