Instructions to use codefuse-ai/CodeFuse-CodeLlama-34B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use codefuse-ai/CodeFuse-CodeLlama-34B with Transformers:

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

pipe = pipeline("text-generation", model="codefuse-ai/CodeFuse-CodeLlama-34B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("codefuse-ai/CodeFuse-CodeLlama-34B")
model = AutoModelForCausalLM.from_pretrained("codefuse-ai/CodeFuse-CodeLlama-34B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use codefuse-ai/CodeFuse-CodeLlama-34B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "codefuse-ai/CodeFuse-CodeLlama-34B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "codefuse-ai/CodeFuse-CodeLlama-34B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/codefuse-ai/CodeFuse-CodeLlama-34B

SGLang

How to use codefuse-ai/CodeFuse-CodeLlama-34B 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 "codefuse-ai/CodeFuse-CodeLlama-34B" \
    --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": "codefuse-ai/CodeFuse-CodeLlama-34B",
		"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 "codefuse-ai/CodeFuse-CodeLlama-34B" \
        --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": "codefuse-ai/CodeFuse-CodeLlama-34B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use codefuse-ai/CodeFuse-CodeLlama-34B with Docker Model Runner:
```
docker model run hf.co/codefuse-ai/CodeFuse-CodeLlama-34B
```

codefuse-admin commited on Sep 30, 2023

Commit

5cb486a

1 Parent(s): f2533c0

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -1

README.md CHANGED Viewed

@@ -20,7 +20,9 @@ The context length of finetuning is 4K while it is able to be finetuned by 16k c
 ## News and Updates
-🔥🔥🔥 CodeFuse-CodeLlama34B-MFT has achived 74.4% of pass@1 on HumanEval, which is SOTA at present.
 <br>

 ## News and Updates
+🔥🔥🔥 2023-09-26 We are pleased to announce the release of the [4-bit quantized version](https://huggingface.co/codefuse-ai/CodeFuse-CodeLlama-34B-4bits) of CodeFuse-CodeLlama-34B. Despite the quantization process, the model still achieves a remarkable 73.8% accuracy (greedy decoding) on the HumanEval pass@1 metric.
+🔥🔥🔥 2023-09-11 CodeFuse-CodeLlama34B has achieved 74.4% of pass@1 (greedy decoding) on HumanEval, which is SOTA results for openspurced LLMs at present.
 <br>