You can deploy this model and start earning money today!

RichardErkhov/
jesseD_-_homer-bot-gguf

Name: jesseD_-_homer-bot-gguf
Rating: 2.5 (61 reviews)

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

homer-bot - GGUF

Model creator: https://huggingface.co/jesseD/
Original model: https://huggingface.co/jesseD/homer-bot/

Name	Quant method	Size
homer-bot.Q2_K.gguf	Q2_K	0.17GB
homer-bot.IQ3_XS.gguf	IQ3_XS	0.18GB
homer-bot.IQ3_S.gguf	IQ3_S	0.19GB
homer-bot.Q3_K_S.gguf	Q3_K_S	0.19GB
homer-bot.IQ3_M.gguf	IQ3_M	0.2GB
homer-bot.Q3_K.gguf	Q3_K	0.21GB
homer-bot.Q3_K_M.gguf	Q3_K_M	0.21GB
homer-bot.Q3_K_L.gguf	Q3_K_L	0.23GB
homer-bot.IQ4_XS.gguf	IQ4_XS	0.22GB
homer-bot.Q4_0.gguf	Q4_0	0.23GB
homer-bot.IQ4_NL.gguf	IQ4_NL	0.23GB
homer-bot.Q4_K_S.gguf	Q4_K_S	0.23GB
homer-bot.Q4_K.gguf	Q4_K	0.25GB
homer-bot.Q4_K_M.gguf	Q4_K_M	0.25GB
homer-bot.Q4_1.gguf	Q4_1	0.25GB
homer-bot.Q5_0.gguf	Q5_0	0.27GB
homer-bot.Q5_K_S.gguf	Q5_K_S	0.27GB
homer-bot.Q5_K.gguf	Q5_K	0.29GB
homer-bot.Q5_K_M.gguf	Q5_K_M	0.29GB
homer-bot.Q5_1.gguf	Q5_1	0.29GB
homer-bot.Q6_K.gguf	Q6_K	0.32GB
homer-bot.Q8_0.gguf	Q8_0	0.41GB

Original model description:

tags:

conversational language:
en

HomerBot: A conversational chatbot imitating Homer Simpson

This model is a fine-tuned DialoGPT (medium version) on Simpsons scripts.

More specifically, we fine-tune DialoGPT-medium for 3 epochs on 10K (character utterance, Homer's response) pairs

For more details, check out our git repo containing all the code.

How to use

python

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch 

tokenizer = AutoTokenizer.from_pretrained("DingleyMaillotUrgell/homer-bot")
model = AutoModelForCausalLM.from_pretrained("DingleyMaillotUrgell/homer-bot")

# Let's chat for 5 lines
for step in range(5):
    # encode the new user input, add the eos_token and return a tensor in Pytorch
    new_user_input_ids = tokenizer.encode(input(">> User: ") + tokenizer.eos_token, return_tensors='pt')
  
    # append the new user input tokens to the chat history
    bot_input_ids = torch.cat([chat_history_ids, new_user_input_ids], dim=-1) if step > 0 else new_user_input_ids

    # generated a response while limiting the total chat history to 1000 tokens, 
    chat_history_ids = model.generate(
        bot_input_ids, 
        max_length=1000,                    
        pad_token_id=tokenizer.eos_token_id,  
        no_repeat_ngram_size=3,
        do_sample=True, 
        top_k=100, 
        top_p=0.7,
        temperature = 0.8
    )
    
    # print last outpput tokens from bot
    print("Homer: {}".format(tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)))

RichardErkhov/jesseD_-_homer-bot-gguf

Original model description:

HomerBot: A conversational chatbot imitating Homer Simpson

How to use

RichardErkhov/
jesseD_-_homer-bot-gguf