Instructions to use q-future/co-instruct-llava-v1.5-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use q-future/co-instruct-llava-v1.5-7b with Transformers:

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

pipe = pipeline("text-generation", model="q-future/co-instruct-llava-v1.5-7b")

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("q-future/co-instruct-llava-v1.5-7b", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use q-future/co-instruct-llava-v1.5-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "q-future/co-instruct-llava-v1.5-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "q-future/co-instruct-llava-v1.5-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/q-future/co-instruct-llava-v1.5-7b

SGLang

How to use q-future/co-instruct-llava-v1.5-7b 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 "q-future/co-instruct-llava-v1.5-7b" \
    --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": "q-future/co-instruct-llava-v1.5-7b",
		"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 "q-future/co-instruct-llava-v1.5-7b" \
        --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": "q-future/co-instruct-llava-v1.5-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use q-future/co-instruct-llava-v1.5-7b with Docker Model Runner:
```
docker model run hf.co/q-future/co-instruct-llava-v1.5-7b
```

Training the Co-Instruct-562K dataset with LLaVA-1.5-7B to facilitate users that prefer the LLaVA structure.

It is notably less accurate than the main version: https://huggingface.co/q-future/co-instruct, please refer to that checkpoint if you want a more accurate model.

Preliminary Results:

Q-Bench-Single-MCQ (A1, test): 73.38% (Co-Instruct-Main: 77.11%, GPT-4V-Turbo: 74.10%, Q-Instruct-LLaVA-v1.5: 67.42%, LLaVA-v1.5: 60.07%)
Q-Bench-Pair-MCQ (A1, test): 75.88% (Co-Instruct-Main: 80.18%, GPT-4V-Turbo: 78.07%, Q-Instruct-LLaVA-v1.5: 54.50%, LLaVA-v1.5: 52.25%)

We are working on improving it in the future but we also warn that this structure (direct projection) might not be very friendly to multi-image scenarios.

Downloads last month: 4

Safetensors

Model size

7B params

Tensor type

BF16

Dataset used to train q-future/co-instruct-llava-v1.5-7b

Paper for q-future/co-instruct-llava-v1.5-7b

Towards Open-ended Visual Quality Comparison

Paper • 2402.16641 • Published Feb 26, 2024 • 17