internlm2-1m

PyTorch

4 versions

InternLM2.5 is a 7B parameter model tailored for practical scenarios with outstanding reasoning capability.

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 internlm2/1m:

    max-serve serve --huggingface-repo-id internlm/internlm2_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": "internlm2/1m",
        "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

internLM logo

InternLM2.5 has released an open-source 7 billion parameter base model and a chat model optimized for practical applications. The model stands out with the following features:

  • Outstanding reasoning capability: It delivers state-of-the-art performance in mathematical reasoning, surpassing models like Llama3 and Gemma2-9B.

  • Stronger tool use: InternLM2.5 excels in leveraging tools for tasks like instruction following, tool selection, and reflection. It supports gathering information from over 100 web pages, with implementation soon to be available in Lagent.

  • Deep thinking capability: InternLM3 supports both the deep thinking mode for solving complicated reasoning tasks via the long chain-of-thought and the normal response mode for fluent user interactions.

Reference

GitHub

Hugging Face

DETAILS

MODEL CLASS
PyTorch

MODULAR GITHUB

Modular

CREATED BY

internlm

MODEL

internlm/internlm2_5-7b-chat

TAGS

arxiv:2403.17297
autotrain_compatible
conversational
custom_code
internlm2
license:other
region:us
safetensors
text-generation
transformers

@ Copyright - Modular Inc - 2024