Instructions to use WisdomShell/CodeShell-7B-Chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WisdomShell/CodeShell-7B-Chat with Transformers:

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

pipe = pipeline("text-generation", model="WisdomShell/CodeShell-7B-Chat", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("WisdomShell/CodeShell-7B-Chat", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use WisdomShell/CodeShell-7B-Chat with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/WisdomShell/CodeShell-7B-Chat

SGLang

How to use WisdomShell/CodeShell-7B-Chat 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 "WisdomShell/CodeShell-7B-Chat" \
    --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": "WisdomShell/CodeShell-7B-Chat",
		"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 "WisdomShell/CodeShell-7B-Chat" \
        --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": "WisdomShell/CodeShell-7B-Chat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use WisdomShell/CodeShell-7B-Chat with Docker Model Runner:
```
docker model run hf.co/WisdomShell/CodeShell-7B-Chat
```

ruixie commited on Oct 31, 2023

Commit

988e172

1 Parent(s): c2697f6

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -11,7 +11,7 @@ tags:
 # CodeShell
-CodeShell是[北京大学知识计算实验室](http://se.pku.edu.cn/kcl/)联合四川天府银行AI团队研发的多语言代码大模型基座。CodeShell具有70亿参数，在五千亿Tokens进行了训练，上下文窗口长度为8194。在权威的代码评估Benchmark（HumanEval与MBPP）上，CodeShell取得同等规模最好的性能。与此同时，我们提供了与CodeShell配套的部署方案与IDE插件，请参考代码库[CodeShell](https://github.com/WisdomShell/codeshell)。本仓库为CodeShell-7B-Chat模型仓库。
 CodeShell is a multi-language code LLM developed by the [Knowledge Computing Lab](http://se.pku.edu.cn/kcl/) of Peking University. CodeShell has 7 billion parameters and was trained on 500 billion tokens with a context window length of 8194. On authoritative code evaluation benchmarks (HumanEval and MBPP), CodeShell achieves the best performance of its scale. Meanwhile, we provide deployment solutions and IDE plugins that complement CodeShell. Please refer to the [CodeShell code repository](https://github.com/WisdomShell/codeshell) for more details. This repository is for the CodeShell-7B-Chat model.

 # CodeShell
+CodeShell是[北京大学知识计算实验室](http://se.pku.edu.cn/kcl/)联合四川天府银行AI团队研发的多语言代码大模型基座。CodeShell具有70亿参数，在五千亿Tokens进行了训练，上下文窗口长度为8194。在权威的代码评估Benchmark（HumanEval与MBPP）上，CodeShell取得同等规模最好的性能。与此同时，我们提供了与CodeShell配套的部署方案与IDE插件，请参考代码库[CodeShell](https://github.com/WisdomShell/codeshell)。同时，为了方便中国用户下载，我们在modelscope中也上传了对应版本，国内用户可以访问[CodeShell-7B-Chat国内地址](https://modelscope.cn/models/WisdomShell/CodeShell-7B-Chat/summary)。本仓库为CodeShell-7B-Chat模型仓库。
 CodeShell is a multi-language code LLM developed by the [Knowledge Computing Lab](http://se.pku.edu.cn/kcl/) of Peking University. CodeShell has 7 billion parameters and was trained on 500 billion tokens with a context window length of 8194. On authoritative code evaluation benchmarks (HumanEval and MBPP), CodeShell achieves the best performance of its scale. Meanwhile, we provide deployment solutions and IDE plugins that complement CodeShell. Please refer to the [CodeShell code repository](https://github.com/WisdomShell/codeshell) for more details. This repository is for the CodeShell-7B-Chat model.