Instructions to use Kudod/image-captionning-pokemon with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Kudod/image-captionning-pokemon with Transformers:

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

pipe = pipeline("image-text-to-text", model="Kudod/image-captionning-pokemon")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Kudod/image-captionning-pokemon")
model = AutoModelForMultimodalLM.from_pretrained("Kudod/image-captionning-pokemon", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Kudod/image-captionning-pokemon with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Kudod/image-captionning-pokemon

SGLang

How to use Kudod/image-captionning-pokemon 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 "Kudod/image-captionning-pokemon" \
    --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": "Kudod/image-captionning-pokemon",
		"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 "Kudod/image-captionning-pokemon" \
        --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": "Kudod/image-captionning-pokemon",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Kudod/image-captionning-pokemon with Docker Model Runner:
```
docker model run hf.co/Kudod/image-captionning-pokemon
```

где tokenizer.json?

by JarWithWater - opened 29 days ago

Discussion

JarWithWater

29 days ago

для запуска текстовых ИИ мы обычно используем токенизатор, мы обучаем BPE, и загружаем его на hf, либо загружаем python файл токенизации данной ИИ (смотреть как делать файл токенизации https://huggingface.co/HBB-Community/AntiSpam-v1/blob/main/tokenization_antispam.py, но вы не добавили токенизатор.

пожалуйста, добавьте README.md с ссылкой на токенайзер или залейте токенайзер на hf

хорошего дня

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment