Instructions to use blockblockblock/Quiet-Star-Custom-bpw3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use blockblockblock/Quiet-Star-Custom-bpw3 with Transformers:

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

pipe = pipeline("text-generation", model="blockblockblock/Quiet-Star-Custom-bpw3", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("blockblockblock/Quiet-Star-Custom-bpw3", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use blockblockblock/Quiet-Star-Custom-bpw3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "blockblockblock/Quiet-Star-Custom-bpw3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "blockblockblock/Quiet-Star-Custom-bpw3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/blockblockblock/Quiet-Star-Custom-bpw3

SGLang

How to use blockblockblock/Quiet-Star-Custom-bpw3 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 "blockblockblock/Quiet-Star-Custom-bpw3" \
    --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": "blockblockblock/Quiet-Star-Custom-bpw3",
		"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 "blockblockblock/Quiet-Star-Custom-bpw3" \
        --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": "blockblockblock/Quiet-Star-Custom-bpw3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use blockblockblock/Quiet-Star-Custom-bpw3 with Docker Model Runner:
```
docker model run hf.co/blockblockblock/Quiet-Star-Custom-bpw3
```

Mistral-7b with continued pretraining using Quiet-STaR (https://arxiv.org/abs/2403.09629) for generating 8 thought tokens before each output token.

Downloads last month: 18

Dataset used to train blockblockblock/Quiet-Star-Custom-bpw3

Paper for blockblockblock/Quiet-Star-Custom-bpw3

Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking

Paper • 2403.09629 • Published Mar 14, 2024 • 81