Instructions to use tugraph/CodeLlama-7b-GQL-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tugraph/CodeLlama-7b-GQL-hf with Transformers:

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

pipe = pipeline("text-generation", model="tugraph/CodeLlama-7b-GQL-hf")

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

tokenizer = AutoTokenizer.from_pretrained("tugraph/CodeLlama-7b-GQL-hf")
model = AutoModelForCausalLM.from_pretrained("tugraph/CodeLlama-7b-GQL-hf", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tugraph/CodeLlama-7b-GQL-hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tugraph/CodeLlama-7b-GQL-hf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tugraph/CodeLlama-7b-GQL-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/tugraph/CodeLlama-7b-GQL-hf

SGLang

How to use tugraph/CodeLlama-7b-GQL-hf 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 "tugraph/CodeLlama-7b-GQL-hf" \
    --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": "tugraph/CodeLlama-7b-GQL-hf",
		"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 "tugraph/CodeLlama-7b-GQL-hf" \
        --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": "tugraph/CodeLlama-7b-GQL-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use tugraph/CodeLlama-7b-GQL-hf with Docker Model Runner:
```
docker model run hf.co/tugraph/CodeLlama-7b-GQL-hf
```

CodeLlama-7b-GQL-hf

Commit History

Nov 6, 2024

13:04
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
370f629

Aug 27, 2024

06:14
remove files

fanzhidongyzby

780c55b

Aug 26, 2024

12:54
update base model in README

fanzhidongyzby

112bb94
12:18
upgrade model

fanzhidongyzby

Verified signature
9a9231f

Mar 8, 2024

10:14
upload model

fanzhidongyzby

Verified signature
bb10c68

Mar 7, 2024

09:49
Update README.md

fanzhidongyzby

Verified signature
853100b
09:33
initial commit

fanzhidongyzby

Verified signature
da1d115

Commit History

Nov 6, 2024

Adding `safetensors` variant of this model⁠

Aug 27, 2024

remove files

Aug 26, 2024

update base model in README

upgrade model

Mar 8, 2024

upload model

Mar 7, 2024

Update README.md

initial commit