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

Libraries

How to use anezatra/gpt2-conversational with Transformers:

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

pipe = pipeline("text-generation", model="anezatra/gpt2-conversational")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("anezatra/gpt2-conversational")
model = AutoModelForCausalLM.from_pretrained("anezatra/gpt2-conversational")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use anezatra/gpt2-conversational with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/anezatra/gpt2-conversational

SGLang

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

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

GPT-2 Conversational

Model Description

This model is a GPT-2 model that imitates the speech of a normal person. The feature of the model is that it speaks in a normal human voice without knowing that it is an artificial intelligence. Please do not use this model illegally.

Example Generates

Human: Hi!
Robot: Hey there. How are you! How'm doing?
Human: It's good! I spent most of it watching horse racing. How about yourself?
Robot: Yes, I played soccer at an amateur level. That's a great sport. I'm a big fan of the sport!
Human: Interesting! What sort of events do you plan?
Robot: I plan to travel to a lot of places. I'll probably be back in a couple months to learn what to do today, and then resume my work.

Authors

Developed by: Anezatra
Model type: GPT2 (AGI)
Contacts: https://github.com/anezatra

Downloads last month: 2

Safetensors

Model size

0.1B params

Tensor type

F32