Instructions to use Hyeongdon/t5-large-character_plot_portion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Hyeongdon/t5-large-character_plot_portion with Transformers:

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

pipe = pipeline("text-generation", model="Hyeongdon/t5-large-character_plot_portion")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("Hyeongdon/t5-large-character_plot_portion")
model = AutoModelForSeq2SeqLM.from_pretrained("Hyeongdon/t5-large-character_plot_portion")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Hyeongdon/t5-large-character_plot_portion with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Hyeongdon/t5-large-character_plot_portion"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Hyeongdon/t5-large-character_plot_portion",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Hyeongdon/t5-large-character_plot_portion

SGLang

How to use Hyeongdon/t5-large-character_plot_portion 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 "Hyeongdon/t5-large-character_plot_portion" \
    --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": "Hyeongdon/t5-large-character_plot_portion",
		"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 "Hyeongdon/t5-large-character_plot_portion" \
        --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": "Hyeongdon/t5-large-character_plot_portion",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Hyeongdon/t5-large-character_plot_portion with Docker Model Runner:
```
docker model run hf.co/Hyeongdon/t5-large-character_plot_portion
```

Purpose

As a part of a project assignment in EPFL's CS-401 class, we need a simple model to extract the importance of the character from the movie plot. From the movie script data crawled from https://imsdb.com/, we calculated gold portion of each character over entire script, and joined it with movie plot datasets.

Model info

Input prompt format

f"Predict the percentage of a movie's plot that a character takes up.\nCharacter: {character_name} \nPlot: {plot}"

Output

13.4

We used max_token = 2048 for training.

| Sample code

tokenizer = T5Tokenizer.from_pretrained("Hyeongdon/t5-large-character_plot_portion") # same as default t5 tokenizer
model = T5ForConditionalGeneration.from_pretrained("Hyeongdon/t5-large-character_plot_portion")
model_inputs = tokenizer(prompts, max_length=2048, truncation=True, padding='max_length', return_tensors='pt')
model.eval()
with torch.no_grad():
    probs = model.generate(input_ids=model_inputs['input_ids'].to(device), attention_mask=model_inputs['attention_mask'].to(device))

Limitation & Tips

ChatGPT shows better performance without any fine-tuning. Based on our internal metric, T5-large slightly underperforms compared to GPT-3.5 or GPT-4. If you are interested in our research project, refer https://margg00.github.io/

Downloads last month: 5

Safetensors

Model size

0.7B params

Tensor type

F32