Instructions to use TeetouchQQ/ThaiFood-Image-captioning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TeetouchQQ/ThaiFood-Image-captioning with Transformers:

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

pipe = pipeline("image-text-to-text", model="TeetouchQQ/ThaiFood-Image-captioning")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("TeetouchQQ/ThaiFood-Image-captioning")
model = AutoModelForMultimodalLM.from_pretrained("TeetouchQQ/ThaiFood-Image-captioning")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TeetouchQQ/ThaiFood-Image-captioning with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/TeetouchQQ/ThaiFood-Image-captioning

SGLang

How to use TeetouchQQ/ThaiFood-Image-captioning 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 "TeetouchQQ/ThaiFood-Image-captioning" \
    --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": "TeetouchQQ/ThaiFood-Image-captioning",
		"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 "TeetouchQQ/ThaiFood-Image-captioning" \
        --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": "TeetouchQQ/ThaiFood-Image-captioning",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TeetouchQQ/ThaiFood-Image-captioning with Docker Model Runner:
```
docker model run hf.co/TeetouchQQ/ThaiFood-Image-captioning
```

TeetouchQQ commited on Jul 4, 2022

Commit

6ea8292

1 Parent(s): 69a44ff

Upload optimizer.pt

Browse files

Files changed (1) hide show

optimizer.pt +1 -1

optimizer.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2be612340c255b207b49517e226474ae76005832b61309a68246685348b7ac0
 size 1657224497

 version https://git-lfs.github.com/spec/v1
+oid sha256:5191c54e1858ef6eabf9515aded5c40e0e9f70e80ff4816020d76f6cb4cabfb7
 size 1657224497