Instructions to use clarin-knext/T5-large-CST-finetuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use clarin-knext/T5-large-CST-finetuned with Transformers:

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

pipe = pipeline("text-generation", model="clarin-knext/T5-large-CST-finetuned")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("clarin-knext/T5-large-CST-finetuned")
model = AutoModelForSeq2SeqLM.from_pretrained("clarin-knext/T5-large-CST-finetuned")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use clarin-knext/T5-large-CST-finetuned with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "clarin-knext/T5-large-CST-finetuned"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "clarin-knext/T5-large-CST-finetuned",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/clarin-knext/T5-large-CST-finetuned

SGLang

How to use clarin-knext/T5-large-CST-finetuned 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 "clarin-knext/T5-large-CST-finetuned" \
    --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": "clarin-knext/T5-large-CST-finetuned",
		"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 "clarin-knext/T5-large-CST-finetuned" \
        --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": "clarin-knext/T5-large-CST-finetuned",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use clarin-knext/T5-large-CST-finetuned with Docker Model Runner:
```
docker model run hf.co/clarin-knext/T5-large-CST-finetuned
```

T5-large-CST-finetuned / README.md

dkurowski

Update README.md

b5d96c9 over 2 years ago

preview code

raw

history blame contribute delete

797 Bytes

metadata

license: cc-by-sa-4.0
datasets:
  - clarin-knext/cst_datasets
language:
  - en
metrics:
  - accuracy
pipeline_tag: text2text-generation
model-index:
  - name: accuracy
    results:
      - task:
          type: text-classification
          name: Text Classification
        metrics:
          - type: accuracy
            value: 63.31
            verified: false
widget:
  - text: >-
      Taking pictures can be straining for the arms. | The photographer is
      massaging her arm, sore from holding the lens.
    example_title: Generalization example
  - text: >-
      The children told their parents that as they were going up to the third
      floor, the escalator stopped. | When we were reaching the third floor, the
      escalator stopped.
    example_title: Indirect speech example

Accuracy per class

TODO

Usage

TODO