command-r-35b

PyTorch

1 versions

Command R is a Large Language Model optimized for conversational interaction and long context tasks.

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 command-r/35b:

    max-serve serve --huggingface-repo-id CohereForAI/c4ai-command-r-v01

    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": "command-r/35b",
        "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. 🎉 Hooray! You’re running Generative AI. Our goal is to make this as easy as possible.

About

Command R is a generative model designed for long context tasks, excelling in retrieval-augmented generation (RAG) and the integration of external APIs and tools. Developed for enterprise-scale deployment, Command R provides:

  • High accuracy in RAG and tool integration
  • Low latency with high throughput
  • Extended context window of 128k tokens
  • Robust performance across 10 major languages

The model is tailored for businesses requiring reliable, high-performing AI systems capable of handling large-scale applications. Command R demonstrates exceptional proficiency in efficiently processing extensive contexts while maintaining strong multilingual functionality.

Two versions are available:

  • v0.1: The original release
  • 08-2024: Updated version launched in August 2024

For additional details, visit the following resources:

DETAILS

MODEL CLASS
PyTorch

MODULAR GITHUB

Modular

CREATED BY

CohereForAI

MODEL

CohereForAI/c4ai-command-r-v01

TAGS

ar
autotrain_compatible
cohere
conversational
de
doi:10.57967/hf/3139
en
es
fr
it
ja
ko
license:cc-by-nc-4.0
pt
region:us
safetensors
text-generation
text-generation-inference
transformers
zh

@ Copyright - Modular Inc - 2024