YAML Metadata Warning:The pipeline tag "text2text-generation" is not in the official list: text-classification, token-classification, table-question-answering, question-answering, zero-shot-classification, translation, summarization, feature-extraction, text-generation, fill-mask, sentence-similarity, text-to-speech, text-to-audio, automatic-speech-recognition, audio-to-audio, audio-classification, audio-text-to-text, voice-activity-detection, depth-estimation, image-classification, object-detection, image-segmentation, text-to-image, image-to-text, image-to-image, image-to-video, unconditional-image-generation, video-classification, reinforcement-learning, robotics, tabular-classification, tabular-regression, tabular-to-text, table-to-text, multiple-choice, text-ranking, text-retrieval, time-series-forecasting, text-to-video, image-text-to-text, image-text-to-image, image-text-to-video, visual-question-answering, document-question-answering, zero-shot-image-classification, graph-ml, mask-generation, zero-shot-object-detection, text-to-3d, image-to-3d, image-feature-extraction, video-text-to-text, keypoint-detection, visual-document-retrieval, any-to-any, video-to-video, other

Usage

import torch
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

device = "cuda"

tokenizer = AutoTokenizer.from_pretrained('TeraSpace/dialofred')
model = AutoModelForSeq2SeqLM.from_pretrained('TeraSpace/dialofred', device_map=device)# Add torch_dtype=torch.bfloat16 to use less memory
while True:
    text_inp = input("=>")
    lm_text=f'<SC1>- {text_inp}\n- <extra_id_0>'
    input_ids=torch.tensor([tokenizer.encode(lm_text)]).to(model.device)
    # outputs=model.generate(input_ids=input_ids,
    #                                 max_length=200,
    #                                 eos_token_id=tokenizer.eos_token_id,
    #                                 early_stopping=True,
    #                                 do_sample=True,
    #                                 temperature=1.0,
    #                                 top_k=0,
    #                                 top_p=0.85)
    # outputs=model.generate(input_ids,eos_token_id=tokenizer.eos_token_id,early_stopping=True)
    outputs=model.generate(input_ids=input_ids,
                                    max_length=200,
                                    eos_token_id=tokenizer.eos_token_id,
                                    early_stopping=True,
                                    do_sample=True,
                                    temperature=0.7,
                                    top_k=0,
                                    top_p=0.8)
    
    print(tokenizer.decode(outputs[0][1:]))

Downloads last month: 765