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

Libraries

How to use mylesmharrison/gpt2-moviedialog with Transformers:

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

pipe = pipeline("text-generation", model="mylesmharrison/gpt2-moviedialog")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mylesmharrison/gpt2-moviedialog")
model = AutoModelForCausalLM.from_pretrained("mylesmharrison/gpt2-moviedialog", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mylesmharrison/gpt2-moviedialog with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/mylesmharrison/gpt2-moviedialog

SGLang

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

Docker Model Runner
How to use mylesmharrison/gpt2-moviedialog with Docker Model Runner:
```
docker model run hf.co/mylesmharrison/gpt2-moviedialog
```

mylesmharrison/gpt2-moviedialog

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

Train Loss: 2.3485
Validation Loss: 2.3753
Epoch: 2

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': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': 1.0, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 4227, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
training_precision: float32

Training results

Train Loss	Validation Loss	Epoch
2.5074	2.4004	0
2.3925	2.3816	1
2.3485	2.3753	2

Framework versions

Transformers 4.31.0
TensorFlow 2.12.0
Datasets 2.14.2
Tokenizers 0.13.3

Downloads last month: 2

Model tree for mylesmharrison/gpt2-moviedialog

Base model

openai-community/gpt2

Finetuned

(2243)

this model

mylesmharrison
/

gpt2-moviedialog

mylesmharrison/gpt2-moviedialog

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Model tree for mylesmharrison/gpt2-moviedialog

Dataset used to train mylesmharrison/gpt2-moviedialog

Space using mylesmharrison/gpt2-moviedialog 1