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

Libraries

How to use sshleifer/tiny-xlnet-base-cased with Transformers:

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

pipe = pipeline("text-generation", model="sshleifer/tiny-xlnet-base-cased")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sshleifer/tiny-xlnet-base-cased")
model = AutoModelForCausalLM.from_pretrained("sshleifer/tiny-xlnet-base-cased", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sshleifer/tiny-xlnet-base-cased with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/sshleifer/tiny-xlnet-base-cased

SGLang

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

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

tiny-xlnet-base-cased

Commit History

Jul 26, 2023

14:07
Adding `safetensors` variant of this model⁠

SFconvertbot

7b6ed3c

May 8, 2020

15:35
Update spiece.model

system HF Staff

275d2c3
15:35
Update tokenizer_config.json

system HF Staff

542dafd
15:35
Update config.json

system HF Staff

78e22fb
15:35
Update pytorch_model.bin

system HF Staff

0641078
15:35
Update special_tokens_map.json

system HF Staff

4e4a854
15:22
Update tokenizer_config.json

system HF Staff

e5b4baf
15:22
Update spiece.model

system HF Staff

13ec31a
15:22
Update special_tokens_map.json

system HF Staff

7427cc1
15:22
Update config.json

system HF Staff

7eee841
15:22
initial commit

system HF Staff

2aa31ce

Commit History

Jul 26, 2023

Adding `safetensors` variant of this model⁠

May 8, 2020

Update spiece.model

Update tokenizer_config.json

Update config.json

Update pytorch_model.bin

Update special_tokens_map.json

Update tokenizer_config.json

Update spiece.model

Update special_tokens_map.json

Update config.json

initial commit