Instructions to use ChayanM/SwinV2-GPT2_Mimic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ChayanM/SwinV2-GPT2_Mimic with Transformers:

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

pipe = pipeline("image-text-to-text", model="ChayanM/SwinV2-GPT2_Mimic")

# Load model directly
from transformers import AutoTokenizer, AutoModelForImageTextToText

tokenizer = AutoTokenizer.from_pretrained("ChayanM/SwinV2-GPT2_Mimic")
model = AutoModelForImageTextToText.from_pretrained("ChayanM/SwinV2-GPT2_Mimic")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ChayanM/SwinV2-GPT2_Mimic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ChayanM/SwinV2-GPT2_Mimic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ChayanM/SwinV2-GPT2_Mimic",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ChayanM/SwinV2-GPT2_Mimic

SGLang

How to use ChayanM/SwinV2-GPT2_Mimic 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 "ChayanM/SwinV2-GPT2_Mimic" \
    --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": "ChayanM/SwinV2-GPT2_Mimic",
		"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 "ChayanM/SwinV2-GPT2_Mimic" \
        --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": "ChayanM/SwinV2-GPT2_Mimic",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ChayanM/SwinV2-GPT2_Mimic with Docker Model Runner:
```
docker model run hf.co/ChayanM/SwinV2-GPT2_Mimic
```

SwinV2-GPT2_Mimic

This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.1623
Rouge1: 30.2654
Rouge2: 21.4825
Rougel: 30.2471
Rougelsum: 30.3167
Gen Len: 9.0

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: 4
eval_batch_size: 4
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	125	0.1705	30.2654	21.4825	30.2471	30.3167	9.0
No log	2.0	250	0.1623	30.2654	21.4825	30.2471	30.3167	9.0

Framework versions

Transformers 4.37.1
Pytorch 1.13.1+cu117
Datasets 2.15.0
Tokenizers 0.15.1

Downloads last month: 3

Safetensors

Model size

0.2B params

Tensor type

F32

Inference Providers NEW

Image-Text-to-Text

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