Instructions to use ali-vosoughi/oscar-llava-v1.5-7b-projector with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ali-vosoughi/oscar-llava-v1.5-7b-projector with Transformers:

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

pipe = pipeline("text-generation", model="ali-vosoughi/oscar-llava-v1.5-7b-projector")

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("ali-vosoughi/oscar-llava-v1.5-7b-projector")
model = AutoModelForMultimodalLM.from_pretrained("ali-vosoughi/oscar-llava-v1.5-7b-projector")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ali-vosoughi/oscar-llava-v1.5-7b-projector with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ali-vosoughi/oscar-llava-v1.5-7b-projector

SGLang

How to use ali-vosoughi/oscar-llava-v1.5-7b-projector 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 "ali-vosoughi/oscar-llava-v1.5-7b-projector" \
    --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": "ali-vosoughi/oscar-llava-v1.5-7b-projector",
		"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 "ali-vosoughi/oscar-llava-v1.5-7b-projector" \
        --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": "ali-vosoughi/oscar-llava-v1.5-7b-projector",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ali-vosoughi/oscar-llava-v1.5-7b-projector with Docker Model Runner:
```
docker model run hf.co/ali-vosoughi/oscar-llava-v1.5-7b-projector
```

OSCaR LLaVA v1.5 7B Projector

This repository contains the projector artifact staged for the OSCaR public release.

Artifact Type

Local staging directory: llava-v1.5-7b-pretrain-projector
Public repo id: ali-vosoughi/oscar-llava-v1.5-7b-projector
Training data condition: projector pretraining assets used before OSCaR LoRA fine-tuning

Files

config.json
mm_projector.bin

Loading

This is a projector-only release. It is intended for the pretraining and fine-tuning workflow documented in the OSCaR code repository.

Example:

bash scripts/train/pretrain_v1_5_13b_projector.sh

Training Configuration

LLaVA v1.5 stack
CLIP ViT-L/336 vision tower
LoRA rank 128
LoRA alpha 256
learning rate 2e-4
1 epoch
max sequence length 2048

Related Resources

Code: https://github.com/nguyennm1024/OSCaR
Dataset: https://huggingface.co/datasets/ali-vosoughi/oscar-dataset
Paper: https://arxiv.org/abs/2402.17128

Downloads last month: 6

Model tree for ali-vosoughi/oscar-llava-v1.5-7b-projector

Base model

openai/clip-vit-large-patch14-336

Finetuned

(33)

this model

Paper for ali-vosoughi/oscar-llava-v1.5-7b-projector

OSCaR: Object State Captioning and State Change Representation

Paper • 2402.17128 • Published Apr 2, 2024