Instructions to use devjwsong/gpt2-open-domain-dialogue with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use devjwsong/gpt2-open-domain-dialogue with Transformers:

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

pipe = pipeline("text-generation", model="devjwsong/gpt2-open-domain-dialogue")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("devjwsong/gpt2-open-domain-dialogue")
model = AutoModelForCausalLM.from_pretrained("devjwsong/gpt2-open-domain-dialogue", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use devjwsong/gpt2-open-domain-dialogue with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/devjwsong/gpt2-open-domain-dialogue

SGLang

How to use devjwsong/gpt2-open-domain-dialogue 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 "devjwsong/gpt2-open-domain-dialogue" \
    --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": "devjwsong/gpt2-open-domain-dialogue",
		"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 "devjwsong/gpt2-open-domain-dialogue" \
        --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": "devjwsong/gpt2-open-domain-dialogue",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use devjwsong/gpt2-open-domain-dialogue with Docker Model Runner:
```
docker model run hf.co/devjwsong/gpt2-open-domain-dialogue
```

Model Card for Model ID

This model is based on GPT2LMHeadModel which has been trained with a total of 4 open-domain dialogue dataset.

Model Details

The details can be found on my blog posts:

Model Description

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

Developed by: devjwsong
Model type: GPT2LMHeadModel
Language(s) (NLP): English
License: MIT
Finetuned from model [optional]: openai-community/gpt2

Model Sources

Repository: https://github.com/devjwsong/gpt2-dialogue-generation-pytorch

Citation

Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., & Sutskever, I. (2019). Language models are unsupervised multitask learners. OpenAI blog, 1(8), 9.
https://songstudio.info/tech/tech-33
https://songstudio.info/tech/tech-35

BibTeX:

@misc{Song_2020,
  title={Multi-turn chatbot project (3): GPT-2 chatbot with multi-turn generation settings},
  url={https://songstudio.info/tech/tech-35},
  journal={SongStudio},
  author={Song, Jaewoo},
  year={2020},
  month={Nov}
}

devjwsong
/

gpt2-open-domain-dialogue

Model Card for Model ID

Model Details

Model Description

Model Sources

Citation

Model Card Authors

Model Card Contact

Datasets used to train devjwsong/gpt2-open-domain-dialogue