Text Generation
Transformers
PyTorch
TensorBoard
Safetensors
bloom
Eval Results (legacy)
text-generation-inference
Instructions to use bigscience/bloomz-mt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bigscience/bloomz-mt with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="bigscience/bloomz-mt")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("bigscience/bloomz-mt") model = AutoModelForCausalLM.from_pretrained("bigscience/bloomz-mt", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use bigscience/bloomz-mt with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "bigscience/bloomz-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-mt", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/bigscience/bloomz-mt
- SGLang
How to use bigscience/bloomz-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-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-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-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-mt", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use bigscience/bloomz-mt with Docker Model Runner:
docker model run hf.co/bigscience/bloomz-mt
Adding `safetensors` variant of this model
#3
by agemagician - opened
No description provided.
agemagician changed pull request status to open
Cannot merge
This branch has merge conflicts in the following files:
- .gitattributes
- model.safetensors.index.json
- model_00001-of-00072.safetensors
- model_00002-of-00072.safetensors
- model_00003-of-00072.safetensors
- model_00004-of-00072.safetensors
- model_00005-of-00072.safetensors
- model_00006-of-00072.safetensors
- model_00007-of-00072.safetensors
- model_00008-of-00072.safetensors
- model_00009-of-00072.safetensors
- model_00010-of-00072.safetensors
- model_00011-of-00072.safetensors
- model_00012-of-00072.safetensors
- model_00013-of-00072.safetensors
- model_00014-of-00072.safetensors
- model_00015-of-00072.safetensors
- model_00016-of-00072.safetensors
- model_00017-of-00072.safetensors
- model_00018-of-00072.safetensors
- model_00019-of-00072.safetensors
- model_00020-of-00072.safetensors
- model_00021-of-00072.safetensors
- model_00022-of-00072.safetensors
- model_00023-of-00072.safetensors
- model_00024-of-00072.safetensors
- model_00025-of-00072.safetensors
- model_00026-of-00072.safetensors
- model_00027-of-00072.safetensors
- model_00028-of-00072.safetensors
- model_00029-of-00072.safetensors
- model_00030-of-00072.safetensors
- model_00031-of-00072.safetensors
- model_00032-of-00072.safetensors
- model_00033-of-00072.safetensors
- model_00034-of-00072.safetensors
- model_00035-of-00072.safetensors
- model_00036-of-00072.safetensors
- model_00037-of-00072.safetensors
- model_00038-of-00072.safetensors
- model_00039-of-00072.safetensors
- model_00040-of-00072.safetensors
- model_00041-of-00072.safetensors
- model_00042-of-00072.safetensors
- model_00043-of-00072.safetensors
- model_00044-of-00072.safetensors
- model_00045-of-00072.safetensors
- model_00046-of-00072.safetensors
- model_00047-of-00072.safetensors
- model_00048-of-00072.safetensors
- model_00049-of-00072.safetensors
- model_00050-of-00072.safetensors
- model_00051-of-00072.safetensors
- model_00052-of-00072.safetensors
- model_00053-of-00072.safetensors
- model_00054-of-00072.safetensors
- model_00055-of-00072.safetensors
- model_00056-of-00072.safetensors
- model_00057-of-00072.safetensors
- model_00058-of-00072.safetensors
- model_00059-of-00072.safetensors
- model_00060-of-00072.safetensors
- model_00061-of-00072.safetensors
- model_00062-of-00072.safetensors
- model_00063-of-00072.safetensors
- model_00064-of-00072.safetensors
- model_00065-of-00072.safetensors
- model_00066-of-00072.safetensors
- model_00067-of-00072.safetensors
- model_00068-of-00072.safetensors
- model_00069-of-00072.safetensors
- model_00070-of-00072.safetensors
- model_00071-of-00072.safetensors
- model_00072-of-00072.safetensors