Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| import torch | |
| from transformers import (AutoModel, AutoModelForCausalLM, AutoTokenizer, | |
| LlamaForCausalLM, LlamaTokenizer) | |
| title = "🤖AI ChatBot" | |
| description = "A State-of-the-Art Large-scale Pretrained Response generation model (DialoGPT)" | |
| examples = [["How are you?"]] | |
| tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-large") | |
| model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-large") | |
| # tokenizer = LlamaTokenizer.from_pretrained("hf-internal-testing/llama-tokenizer") | |
| # model = LlamaForCausalLM.from_pretrained("hf-internal-testing/llama-tokenizer") | |
| #model = "meta-llama/Llama-2-7b-chat-hf" | |
| #tokenizer = AutoTokenizer.from_pretrained(model) | |
| def predict(input, history=[]): | |
| # tokenize the new input sentence | |
| new_user_input_ids = tokenizer.encode( | |
| input + tokenizer.eos_token, return_tensors="pt" | |
| ) | |
| # append the new user input tokens to the chat history | |
| bot_input_ids = torch.cat([torch.LongTensor(history), new_user_input_ids], dim=-1) | |
| # generate a response | |
| history = model.generate( | |
| bot_input_ids, max_length=4000, pad_token_id=tokenizer.eos_token_id | |
| ).tolist() | |
| # convert the tokens to text, and then split the responses into lines | |
| response = tokenizer.decode(history[0]).split("<|endoftext|>") | |
| # print('decoded_response-->>'+str(response)) | |
| response = [ | |
| (response[i], response[i + 1]) for i in range(0, len(response) - 1, 2) | |
| ] # convert to tuples of list | |
| # print('response-->>'+str(response)) | |
| return response, history | |
| gr.Interface( | |
| fn=predict, | |
| title=title, | |
| description=description, | |
| examples=examples, | |
| inputs=["text", "state"], | |
| outputs=["chatbot", "state"], | |
| # theme="finlaymacklon/boxy_violet", | |
| theme='HaleyCH/HaleyCH_Theme', | |
| ).launch() |