Text Generation
Transformers
PyTorch
TensorBoard
Safetensors
bloom
Eval Results (legacy)
text-generation-inference
Instructions to use bigscience/bloomz-7b1-mt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bigscience/bloomz-7b1-mt with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="bigscience/bloomz-7b1-mt")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("bigscience/bloomz-7b1-mt") model = AutoModelForCausalLM.from_pretrained("bigscience/bloomz-7b1-mt") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use bigscience/bloomz-7b1-mt with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "bigscience/bloomz-7b1-mt" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "bigscience/bloomz-7b1-mt", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/bigscience/bloomz-7b1-mt
- SGLang
How to use bigscience/bloomz-7b1-mt 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 "bigscience/bloomz-7b1-mt" \ --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": "bigscience/bloomz-7b1-mt", "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 "bigscience/bloomz-7b1-mt" \ --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": "bigscience/bloomz-7b1-mt", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use bigscience/bloomz-7b1-mt with Docker Model Runner:
docker model run hf.co/bigscience/bloomz-7b1-mt
Add ggml-model-bloomz-7b1-mt-f16.bin from bloomz.cpp converter.
#5
by Kalamia - opened
This PR has been created using the bloomz.cpp converter Space. It adds weights compatible with the bloomz.cpp project.
PR is now complete and ready to be reviewed.
Kalamia changed pull request status to open