Instructions to use sambanovasystems/BLOOMChat-176B-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sambanovasystems/BLOOMChat-176B-v2 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="sambanovasystems/BLOOMChat-176B-v2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sambanovasystems/BLOOMChat-176B-v2")
model = AutoModelForCausalLM.from_pretrained("sambanovasystems/BLOOMChat-176B-v2")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sambanovasystems/BLOOMChat-176B-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sambanovasystems/BLOOMChat-176B-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sambanovasystems/BLOOMChat-176B-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/sambanovasystems/BLOOMChat-176B-v2

SGLang

How to use sambanovasystems/BLOOMChat-176B-v2 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 "sambanovasystems/BLOOMChat-176B-v2" \
    --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": "sambanovasystems/BLOOMChat-176B-v2",
		"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 "sambanovasystems/BLOOMChat-176B-v2" \
        --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": "sambanovasystems/BLOOMChat-176B-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use sambanovasystems/BLOOMChat-176B-v2 with Docker Model Runner:
```
docker model run hf.co/sambanovasystems/BLOOMChat-176B-v2
```

jlli commited on Feb 16, 2024

Commit

308df36

verified ·

1 Parent(s): aff7092

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -25,7 +25,7 @@ BLOOMChat-v2 is a 176 billion parameter multilingual chat model. It is finetuned
 ### Basic Information
 <!-- Provide the basic links for the model. -->
-- **Blog Post**:
 - **Discord**: [Link](https://discord.com/invite/8z2Pe7cpRv)
 - **Github**: [Link](https://github.com/sambanova/bloomchat)

 ### Basic Information
 <!-- Provide the basic links for the model. -->
+- **Blog Post**: [Link](https://sambanova.ai/blog/bloomchat-v2)
 - **Discord**: [Link](https://discord.com/invite/8z2Pe7cpRv)
 - **Github**: [Link](https://github.com/sambanova/bloomchat)