Getting Started with WizardLM-1.0-Uncensored-CodeLlama-34b

Nov 20, 2023 • 3 minutes to read

The WizardLM-1.0-Uncensored-CodeLlama-34b is a language model that is based on the CodeLlama-34b architecture, known for its strong coding abilities. This model represents a retraining of the WizardLM-13B-V1.0, utilizing a filtered dataset aimed at reducing refusals, avoidance, and bias in its responses.

In this article, we will cover

  • How to run WizardLM-1.0-Uncensored-CodeLlama-34b on your own device
  • How to create an OpenAI-compatible API service for WizardLM-1.0-Uncensored-CodeLlama-34b

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 | 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

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

That's it. You can chat with the model in the terminal by entering the following command.

wasmedge --dir .:. --nn-preload default:GGML:AUTO:WizardLM-1.0-Uncensored-CodeLlama-34b-ggml-model-q4_0.gguf llama-chat.wasm -p vicuna-chat -s 'You are a helpful AI assistant.'

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 6.82 tokens per second.


Tell me Python code for this nth fibonacci number.


Here is the Python code for the nth Fibonacci number:

def fibonacci(n):
    if n <= 1:
        return n
        return fibonacci(n-1) + fibonacci(n-2)
n = int(input("Enter the value of n: "))
print("The", n, "th Fibonacci number is:", fibonacci(n))

- 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.


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, 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

Then, use the following command lines to start an API server for the model.

wasmedge --dir .:. --nn-preload default:GGML:AUTO:WizardLM-1.0-Uncensored-CodeLlama-34b.Q5_K_M.gguf llama-api-server.wasm -p vicuna

From another terminal, you can interact with the API server using curl.

curl -X POST -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":"WizardLM-1.0-Uncensored-CodeLlama-34b"}'

That’s all. WasmEdge is 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!

LLMAI inferenceRustWebAssembly
A high-performance, extensible, and hardware optimized WebAssembly Virtual Machine for automotive, cloud, AI, and blockchain applications