Instructions to use liuhaotian/LLaVA-Lightning-MPT-7B-preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use liuhaotian/LLaVA-Lightning-MPT-7B-preview with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="liuhaotian/LLaVA-Lightning-MPT-7B-preview")

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("liuhaotian/LLaVA-Lightning-MPT-7B-preview", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use liuhaotian/LLaVA-Lightning-MPT-7B-preview with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "liuhaotian/LLaVA-Lightning-MPT-7B-preview"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "liuhaotian/LLaVA-Lightning-MPT-7B-preview",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/liuhaotian/LLaVA-Lightning-MPT-7B-preview

SGLang

How to use liuhaotian/LLaVA-Lightning-MPT-7B-preview with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "liuhaotian/LLaVA-Lightning-MPT-7B-preview" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "liuhaotian/LLaVA-Lightning-MPT-7B-preview",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "liuhaotian/LLaVA-Lightning-MPT-7B-preview" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "liuhaotian/LLaVA-Lightning-MPT-7B-preview",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use liuhaotian/LLaVA-Lightning-MPT-7B-preview with Docker Model Runner:
```
docker model run hf.co/liuhaotian/LLaVA-Lightning-MPT-7B-preview
```

Training Instructions

by crystal-technologies - opened Dec 15, 2023

Discussion

crystal-technologies

Dec 15, 2023

Hello! I am extremely impressed by the work that you have done.
I am interested in training my own LLaVa-MPT model using a more higher-end MPT-30B base model, but I cannot seem to find any instructions on how to do so. I have come across various resources that explain the training process using LLaMA models, but not specifically for the MPT. If you could provide any guidance or resources, it would be greatly appreciated.

Thank you very much!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment