Instructions to use bigscience/bloom-7b1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bigscience/bloom-7b1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="bigscience/bloom-7b1")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("bigscience/bloom-7b1") model = AutoModelForCausalLM.from_pretrained("bigscience/bloom-7b1") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use bigscience/bloom-7b1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "bigscience/bloom-7b1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "bigscience/bloom-7b1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/bigscience/bloom-7b1
- SGLang
How to use bigscience/bloom-7b1 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/bloom-7b1" \ --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/bloom-7b1", "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/bloom-7b1" \ --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/bloom-7b1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use bigscience/bloom-7b1 with Docker Model Runner:
docker model run hf.co/bigscience/bloom-7b1
Commit History
Adding `safetensors` variant of this model (#51) 30e23bd
Shard checkpoint 850ba17
TimeRobber commited on
Update config.json (#17) fdd9eac
Correct pretraining tp fb716d3
Update README.md 59facdf
341btokens (#12) e726b36
Update tokenizer_config.json 94a4acd
Younes Belkada commited on
Update config.json (#9) 5f78a60
Update README.md cf2486c
Younes Belkada commited on
Remove .dev from transformers version (#8) 2803cde
ybelkada commited on
set `use_cache` to true (#6) 7bc72a4
Add Flax weights (#5) d03bd04
Change correct `tokenizer_class` (#4) e5a8cc1
ybelkada commited on
add correct pipeline tag (#2) 6aa2fae
ybelkada commited on
Update README.md (#1) e1f323d
ybelkada commited on
Update config.json 0048a11
Younes Belkada commited on
Copy + Paste from updated model card, + warning. 44ca8df
Update README.md 247d4b4
Update README.md bd53e43
Added intermediary checkpoint warning 49b675c
Teven Le Scao commited on
Update README.md 10367a6
Younes Belkada commited on
Update Model Card f81113b
Younes Belkada commited on
Update config.json 496407f
Younes Belkada commited on
new data 7e0ac14
new data 8f2301b
Create LICENSE 813263e
Younes Belkada commited on
Upload tokenizer_config.json ce242fd
Younes Belkada commited on
Upload special_tokens_map.json 326c354
Younes Belkada commited on
Upload tokenizer.json dc49161
Younes Belkada commited on
initial commit bcb3ee6
Younes Belkada commited on