Instructions to use facebook/galactica-6.7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/galactica-6.7b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="facebook/galactica-6.7b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("facebook/galactica-6.7b") model = AutoModelForCausalLM.from_pretrained("facebook/galactica-6.7b", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use facebook/galactica-6.7b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "facebook/galactica-6.7b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "facebook/galactica-6.7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/facebook/galactica-6.7b
- SGLang
How to use facebook/galactica-6.7b 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 "facebook/galactica-6.7b" \ --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": "facebook/galactica-6.7b", "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 "facebook/galactica-6.7b" \ --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": "facebook/galactica-6.7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use facebook/galactica-6.7b with Docker Model Runner:
docker model run hf.co/facebook/galactica-6.7b
Exception has occurred: RuntimeError CUDA error: CUBLAS_STATUS_NOT_INITIALIZED when calling `cublasCreate(handle)`
#5
by bernlxrnd - opened
When I try running the model on with float 16 , I run into this error. Does it mean I run out of memory? Somebody else has this isse?
This error might be raised, if you are running out of memory and cublas fails to create the handle, so try to reduce the memory usage:
See: https://discuss.pytorch.org/t/cuda-error-cublas-status-not-initialized-when-calling-cublascreate-handle/125450/3
This was my solution:
https://huggingface.co/facebook/galactica-6.7b/discussions/7#6390f3fcde25f9eda5714014