Choose Version

(2 versions)

MAX Model

GPU

This version is not quantized and a GPU is recommended.

Install our magic package manager:
```
curl -ssL https://magic.modular.com/ | bash
```
Then run the source command that's printed in your terminal.

Install Max Pipelines in order to run this model.

magic global install max-pipelines && magic global update

Start a local endpoint for vicuna-delta-v0/7B:

max-pipelines serve --huggingface-repo-id=lmsys/vicuna-7b-delta-v0

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

Server ready on http://0.0.0.0:8000 (Press CTRL+C to quit)

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": "lmsys/vicuna-7b-delta-v0",
    "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'

🎉 Hooray! You’re running Generative AI. Our goal is to make this as easy as possible.

Deploy this model to cloud

Vicuna Model Card

Model Details

Vicuna is developed as a chat assistant by fine-tuning the LLaMA model on conversations from ShareGPT.

Developed by: LMSYS
Model type: An auto-regressive language model founded on transformer architecture.
License: Non-commercial license
Finetuned from model: LLaMA

Model Sources

Repository: GitHub Repository
Blog: LMSYS Blog
Paper: Research Paper
Demo: Live Demo

Uses

Vicuna is primarily used for research in large language models and chatbots, targeting researchers and hobbyists in natural language processing, machine learning, and artificial intelligence sectors.

How to Get Started with the Model

Command Line Interface: Vicuna Weights
APIs: API Integration

Training Details

Vicuna v0 is derived from LLaMA, using supervised instruction fine-tuning. It was trained on approximately 70,000 conversations from ShareGPT.com. For detailed information, refer to the appendix in this paper.

Evaluation

The Vicuna model is evaluated using standard benchmarks, human preference ratings, and LLM-as-a-judge methodology. Further insights are available in the research paper and comparison leaderboard.

Differences Between Versions

For updates and version differences of Vicuna, refer to vicuna_weights_version.md.

Citations

Please refer to the following papers for more detailed insights:

LLaMA: Research Paper
Vicuna: Research Paper

Metadata

architectures.0	LlamaForCausalLM
model_type	llama

Version: 7B GPU undefined

This code works on compatible Linux machines.
We are actively working on enabling MAX Serve for MacOS ARM64 as well.

You can quickly deploy vicuna-delta-v0-7B to an endpoint using our MAX container. It includes the latest version of MAX with GPU support and our Python-based inference server called MAX Serve.

With the following Docker command, you’ll get an OpenAI-compatible endpoint running vicuna-delta-v0-7B:

docker run --gpus 1 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_HUB_ENABLE_HF_TRANSFER=1" \
    --env "HF_TOKEN=" \
    -p 8000:8000 \
    docker.modular.com/modular/max-openai-api:nightly \
    --huggingface-repo-id lmsys/vicuna-7b-delta-v0

In order to download the model from Hugging Face, you just need to fill in the HF_TOKEN value with your access token, unless the model is from https://huggingface.co/modularai.

Learn more

For more information about the container image, see the MAX container documentation.

To learn more about how to deploy MAX to the cloud, check out our MAX Serve tutorials.

Developed by: LMSYS
Model type: An auto-regressive language model based on the transformer architecture.
License: Non-commercial license
Finetuned from model: LLaMA.

DETAILS

ChatMODEL CLASS

MAX Model

MAX Models are popular open-source models converted to MAX’s native graph format. Anything with the label is either SOTA or being worked on. Learn more about MAX Models.

Browse all MAX Models

HARDWARE

GPU

QUANTIZATION

ARCHITECTURE

MAX Model

MAX GITHUB

Modular / MAX

MODEL

lmsys

lmsys/vicuna-7b-delta-v0

QUESTIONS ABOUT THIS MODEL?

Resources & support for
running vicuna-delta-v0-7B

Browse 27+ Tutorials

View Tutorials

Get help using MAX

Modular Forum

Read Documentation

Go to Docs

vicuna-delta-v0-7B

Vicuna Model Card

Model Details

Model Sources

Uses

How to Get Started with the Model

Training Details

Evaluation

Differences Between Versions

Citations

Metadata

Learn more

Resources & support for running vicuna-delta-v0-7B

Resources & support for
running vicuna-delta-v0-7B