Instructions to use aisuko/ft-distilGPT2-with-ELI5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aisuko/ft-distilGPT2-with-ELI5 with Transformers:

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

pipe = pipeline("text-generation", model="aisuko/ft-distilGPT2-with-ELI5")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("aisuko/ft-distilGPT2-with-ELI5")
model = AutoModelForCausalLM.from_pretrained("aisuko/ft-distilGPT2-with-ELI5")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use aisuko/ft-distilGPT2-with-ELI5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aisuko/ft-distilGPT2-with-ELI5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aisuko/ft-distilGPT2-with-ELI5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/aisuko/ft-distilGPT2-with-ELI5

SGLang

How to use aisuko/ft-distilGPT2-with-ELI5 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 "aisuko/ft-distilGPT2-with-ELI5" \
    --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": "aisuko/ft-distilGPT2-with-ELI5",
		"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 "aisuko/ft-distilGPT2-with-ELI5" \
        --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": "aisuko/ft-distilGPT2-with-ELI5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use aisuko/ft-distilGPT2-with-ELI5 with Docker Model Runner:
```
docker model run hf.co/aisuko/ft-distilGPT2-with-ELI5
```

ft-distilGPT2-with-ELI5

This model is a fine-tuned version of distilgpt2 on the None dataset. It achieves the following results on the evaluation set:

Loss: 3.9586

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: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	16	3.9655
No log	2.0	32	3.9544
No log	3.0	48	3.9496
No log	4.0	64	3.9508
No log	5.0	80	3.9515
No log	6.0	96	3.9527
No log	7.0	112	3.9549
No log	8.0	128	3.9564
No log	9.0	144	3.9582
No log	10.0	160	3.9586

Framework versions

Transformers 4.35.2
Pytorch 2.0.0
Datasets 2.15.0
Tokenizers 0.14.1

Downloads last month: 6

Safetensors

Model size

81.9M params

Tensor type

F32

Model tree for aisuko/ft-distilGPT2-with-ELI5

Base model

distilbert/distilgpt2

Finetuned

(1523)

this model