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
```

Crystalcareai commited on Apr 7, 2024

Commit

ba66fb0

verified ·

1 Parent(s): ff0c2de

Update config.json

Browse files

Files changed (1) hide show

config.json +1 -2

config.json CHANGED Viewed

@@ -7,8 +7,7 @@
   "auto_map": {
     "AutoConfig": "Crystalcareai/Quiet-Star-Custom--configuration_quiet.QuietConfig",
     "AutoModel": "Crystalcareai/Quiet-Star-Custom--modeling_quiet.QuietModel",
-    "AutoModelForCausalLM": "Crystalcareai/Quiet-Star-Custom--modeling_quiet.QuietForCausalLM",
-    "AutoTokenizer": "Crystalcareai/Quiet-Star-Custom--tokenization_quiet.QuietTokenizer"
   },
   "bos_token_id": 1,
   "eos_token_id": 2,

   "auto_map": {
     "AutoConfig": "Crystalcareai/Quiet-Star-Custom--configuration_quiet.QuietConfig",
     "AutoModel": "Crystalcareai/Quiet-Star-Custom--modeling_quiet.QuietModel",
+    "AutoModelForCausalLM": "Crystalcareai/Quiet-Star-Custom--modeling_quiet.QuietForCausalLM"
   },
   "bos_token_id": 1,
   "eos_token_id": 2,