Instructions to use Srish117/gpt2-wikitext2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Srish117/gpt2-wikitext2 with Transformers:

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

pipe = pipeline("text-generation", model="Srish117/gpt2-wikitext2")

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

tokenizer = AutoTokenizer.from_pretrained("Srish117/gpt2-wikitext2")
model = AutoModelForCausalLM.from_pretrained("Srish117/gpt2-wikitext2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Srish117/gpt2-wikitext2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Srish117/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": "Srish117/gpt2-wikitext2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Srish117/gpt2-wikitext2

SGLang

How to use Srish117/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 "Srish117/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": "Srish117/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 "Srish117/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": "Srish117/gpt2-wikitext2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Srish117/gpt2-wikitext2 with Docker Model Runner:
```
docker model run hf.co/Srish117/gpt2-wikitext2
```

gpt2-wikitext2

Commit History

Jan 15, 2025

05:05
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
682aa72

Oct 10, 2023

09:53
update model card README.md

Srish117

e143136
09:53
End of training

Srish117

208c574
09:50
Training in progress, step 6500

Srish117

c5dc82d
09:47
Training in progress, step 6000

Srish117

c822121
09:43
Training in progress, step 5500

Srish117

6c8a873
09:40
Training in progress, step 5000

Srish117

8a08399
09:37
Training in progress, step 4500

Srish117

35f1d1e
09:33
Training in progress, step 4000

Srish117

73bf318
09:30
Training in progress, step 3500

Srish117

bfaa283
09:26
Training in progress, step 3000

Srish117

a8a7cc8
09:23
Training in progress, step 2500

Srish117

88fab6d
09:19
Training in progress, step 2000

Srish117

0b9350f
09:16
Training in progress, step 1500

Srish117

2bc057b
09:12
Training in progress, step 1000

Srish117

898496a
09:09
Training in progress, step 500

Srish117

1674f16
09:06
initial commit

Srish117

aa93c4c

Commit History

Jan 15, 2025

Adding `safetensors` variant of this model⁠

Oct 10, 2023

update model card README.md

End of training

Training in progress, step 6500

Training in progress, step 6000

Training in progress, step 5500

Training in progress, step 5000

Training in progress, step 4500

Training in progress, step 4000

Training in progress, step 3500

Training in progress, step 3000

Training in progress, step 2500

Training in progress, step 2000

Training in progress, step 1500

Training in progress, step 1000

Training in progress, step 500

initial commit