Instructions to use jonastokoliu/image_caption_git-base_pokemon-blip-captions_finetune with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jonastokoliu/image_caption_git-base_pokemon-blip-captions_finetune with Transformers:

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

pipe = pipeline("image-text-to-text", model="jonastokoliu/image_caption_git-base_pokemon-blip-captions_finetune")

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("jonastokoliu/image_caption_git-base_pokemon-blip-captions_finetune")
model = AutoModelForMultimodalLM.from_pretrained("jonastokoliu/image_caption_git-base_pokemon-blip-captions_finetune", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jonastokoliu/image_caption_git-base_pokemon-blip-captions_finetune with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/jonastokoliu/image_caption_git-base_pokemon-blip-captions_finetune

SGLang

How to use jonastokoliu/image_caption_git-base_pokemon-blip-captions_finetune 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 "jonastokoliu/image_caption_git-base_pokemon-blip-captions_finetune" \
    --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": "jonastokoliu/image_caption_git-base_pokemon-blip-captions_finetune",
		"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 "jonastokoliu/image_caption_git-base_pokemon-blip-captions_finetune" \
        --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": "jonastokoliu/image_caption_git-base_pokemon-blip-captions_finetune",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use jonastokoliu/image_caption_git-base_pokemon-blip-captions_finetune with Docker Model Runner:
```
docker model run hf.co/jonastokoliu/image_caption_git-base_pokemon-blip-captions_finetune
```

image_caption_git-base_pokemon-blip-captions_finetune

This model is a fine-tuned version of microsoft/git-base on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.0382
Wer Score: 2.2973

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 50
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Score
7.1973	4.17	50	4.4470	21.4968
2.3075	8.33	100	0.4412	10.5882
0.1359	12.5	150	0.0328	1.5792
0.0188	16.67	200	0.0293	1.1776
0.0068	20.83	250	0.0329	2.0798
0.0023	25.0	300	0.0354	2.6898
0.0014	29.17	350	0.0365	2.5650
0.0012	33.33	400	0.0374	2.4118
0.0011	37.5	450	0.0377	2.4080
0.001	41.67	500	0.0381	2.3745
0.0009	45.83	550	0.0382	2.2857
0.0009	50.0	600	0.0382	2.2973

Framework versions

Transformers 4.29.2
Pytorch 2.0.0+cu117
Datasets 2.12.0
Tokenizers 0.13.3

Downloads last month: 14

Inference Providers NEW

Image-Text-to-Text

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support