RichardErkhov/emre_-_spanish-dialoGPT-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

spanish-dialoGPT - GGUF

• Model creator: https://huggingface.co/emre/
• Original model: https://huggingface.co/emre/spanish-dialoGPT/

Name	Quant method	Size
spanish-dialoGPT.Q2_K.gguf	Q2_K	0.08GB
spanish-dialoGPT.IQ3_XS.gguf	IQ3_XS	0.08GB
spanish-dialoGPT.IQ3_S.gguf	IQ3_S	0.08GB
spanish-dialoGPT.Q3_K_S.gguf	Q3_K_S	0.08GB
spanish-dialoGPT.IQ3_M.gguf	IQ3_M	0.09GB
spanish-dialoGPT.Q3_K.gguf	Q3_K	0.09GB
spanish-dialoGPT.Q3_K_M.gguf	Q3_K_M	0.09GB
spanish-dialoGPT.Q3_K_L.gguf	Q3_K_L	0.1GB
spanish-dialoGPT.IQ4_XS.gguf	IQ4_XS	0.1GB
spanish-dialoGPT.Q4_0.gguf	Q4_0	0.1GB
spanish-dialoGPT.IQ4_NL.gguf	IQ4_NL	0.1GB
spanish-dialoGPT.Q4_K_S.gguf	Q4_K_S	0.1GB
spanish-dialoGPT.Q4_K.gguf	Q4_K	0.11GB
spanish-dialoGPT.Q4_K_M.gguf	Q4_K_M	0.11GB
spanish-dialoGPT.Q4_1.gguf	Q4_1	0.11GB
spanish-dialoGPT.Q5_0.gguf	Q5_0	0.11GB
spanish-dialoGPT.Q5_K_S.gguf	Q5_K_S	0.11GB
spanish-dialoGPT.Q5_K.gguf	Q5_K	0.12GB
spanish-dialoGPT.Q5_K_M.gguf	Q5_K_M	0.12GB
spanish-dialoGPT.Q5_1.gguf	Q5_1	0.12GB
spanish-dialoGPT.Q6_K.gguf	Q6_K	0.13GB
spanish-dialoGPT.Q8_0.gguf	Q8_0	0.17GB

Original model description:

tags: - conversational license: mit datasets: - bigscience/opensubtitles language: - es pipeline_tag: text-generation

Finetuned DialoGPT model on Spanish Conversations

This model was finetuned from the original DialoGPT-medium model on subtitles from Spanish movies and telenovelas from the awesome OpenSubtitle dataset.

DialoGPT paper: https://arxiv.org/abs/1911.00536

Some example dialog from the model:

Role	Response
User	¿Cómo está el clima hoy?
Bot	Muy bien.
User	Eso es bueno escuchar. ¿Vas a ir a la playa?
Bot	No, también puedo regresar.
User	Oh bien, bueno, iré a la playa más tarde.
Bot	¡No!
User	¿Qué está mal con eso?
Bot	¡Cómo que no!
User	Estoy confundido, ¿por qué no puedo ir a la playa?
Bot	¡Cómo que no!
User	Explícamelo por favor.
Bot	¡No!

Using the model

Example code for trying out the model (taken directly from the DialoGPT-medium model card):

from transformers import AutoModelWithLMHead, AutoTokenizer
import torch


tokenizer = AutoTokenizer.from_pretrained("emre/spanish-dialoGPT")
model = AutoModelWithLMHead.from_pretrained("emre/spanish-dialoGPT")

# 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)

    # pretty print last ouput tokens from bot
    print("DialoGPT: {}".format(tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)))