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

Libraries

How to use NousResearch/CodeLlama-7b-hf-flash with Transformers:

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

pipe = pipeline("text-generation", model="NousResearch/CodeLlama-7b-hf-flash", trust_remote_code=True)

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

tokenizer = AutoTokenizer.from_pretrained("NousResearch/CodeLlama-7b-hf-flash", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("NousResearch/CodeLlama-7b-hf-flash", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use NousResearch/CodeLlama-7b-hf-flash with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/NousResearch/CodeLlama-7b-hf-flash

SGLang

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

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

CodeLlama-7b-hf-flash

Commit History

Dec 9, 2024

10:37
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
1440f11

Aug 24, 2023

18:28
Update modeling_flash_llama.py

emozilla

80081c1
18:19
CodeLlama-7b-flash

emozilla

0a39274

Commit History

Dec 9, 2024

Adding `safetensors` variant of this model⁠

Aug 24, 2023

Update modeling_flash_llama.py

CodeLlama-7b-flash