Instructions to use KunpengSong/MoMA_llava_7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KunpengSong/MoMA_llava_7b with Transformers:

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

pipe = pipeline("text-generation", model="KunpengSong/MoMA_llava_7b")

# Load model directly
from transformers import AutoProcessor, AutoModelForCausalLM

processor = AutoProcessor.from_pretrained("KunpengSong/MoMA_llava_7b")
model = AutoModelForCausalLM.from_pretrained("KunpengSong/MoMA_llava_7b")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use KunpengSong/MoMA_llava_7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KunpengSong/MoMA_llava_7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KunpengSong/MoMA_llava_7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/KunpengSong/MoMA_llava_7b

SGLang

How to use KunpengSong/MoMA_llava_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 "KunpengSong/MoMA_llava_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": "KunpengSong/MoMA_llava_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 "KunpengSong/MoMA_llava_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": "KunpengSong/MoMA_llava_7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use KunpengSong/MoMA_llava_7b with Docker Model Runner:
```
docker model run hf.co/KunpengSong/MoMA_llava_7b
```

KunpengSong commited on Apr 20, 2024

Commit

fa41740

verified ·

1 Parent(s): fd52036

Upload 2 files

Browse files

Files changed (2) hide show

pytorch_model-00001-of-00002.bin +3 -0
pytorch_model-00002-of-00002.bin +3 -0

pytorch_model-00001-of-00002.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:8f9de2fdcef404b761ca8faafc45c70faa1c8f19b375fe7874b83602bd68bf52
+size 9976637886

pytorch_model-00002-of-00002.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:2cfdbbece34b2a19fc5faca9865bb9cbea694d8579e78db37c7ddabf4743499a
+size 4149446034