codeqwen-7b

PyTorch

1 versions

CodeQwen1.5 is a large language model pretrained on a large amount of code data.

Run this model

  1. Install our magic package manager:

    curl -ssL https://magic.modular.com/ | bash

    Then run the source command that's printed in your terminal.

  2. Install Max Pipelines in order to run this model.

    magic global install max-pipelines
  3. Start a local endpoint for codeqwen/7b:

    max-serve serve --huggingface-repo-id Qwen/CodeQwen1.5-7B-Chat

    The endpoint is ready when you see the URI printed in your terminal:

    Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)
  4. Now open another terminal to send a request using curl:

    curl -N http://0.0.0.0:8000/v1/chat/completions -H "Content-Type: application/json" -d '{
        "model": "codeqwen/7b",
        "stream": true,
        "messages": [
            {"role": "system", "content": "You are a helpful assistant."},
            {"role": "user", "content": "Who won the World Series in 2020?"}
        ]
    }' | grep -o '"content":"[^"]*"' | sed 's/"content":"//g' | sed 's/"//g' | tr -d '
    ' | sed 's/\n/
    /g'
  5. ๐ŸŽ‰ Hooray! Youโ€™re running Generative AI. Our goal is to make this as easy as possible.

About

CodeQwen1.5 builds upon Qwen1.5 and is designed as a robust AI model specializing in code-related tasks. Trained on an extensive dataset comprising 3 trillion tokens of code, it exhibits exceptional coding capabilities, making it a competitive choice across a range of benchmarks.

Key Features

  • Advanced Code Generation: Demonstrates strong performance in creating and completing code tasks.
  • Long Context Handling: Supports up to 64,000 tokens for understanding and generating extensive code bases or documentation.
  • Multi-Language Proficiency: Provides support for 92 programming languages, catering to diverse developer needs.
  • Versatile Use Cases: Excels in tasks such as Text-to-SQL conversion, debugging, and other programming-related applications.

References

Blog Post

GitHub

HuggingFace

DETAILS

MODEL CLASS
PyTorch

MODULAR GITHUB

Modular

CREATED BY

Qwen

MODEL

Qwen/CodeQwen1.5-7B-Chat

TAGS

arxiv:2309.16609
autotrain_compatible
chat
code
conversational
en
endpoints_compatible
license:other
qwen2
region:us
safetensors
text-generation
text-generation-inference
transformers

@ Copyright - Modular Inc - 2024