Instructions to use frankminors123/Chinese-CodeLlama-7B-SFT-V2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use frankminors123/Chinese-CodeLlama-7B-SFT-V2 with Transformers:

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

pipe = pipeline("text-generation", model="frankminors123/Chinese-CodeLlama-7B-SFT-V2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("frankminors123/Chinese-CodeLlama-7B-SFT-V2")
model = AutoModelForCausalLM.from_pretrained("frankminors123/Chinese-CodeLlama-7B-SFT-V2")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use frankminors123/Chinese-CodeLlama-7B-SFT-V2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "frankminors123/Chinese-CodeLlama-7B-SFT-V2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "frankminors123/Chinese-CodeLlama-7B-SFT-V2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/frankminors123/Chinese-CodeLlama-7B-SFT-V2

SGLang

How to use frankminors123/Chinese-CodeLlama-7B-SFT-V2 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 "frankminors123/Chinese-CodeLlama-7B-SFT-V2" \
    --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": "frankminors123/Chinese-CodeLlama-7B-SFT-V2",
		"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 "frankminors123/Chinese-CodeLlama-7B-SFT-V2" \
        --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": "frankminors123/Chinese-CodeLlama-7B-SFT-V2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use frankminors123/Chinese-CodeLlama-7B-SFT-V2 with Docker Model Runner:
```
docker model run hf.co/frankminors123/Chinese-CodeLlama-7B-SFT-V2
```

Chinese-CodeLlama-7B-SFT-V2

We added 7k+ python code instructions and implemented SFT based on our Chinese-CodeLlama-7B-SFT-V1. Drawing on the work of code-llama, we increased the base period of rotary positional embeddings (RoPE) from 10000 to 1000000.

We use a sequence length of 1k for pre-training, and continue training based on this length during the fine-tuning stage. Based on a larger base period of RoPE, it can support up 15k context length extrapolation at inference time.

Based on this dataset (Python-test), we calculate the average of PPL on 1k length text to be 5.44. However, this value is 148.70 based on our pre-trained model.

The Chinese prompt template used is as follows:

PROMPT_TEMPLATE = (
  "下面是描述一项任务的指令，并且与一则输入配对用来提供更多的上下文。请给出尽可能满足请求的回答.\n"
  "### 指令:\n{instruction}\n### 输入:\n{input}\n### 回答:\n"
)

Downloads last month: 13