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

Libraries

How to use testingtime/gpt2-wikitext2 with Transformers:

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

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

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

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use testingtime/gpt2-wikitext2 with vLLM:

Install from pip and serve model

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

Use Docker

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

SGLang

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

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

gpt2-wikitext2

This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 5.1991

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
training_steps: 50000

Training results

Training Loss	Epoch	Step	Validation Loss
6.4398	1.0	2241	6.3596
6.0236	2.0	4482	6.0117
5.6951	3.0	6723	5.7901
5.4821	4.0	8964	5.6291
5.2827	5.0	11205	5.5087
5.1335	6.0	13446	5.4132
4.9653	7.0	15687	5.3436
4.8575	8.0	17928	5.2822
4.7115	9.0	20169	5.2414
4.5957	10.0	22410	5.2125
4.4842	11.0	24651	5.1877
4.3761	12.0	26892	5.1672
4.2879	13.0	29133	5.1585
4.1845	14.0	31374	5.1579
4.1079	15.0	33615	5.1553
4.0398	16.0	35856	5.1583
3.9677	17.0	38097	5.1684
3.8959	18.0	40338	5.1724
3.8508	19.0	42579	5.1800
3.8001	20.0	44820	5.1902
3.7679	21.0	47061	5.1943
3.7323	22.0	49302	5.1982
3.7191	22.3115	50000	5.1991

Framework versions

Transformers 4.44.2
Pytorch 2.4.0+cu121
Datasets 2.21.0
Tokenizers 0.19.1

Downloads last month: 35

Safetensors

Model size

0.1B params

Tensor type

F32

Model tree for testingtime/gpt2-wikitext2

Base model

openai-community/gpt2

Finetuned

(2317)

this model