Instructions to use Smaraa/gpt2-text-simplification_1e4_adafactor with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Smaraa/gpt2-text-simplification_1e4_adafactor with Transformers:

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

pipe = pipeline("text-generation", model="Smaraa/gpt2-text-simplification_1e4_adafactor")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Smaraa/gpt2-text-simplification_1e4_adafactor")
model = AutoModelForCausalLM.from_pretrained("Smaraa/gpt2-text-simplification_1e4_adafactor")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Smaraa/gpt2-text-simplification_1e4_adafactor with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Smaraa/gpt2-text-simplification_1e4_adafactor"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Smaraa/gpt2-text-simplification_1e4_adafactor",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Smaraa/gpt2-text-simplification_1e4_adafactor

SGLang

How to use Smaraa/gpt2-text-simplification_1e4_adafactor 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 "Smaraa/gpt2-text-simplification_1e4_adafactor" \
    --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": "Smaraa/gpt2-text-simplification_1e4_adafactor",
		"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 "Smaraa/gpt2-text-simplification_1e4_adafactor" \
        --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": "Smaraa/gpt2-text-simplification_1e4_adafactor",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Smaraa/gpt2-text-simplification_1e4_adafactor with Docker Model Runner:
```
docker model run hf.co/Smaraa/gpt2-text-simplification_1e4_adafactor
```

gpt2-text-simplification_1e4_adafactor

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

Loss: 0.8713

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: 0.0001
train_batch_size: 64
eval_batch_size: 64
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss
0.8976	1.0	2326	0.8092
0.8236	2.0	4652	0.7974
0.7807	3.0	6978	0.7940
0.7428	4.0	9304	0.7916
0.7094	5.0	11630	0.7955
0.6828	6.0	13956	0.7996
0.6569	7.0	16282	0.8046
0.6365	8.0	18608	0.8103
0.616	9.0	20934	0.8175
0.6001	10.0	23260	0.8212
0.5819	11.0	25586	0.8291
0.5688	12.0	27912	0.8368
0.5562	13.0	30238	0.8378
0.5437	14.0	32564	0.8462
0.5299	15.0	34890	0.8497
0.5242	16.0	37216	0.8568
0.5158	17.0	39542	0.8643
0.5088	18.0	41868	0.8676
0.5027	19.0	44194	0.8703
0.4989	20.0	46520	0.8713

Framework versions

Transformers 4.30.2
Pytorch 2.0.1+cu118
Datasets 2.13.1
Tokenizers 0.13.3

Downloads last month: 2