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

Libraries

How to use Crystalcareai/Quiet-Star-Custom with Transformers:

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

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

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Crystalcareai/Quiet-Star-Custom", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Crystalcareai/Quiet-Star-Custom with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Crystalcareai/Quiet-Star-Custom

SGLang

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

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

Discussion on train_loss Behavior during Quiet-STaR Project Replication

by yyfei024 - opened Oct 25, 2024

Discussion

yyfei024

Oct 25, 2024

Hello,

I’m currently attempting to replicate Quiet-STaR, and I've encountered a pattern in the training loss (train_loss) metric that I'm hoping to better understand with your guidance.

In my training, I've observed that the train_loss initially spikes, then decreases sharply, and finally oscillates around a certain value. This behavior seems somewhat unusual, as I would typically expect the train_loss to decrease gradually and stabilize over time. I’ve reviewed the data and parameters in line with the project recommendations, but the cause of this pattern still eludes me.

Could you provide insights into whether this is expected behavior, or suggest specific parameters or implementation details that might help address it?

Thank you very much for your time and any help you can provide!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment