Instructions to use Image-Captioning-ML/TimeSformer-GPT2-UCF-mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Image-Captioning-ML/TimeSformer-GPT2-UCF-mini with Transformers:

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

pipe = pipeline("image-text-to-text", model="Image-Captioning-ML/TimeSformer-GPT2-UCF-mini")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Image-Captioning-ML/TimeSformer-GPT2-UCF-mini")
model = AutoModelForMultimodalLM.from_pretrained("Image-Captioning-ML/TimeSformer-GPT2-UCF-mini")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Image-Captioning-ML/TimeSformer-GPT2-UCF-mini with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Image-Captioning-ML/TimeSformer-GPT2-UCF-mini"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Image-Captioning-ML/TimeSformer-GPT2-UCF-mini",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Image-Captioning-ML/TimeSformer-GPT2-UCF-mini

SGLang

How to use Image-Captioning-ML/TimeSformer-GPT2-UCF-mini 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 "Image-Captioning-ML/TimeSformer-GPT2-UCF-mini" \
    --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": "Image-Captioning-ML/TimeSformer-GPT2-UCF-mini",
		"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 "Image-Captioning-ML/TimeSformer-GPT2-UCF-mini" \
        --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": "Image-Captioning-ML/TimeSformer-GPT2-UCF-mini",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Image-Captioning-ML/TimeSformer-GPT2-UCF-mini with Docker Model Runner:
```
docker model run hf.co/Image-Captioning-ML/TimeSformer-GPT2-UCF-mini
```

TimeSformer-GPT2-UCF-mini / README.md

NourFakih

End of training

93332ee verified over 1 year ago

preview code

Raw

History Blame Contribute Delete

1.66 kB

	---
	library_name: transformers
	base_model: Neleac/SpaceTimeGPT
	tags:
	- generated_from_trainer
	metrics:
	- rouge
	model-index:
	- name: TimeSformer-GPT2-UCF-mini
	results: []
	---

	<!-- This model card has been generated automatically according to the information the Trainer had access to. You
	should probably proofread and complete it, then remove this comment. -->

	# TimeSformer-GPT2-UCF-mini

	This model is a fine-tuned version of [Neleac/SpaceTimeGPT](https://huggingface.co/Neleac/SpaceTimeGPT) on an unknown dataset.
	It achieves the following results on the evaluation set:
	- Loss: 0.3065
	- Rouge1: 23.736
	- Rouge2: 1.0376
	- Rougel: 18.1037
	- Rougelsum: 18.4236
	- Gen Len: 31.2877

	## 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: 2
	- eval_batch_size: 2
	- seed: 42
	- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
	- lr_scheduler_type: linear
	- num_epochs: 3.0

	### Training results

	\| Training Loss \| Epoch \| Step \| Validation Loss \| Rouge1 \| Rouge2 \| Rougel \| Rougelsum \| Gen Len \|
	\|:-------------:\|:------:\|:----:\|:---------------:\|:------:\|:------:\|:-------:\|:---------:\|:-------:\|
	\| 0.1547 \| 2.4876 \| 500 \| 0.3065 \| 23.736 \| 1.0376 \| 18.1037 \| 18.4236 \| 31.2877 \|


	### Framework versions

	- Transformers 4.51.1
	- Pytorch 2.5.1+cu124
	- Datasets 3.5.0
	- Tokenizers 0.21.0