Instructions to use Langame/distilgpt2-starter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Langame/distilgpt2-starter with Transformers:

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

pipe = pipeline("text-generation", model="Langame/distilgpt2-starter")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Langame/distilgpt2-starter")
model = AutoModelForCausalLM.from_pretrained("Langame/distilgpt2-starter")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Langame/distilgpt2-starter with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Langame/distilgpt2-starter"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Langame/distilgpt2-starter",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Langame/distilgpt2-starter

SGLang

How to use Langame/distilgpt2-starter 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 "Langame/distilgpt2-starter" \
    --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": "Langame/distilgpt2-starter",
		"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 "Langame/distilgpt2-starter" \
        --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": "Langame/distilgpt2-starter",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Langame/distilgpt2-starter with Docker Model Runner:
```
docker model run hf.co/Langame/distilgpt2-starter
```

distilgpt2-starter

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

Loss: 6.0234

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: 5e-05
train_batch_size: 4
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
gradient_accumulation_steps: 2
total_train_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 500.0

Training results

Training Loss	Epoch	Step	Validation Loss
No log	66.67	200	3.6445
No log	133.33	400	4.5703
1.0101	200.0	600	5.2109
1.0101	266.67	800	5.5430
0.0681	333.33	1000	5.7227
0.0681	400.0	1200	5.8672
0.0681	466.67	1400	5.9961

Framework versions

Transformers 4.17.0.dev0
Pytorch 1.10.0+cu111
Datasets 1.18.1
Tokenizers 0.11.0

Downloads last month: 4

Langame
/

distilgpt2-starter

distilgpt2-starter

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Dataset used to train Langame/distilgpt2-starter