Instructions to use nide01/pokemon_captions with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nide01/pokemon_captions with Transformers:

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

pipe = pipeline("image-text-to-text", model="nide01/pokemon_captions")

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

processor = AutoProcessor.from_pretrained("nide01/pokemon_captions")
model = AutoModelForMultimodalLM.from_pretrained("nide01/pokemon_captions", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nide01/pokemon_captions with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nide01/pokemon_captions"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nide01/pokemon_captions",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/nide01/pokemon_captions

SGLang

How to use nide01/pokemon_captions 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 "nide01/pokemon_captions" \
    --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": "nide01/pokemon_captions",
		"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 "nide01/pokemon_captions" \
        --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": "nide01/pokemon_captions",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use nide01/pokemon_captions with Docker Model Runner:
```
docker model run hf.co/nide01/pokemon_captions
```

nide01 commited on Nov 21, 2023

Commit

e41b5be

1 Parent(s): dfc6f1a

Training in progress, step 40

Browse files

Files changed (2) hide show

model.safetensors +1 -1
runs/Nov21_07-21-08_Heribertos-MacBook-Pro.local/events.out.tfevents.1700551268.Heribertos-MacBook-Pro.local.10766.0 +2 -2

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac10d7026e034b27f73a3baabb383ff0f64273213687307c0d9238a227d4ff2d
 size 706516040

 version https://git-lfs.github.com/spec/v1
+oid sha256:4e0755ea93d35bc23d99f74106d76f3c7d18473ba8d162a8b194541c38f5b702
 size 706516040

runs/Nov21_07-21-08_Heribertos-MacBook-Pro.local/events.out.tfevents.1700551268.Heribertos-MacBook-Pro.local.10766.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:811ffb4c50883c74bf53eba6a96313d0d59b91be8eaf3589f525a3505abf7ee8
-size 5817

 version https://git-lfs.github.com/spec/v1
+oid sha256:0ac228e464b46598163c3f8c00f740350af44ae63cb11ba050659c9455e97440
+size 6289