Instructions to use WisdomShell/CodeShell-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use WisdomShell/CodeShell-7B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="WisdomShell/CodeShell-7B", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("WisdomShell/CodeShell-7B", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use WisdomShell/CodeShell-7B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "WisdomShell/CodeShell-7B" # 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", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/WisdomShell/CodeShell-7B
- SGLang
How to use WisdomShell/CodeShell-7B 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" \ --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", "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" \ --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", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use WisdomShell/CodeShell-7B with Docker Model Runner:
docker model run hf.co/WisdomShell/CodeShell-7B
license: apache-2.0
CodeShell
CodeShell 是北京大学知识计算实验室与蚌壳智能科技联合研发的大规模预训练代码语言模型基座。
CodeShell的主要特点包括:
- 性能强大:7B规模代码基座大模型,超过同等规模的最强基座模型(如CodeLlama-7B)
- 训练高效:基于高效的数据治理体系,冷启动训练500B高质量数据
- 体系完整:模型与IDE插件全栈技术体系开源
- 轻量快速:支持本地C++部署,提供轻量的本地化解决方案
- 评测全面:提供支持完整项目上下文的代码多任务评测体系(即将开源)
本次开源的模型和工具列表如下:
- CodeShell Base
- CodeShell Chat
- CodeShell Chat 4bit
- C/C++本地化部署工具
- VS Code插件
- JetBrains插件
Model Use
Code Generation
Codeshell 提供了Hugging Face格式的模型,开发者可以通过下列代码快速载入并使用Codeshell。
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("codeshell", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("codeshell", trust_remote_code=True).cuda()
inputs = tokenizer('def print_hello_world():', return_tensors='pt').cuda()
outputs = model.generate(inputs)
print(tokenizer.decode(outputs[0]))
Fill in the Moddle
CodeShell 支持Fill-in-the-Middle模式,从而更好的支持软件开发过程。
input_text = "<fim_prefix>def print_hello_world():\n <fim_suffix>\n print('Hello world!')<fim_middle>"
inputs = tokenizer(input_text, return_tensors='pt').cuda()
outputs = model.generate(inputs)
print(tokenizer.decode(outputs[0]))
Model Quantization
CodeShell 支持4 bit/8 bit量化,4 bit量化后,占用显存大小约6G。
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("codeshell", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("codeshell", trust_remote_code=True)
model = model.quantize(4).cuda()
inputs = tokenizer('def print_hello_world():', return_tensors='pt').cuda()
outputs = model.generate(inputs)
print(tokenizer.decode(outputs[0]))
CodeShell IDE Plugin
Web API
CodeShell提供了Web API部署工具,为IDE插件提供API支持。
git clone git@github.com:WisdomShell/codeshell.git
cd codeshell
python api.py
CodeShell提供了C/C++版本的推理支持,在没有GPU的个人PC上也能高效使用。开发者可以根据本地环境进行编译,详见C/C++本地化部署工具。编译完成后,可以通过下列命令启动Web API服务。
./server -m codeshell.gguf
部署完成后,开发者可以通过Web API进行模型推理:
curl --location 'http://127.0.0.1:8080/completion' --header 'Content-Type: application/json' --data '{"messages": {"content": "用python写个hello world"}, "temperature": 0.2, "stream": true}'
VS Code Plugin
CodeShell提供 VS Code插件,开发者可以通过插件进行代码补全、代码问答等操作。VS Code 插件也已开源,插件相关问题欢迎在VS Code插件仓库中讨论。
Model Details
- 模型架构
- Architecture: GPT-2
- Attention: Grouped-Query Attention with Flash Attention 2
- Position embedding: [Rotary Position Embedding](RoFormer: Enhanced Transformer with Rotary Position Embedding)
- Precision: bfloat16
- 超参数
- n_layer: 42
- n_embd: 4096
- n_inner: 16384
- n_head: 32
- num_query_groups: 8
- seq-length: 8192
- vocab_size: 70144
Code Shell使用GPT-2作为基础架构,并使用Grouped-Query Attention、RoPE相对位置编码等技术。
Evaluation
我们选取了目前最流行的两个代码评测数据集对模型进行评估,与目前最先进的两个7b代码大模型CodeLllama与Starcoder相比,Codeshell 取得了最优的成绩。具体评测结果如下。
Pass@1
| 任务 | codeshell-7B | codellama-7B | starcoderbase-7B |
|---|---|---|---|
| humaneval | 33.48 | 29.44 | 27.80 |
| mbpp | 39.08 | 37.60 | 34.16 |
| multiple-java | 29.56 | 29.24 | 24.30 |
| multiple-js | 33.60 | 31.30 | 27.02 |
License
本仓库开源的模型遵循Apache 2.0 许可证,对学术研究完全开放,若需要商用,开发者可发送邮件进行申请,得到书面授权后方可使用。联系邮箱:wye@pku.edu.cn