WizardCoder is a specialized Large Language Model (LLM) tailored for coding tasks.
In this article, we will cover
- How to run WizardCoder-Python-7B on your own device
- How to create an OpenAI-compatible API service for WizardCoder-Python-7B
We will use the Rust + Wasm stack to develop and deploy applications for this model. There are no complex Python packages or C++ toolchains to install! See why we choose this tech stack.
Run the model on your own device
Step 1: Install WasmEdge via the following command line.
curl -sSf https://raw.githubusercontent.com/WasmEdge/WasmEdge/master/utils/install.sh | bash -s -- --plugins wasmedge_rustls wasi_nn-ggml
Step 2: Download the model GGUF file.It may take a long time, since the size of the model is several GBs.
curl -LO https://huggingface.co/second-state/WizardCoder-Python-7B-V1.0/resolve/main/WizardCoder-Python-7B-V1.0-ggml-model-q4_0.gguf
Step 3: Download a cross-platform portable Wasm file for the chat app. The application allows you to chat with the model on the command line. The Rust source code for the app is here.
curl -LO https://github.com/LlamaEdge/LlamaEdge/releases/latest/download/llama-chat.wasm
That's it. You can chat with the model in the terminal by entering the following command.
wasmedge --dir .:. --nn-preload default:GGML:AUTO:WizardCoder-Python-7B-V1.0-ggml-model-q4_0.gguf llama-chat.wasm -p wizard-coder -s 'Below is an instruction that describes a task. Write a response that appropriately completes the request.'
The portable Wasm app automatically takes advantage of the hardware accelerators (eg GPUs) I have on the device.
On my Mac M1 32G memory device, it clocks in at about 17.51 tokens per second.
[USER]:
Tell me Python code for this nth fibonacci number.
[ASSISTANT]:
Here is the Python code for the nth Fibonacci number:
```python
def fibonacci(n):
if n <= 1:
return n
else:
return fibonacci(n-1) + fibonacci(n-2)
n = int(input("Enter the value of n: "))
print("The", n, "th Fibonacci number is:", fibonacci(n))
Explanation:
- The function `fibonacci()` takes an integer `n’ as input and returns the nth Fibonacci number.
If `n' is less than or equal to 1, it returns `n` itself.
Otherwise, it recursively calls itself with 'n-1' and 'n-2' as arguments and returns the sum of the two results.l The function is called with the value of 'n' entered by the user and the result is printed.
[USER]:
Create an OpenAI-compatible API service
An OpenAI-compatible web API allows the model to work with a large ecosystem of LLM tools and agent frameworks such as flows.network, LangChain and LlamaIndex.
Download an API server app. It is also a cross-platform portable Wasm app that can run on many CPU and GPU devices.
curl -LO https://github.com/LlamaEdge/LlamaEdge/releases/latest/download/llama-api-server.wasm
Then, use the following command lines to start an API server for the model.
wasmedge --dir .:. --nn-preload default:GGML:AUTO:WizardCoder-Python-7B.Q5_K_M.gguf llama-api-server.wasm -p wizard-coder
From another terminal, you can interact with the API server using curl.
curl -X POST http://0.0.0.0:8080/v1/chat/completions -H 'accept:application/json' -H 'Content-Type: application/json' -d '{"messages":[{"role":"system", "content":"You are a helpful AI assistant"}, {"role":"user", "content":"What is the capital of France?"}], "model":"WizardCoder-Python-7B"}'
That’s all. WasmEdge is the easiest, fastest, and safest way to run LLM applications. Give it a try!
Join the WasmEdge discord to ask questions or share insights.
No time to DIY? Book a Demo with us to enjoy your own LLMs across devices!