Instructions to use CoryMagic/wikitext-distill with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CoryMagic/wikitext-distill with Transformers:

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

pipe = pipeline("text-generation", model="CoryMagic/wikitext-distill")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CoryMagic/wikitext-distill")
model = AutoModelForCausalLM.from_pretrained("CoryMagic/wikitext-distill")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use CoryMagic/wikitext-distill with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/CoryMagic/wikitext-distill

SGLang

How to use CoryMagic/wikitext-distill 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 "CoryMagic/wikitext-distill" \
    --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": "CoryMagic/wikitext-distill",
		"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 "CoryMagic/wikitext-distill" \
        --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": "CoryMagic/wikitext-distill",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use CoryMagic/wikitext-distill with Docker Model Runner:
```
docker model run hf.co/CoryMagic/wikitext-distill
```

CoryMagic/wikitext-distill

This model is a fine-tuned version of distilgpt2 on an unknown dataset. It achieves the following results on the evaluation set:

Train Loss: 3.3345
Validation Loss: 3.2376
Epoch: 3

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:

optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
training_precision: float32

Training results

Train Loss	Validation Loss	Epoch
3.5754	3.3649	0
3.4385	3.3004	1
3.3769	3.2633	2
3.3345	3.2376	3

Framework versions

Transformers 4.21.3
TensorFlow 2.9.2
Datasets 2.4.0
Tokenizers 0.12.1

Downloads last month: 3