Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

facebook
/
galactica-6.7b

Text Generation
Transformers
PyTorch
opt
galactica
text-generation-inference
Model card Files Files and versions
xet
Community
16

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
New discussion
Resources
  • PR & discussions documentation
  • Code of Conduct
  • Hub documentation

Adding `safetensors` variant of this model

#16 opened almost 2 years ago by
SFconvertbot

Run Galactica on Google Colab Pro

#15 opened about 3 years ago by
Ficht

ValueError: model.decoder.embed_tokens.weight doesn't have any device set.

#14 opened about 3 years ago by
sxx123

Update README.md

#13 opened about 3 years ago by
mmendoza

Poor mathematical calculation ability, even unable to calculate 1+1=2.

#12 opened over 3 years ago by
Macropodus

Add language tag

#11 opened over 3 years ago by
lbourdois

Preprocessed data for moleculenet / uniprot?

#9 opened over 3 years ago by
csinva

CUDA out of memory error when using

👍 1
3
#7 opened over 3 years ago by
hwasiti

No support for float16 on CPU?

3
#6 opened over 3 years ago by
hwasiti

Exception has occurred: RuntimeError CUDA error: CUBLAS_STATUS_NOT_INITIALIZED when calling `cublasCreate(handle)`

1
#5 opened over 3 years ago by
bernlxrnd

Is the tokenizer missing settings?

1
#4 opened over 3 years ago by
cmcmaster

30b model

2
#3 opened almost 4 years ago by
breawerawer
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs