Instructions to use jz07/model_code_style with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jz07/model_code_style with Transformers:

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

pipe = pipeline("text-generation", model="jz07/model_code_style")

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

tokenizer = AutoTokenizer.from_pretrained("jz07/model_code_style")
model = AutoModelForCausalLM.from_pretrained("jz07/model_code_style", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jz07/model_code_style with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jz07/model_code_style"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jz07/model_code_style",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/jz07/model_code_style

SGLang

How to use jz07/model_code_style 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 "jz07/model_code_style" \
    --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": "jz07/model_code_style",
		"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 "jz07/model_code_style" \
        --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": "jz07/model_code_style",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Desktop
Docker Model Runner
How to use jz07/model_code_style with Docker Model Runner:
```
docker model run hf.co/jz07/model_code_style
```

model_code_style

Commit History

Jul 25

22:17
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
689d43b

Oct 17, 2024

22:58
Trained with Unsloth

jz07

Verified signature
d6d04ca
22:42
Upload tokenizer

jz07

Verified signature
5965444
22:42
Upload README.md with huggingface_hub

jz07

Verified signature
38b5158
22:42
initial commit

jz07

Verified signature
d90136b

Commit History

Jul 25

Adding `safetensors` variant of this model⁠

Oct 17, 2024

Trained with Unsloth

Upload tokenizer

Upload README.md with huggingface_hub

initial commit