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

Libraries

How to use sgolkar/gpt2-finetuned-brookstraining with Transformers:

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

pipe = pipeline("text-generation", model="sgolkar/gpt2-finetuned-brookstraining")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sgolkar/gpt2-finetuned-brookstraining")
model = AutoModelForCausalLM.from_pretrained("sgolkar/gpt2-finetuned-brookstraining")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sgolkar/gpt2-finetuned-brookstraining with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/sgolkar/gpt2-finetuned-brookstraining

SGLang

How to use sgolkar/gpt2-finetuned-brookstraining 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 "sgolkar/gpt2-finetuned-brookstraining" \
    --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": "sgolkar/gpt2-finetuned-brookstraining",
		"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 "sgolkar/gpt2-finetuned-brookstraining" \
        --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": "sgolkar/gpt2-finetuned-brookstraining",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use sgolkar/gpt2-finetuned-brookstraining with Docker Model Runner:
```
docker model run hf.co/sgolkar/gpt2-finetuned-brookstraining
```

gpt2-finetuned-brookstraining

This model is a fine-tuned version of gpt2 on the None dataset. It achieves the following results on the evaluation set:

Loss: 4.3233

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: 8
eval_batch_size: 8
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
No log	1.0	201	3.7473
No log	2.0	402	3.7192
3.9557	3.0	603	3.7303
3.9557	4.0	804	3.7354
3.4723	5.0	1005	3.7725
3.4723	6.0	1206	3.7934
3.4723	7.0	1407	3.8325
3.1092	8.0	1608	3.8907
3.1092	9.0	1809	3.9566
2.8224	10.0	2010	3.9908
2.8224	11.0	2211	4.0487
2.8224	12.0	2412	4.0744
2.5733	13.0	2613	4.1212
2.5733	14.0	2814	4.1872
2.3879	15.0	3015	4.2208
2.3879	16.0	3216	4.2358
2.3879	17.0	3417	4.2799
2.2721	18.0	3618	4.3077
2.2721	19.0	3819	4.3217
2.2043	20.0	4020	4.3233

Framework versions

Transformers 4.27.4
Pytorch 1.13.1
Datasets 2.11.0
Tokenizers 0.11.0

Downloads last month: 5