Instructions to use textattack/xlnet-base-cased-RTE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use textattack/xlnet-base-cased-RTE with Transformers:

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

pipe = pipeline("text-generation", model="textattack/xlnet-base-cased-RTE")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("textattack/xlnet-base-cased-RTE")
model = AutoModelForCausalLM.from_pretrained("textattack/xlnet-base-cased-RTE")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use textattack/xlnet-base-cased-RTE with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/textattack/xlnet-base-cased-RTE

SGLang

How to use textattack/xlnet-base-cased-RTE 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 "textattack/xlnet-base-cased-RTE" \
    --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": "textattack/xlnet-base-cased-RTE",
		"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 "textattack/xlnet-base-cased-RTE" \
        --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": "textattack/xlnet-base-cased-RTE",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use textattack/xlnet-base-cased-RTE with Docker Model Runner:
```
docker model run hf.co/textattack/xlnet-base-cased-RTE
```

system HF Staff commited on Jul 6, 2020

Commit

ebc01c0

1 Parent(s): a9d3100

Update README.md

Browse files

Files changed (1) hide show

README.md +10 -0

README.md ADDED Viewed

	@@ -0,0 +1,10 @@

+## TextAttack Model Card
+This `xlnet-base-cased` model was fine-tuned for sequence classification using TextAttack
+and the glue dataset loaded using the `nlp` library. The model was fine-tuned
+for 5 epochs with a batch size of 16, a learning
+rate of 2e-05, and a maximum sequence length of 128.
+Since this was a classification task, the model was trained with a cross-entropy loss function.
+The best score the model achieved on this task was 0.7111913357400722, as measured by the
+eval set accuracy, found after 3 epochs.
+For more information, check out [TextAttack on Github](https://github.com/QData/TextAttack).