Instructions to use mikeluck/gpt2-wikitext2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mikeluck/gpt2-wikitext2 with Transformers:

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

pipe = pipeline("text-generation", model="mikeluck/gpt2-wikitext2")

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

tokenizer = AutoTokenizer.from_pretrained("mikeluck/gpt2-wikitext2")
model = AutoModelForCausalLM.from_pretrained("mikeluck/gpt2-wikitext2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mikeluck/gpt2-wikitext2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mikeluck/gpt2-wikitext2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mikeluck/gpt2-wikitext2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mikeluck/gpt2-wikitext2

SGLang

How to use mikeluck/gpt2-wikitext2 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 "mikeluck/gpt2-wikitext2" \
    --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": "mikeluck/gpt2-wikitext2",
		"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 "mikeluck/gpt2-wikitext2" \
        --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": "mikeluck/gpt2-wikitext2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mikeluck/gpt2-wikitext2 with Docker Model Runner:
```
docker model run hf.co/mikeluck/gpt2-wikitext2
```

mikeluck commited on Apr 15, 2022

Commit

60f3743

1 Parent(s): 8f77420

Training in progress, step 231500

Browse files

Files changed (2) hide show

pytorch_model.bin +1 -1
runs/Apr15_10-48-22_P-wxworkBert-01/events.out.tfevents.1649990920.P-wxworkBert-01.4465.0 +2 -2

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc639f5a098d7d271ca20227c34988360f7e617e00308254faea11406ae70346
 size 510404393

 version https://git-lfs.github.com/spec/v1
+oid sha256:f1c34e48d18bb905056330c8f3798f41997e3f93971fbd319d7402e293956952
 size 510404393

runs/Apr15_10-48-22_P-wxworkBert-01/events.out.tfevents.1649990920.P-wxworkBert-01.4465.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95f07e5bf1a70045bcc21263111d1085eee651c07fc38fe1c8d2c80a4e278d9e
-size 133269

 version https://git-lfs.github.com/spec/v1
+oid sha256:a3d225f73b8a49188376a472c27f58da6cc31069903afd477b6a0c835adea547
+size 134025