Instructions to use gorkemgoknar/gpt2chatbotenglish with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gorkemgoknar/gpt2chatbotenglish with Transformers:

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

pipe = pipeline("text-generation", model="gorkemgoknar/gpt2chatbotenglish")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("gorkemgoknar/gpt2chatbotenglish")
model = AutoModelForCausalLM.from_pretrained("gorkemgoknar/gpt2chatbotenglish")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use gorkemgoknar/gpt2chatbotenglish with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gorkemgoknar/gpt2chatbotenglish"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gorkemgoknar/gpt2chatbotenglish",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/gorkemgoknar/gpt2chatbotenglish

SGLang

How to use gorkemgoknar/gpt2chatbotenglish 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 "gorkemgoknar/gpt2chatbotenglish" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gorkemgoknar/gpt2chatbotenglish",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "gorkemgoknar/gpt2chatbotenglish" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gorkemgoknar/gpt2chatbotenglish",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use gorkemgoknar/gpt2chatbotenglish with Docker Model Runner:
```
docker model run hf.co/gorkemgoknar/gpt2chatbotenglish
```

GPT2 Persona Chatbot based on Movie Characters

Model used for https://www.metayazar.com/chatbot

GPT2 Small Trained on movie scripts (especially Sci-fi)

Usual HF api will not work see HF Spaces for demo usage https://huggingface.co/spaces/gorkemgoknar/moviechatbot

This work is based on Persona Chatbot originally done by Hugging Face team (https://medium.com/huggingface/how-to-build-a-state-of-the-art-conversational-ai-with-transfer-learning-2d818ac26313)

For cleaning movie scripts I also provide cleaner code https://github.com/gorkemgoknar/moviescriptcleaner

Example persona how to: https://gist.github.com/gorkemgoknar/ae29bf9d14fa814e6a64d0e57a4a4ed7

Tried a AI job interview over some characters here, details on this post https://www.linkedin.com/pulse/ai-goes-job-interview-g%C3%B6rkem-g%C3%B6knar/

For obvious reasons I cannot share raw personafile but you can check above gist for example how to create it.

A working "full" demo can be seen in https://www.metayazar.com/chatbot

For Turkish version (with limited training) https://www.metayazar.com/chatbot_tr

Due to double LM head standart hugging face interface will not work. But if you follow huggingface tutorial should be same. Except each persona is encoded as "My name is XXXX"

Use model, tokenizer and parameters within a class and call in below functions to trigger model. Some of the available personas:

    def get_answer(self, input_text, personality, history, params=None):
        
        ##Check length of history (to save 1 computation!)
        if len(history)>0:
            #mostly it will be empty list so need a length check for performance
            #would do string check also but just assume it is list of list of strings, as not public
            
            new_hist = [] 
            for ele in history:
                new_hist.append( self.tokenizer.encode(ele) )
            history = new_hist.copy()

        history.append(self.tokenizer.encode(input_text))

        with torch.no_grad():
            out_ids = self.sample_sequence(personality, history, self.tokenizer, self.model, params=params)
        history.append(out_ids)
        history = history[-(2*self.parameters['max_history']+1):]
        out_text = self.tokenizer.decode(out_ids, skip_special_tokens=True)
        #print(out_text)


        history_decoded = []
        for ele in history:
            history_decoded.append(self.tokenizer.decode(ele))

        return out_text, history_decoded, self.parameters

Downloads last month: 16

Model tree for gorkemgoknar/gpt2chatbotenglish

Finetunes

1 model

gorkemgoknar
/

gpt2chatbotenglish

GPT2 Persona Chatbot based on Movie Characters

Model tree for gorkemgoknar/gpt2chatbotenglish

Spaces using gorkemgoknar/gpt2chatbotenglish 9