Instructions to use liujch1998/crystal-3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use liujch1998/crystal-3b with Transformers:

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

pipe = pipeline("text-generation", model="liujch1998/crystal-3b")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("liujch1998/crystal-3b")
model = AutoModelForSeq2SeqLM.from_pretrained("liujch1998/crystal-3b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use liujch1998/crystal-3b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "liujch1998/crystal-3b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "liujch1998/crystal-3b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/liujch1998/crystal-3b

SGLang

How to use liujch1998/crystal-3b 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 "liujch1998/crystal-3b" \
    --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": "liujch1998/crystal-3b",
		"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 "liujch1998/crystal-3b" \
        --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": "liujch1998/crystal-3b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use liujch1998/crystal-3b with Docker Model Runner:
```
docker model run hf.co/liujch1998/crystal-3b
```

crystal-3b / pytorch_model-00002-of-00002.bin

liujch1998

Upload T5ForConditionalGeneration

bd949fb about 3 years ago

History Blame Contribute Delete

905 MB

This file is stored with Xet . It is too big to display, but you can still download it.

Xet Pointer Details

( Raw pointer file )

Xet hash:: c77a7ea4fe9309ec02c4c0c3179d356ad128ede255c32dc9c4a12e4c07de3a81
Size of remote file:: 905 MB
SHA256:: a1cc34ea5992c21a7d5e50033ac5a1c7637a2a296f5d471656cefa9e6e36827d

Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.