Instructions to use shijiay/llava_clip224_stage2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use shijiay/llava_clip224_stage2 with Transformers:

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

pipe = pipeline("image-text-to-text", model="shijiay/llava_clip224_stage2")

# Load model directly
from transformers import AutoProcessor, AutoModelForCausalLM

processor = AutoProcessor.from_pretrained("shijiay/llava_clip224_stage2")
model = AutoModelForCausalLM.from_pretrained("shijiay/llava_clip224_stage2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use shijiay/llava_clip224_stage2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "shijiay/llava_clip224_stage2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "shijiay/llava_clip224_stage2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/shijiay/llava_clip224_stage2

SGLang

How to use shijiay/llava_clip224_stage2 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 "shijiay/llava_clip224_stage2" \
    --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": "shijiay/llava_clip224_stage2",
		"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 "shijiay/llava_clip224_stage2" \
        --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": "shijiay/llava_clip224_stage2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use shijiay/llava_clip224_stage2 with Docker Model Runner:
```
docker model run hf.co/shijiay/llava_clip224_stage2
```

llava_clip224_stage2 / training_args.bin

shijiayang

upload models

6468ac1 almost 2 years ago

download

history blame contribute delete

6.01 kB

This file is stored with Xet . It is too big to display, but you can still download it.

Xet Pointer Details

( Raw pointer file )

Xet hash:: 45d3039b228f10759c29338c3d314164d73bd8b837f5c22a580143b58dfa4baf
Size of remote file:: 6.01 kB
SHA256:: 8ceb41b90c8d1dbdee243c0cddc035eafa2a46f0bda9392b5444b6b6b7fd65d8

Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.

shijiay
/

llava_clip224_stage2

Detected Pickle imports (12)

Xet Pointer Details