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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("textattack/xlnet-base-cased-CoLA")
model = AutoModelForMultimodalLM.from_pretrained("textattack/xlnet-base-cased-CoLA")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Use Docker

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

SGLang

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

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

system HF Staff commited on Jul 6, 2020

Commit

7a1385b

1 Parent(s): cadf059

Update config.json

Browse files

Files changed (1) hide show

config.json +2 -2

config.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "architectures": [
-    "XLNetForSequenceClassification"
   ],
   "attn_type": "bi",
   "bi_data": false,
@@ -13,7 +13,7 @@
   "end_n_top": 5,
   "eos_token_id": 2,
   "ff_activation": "gelu",
-  "finetuning_task": "cola",
   "initializer_range": 0.02,
   "layer_norm_eps": 1e-12,
   "mem_len": null,

 {
   "architectures": [
+    "XLNetLMHeadModel"
   ],
   "attn_type": "bi",
   "bi_data": false,
   "end_n_top": 5,
   "eos_token_id": 2,
   "ff_activation": "gelu",
+  "finetuning_task": "glue:cola",
   "initializer_range": 0.02,
   "layer_norm_eps": 1e-12,
   "mem_len": null,