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
import torch
import transformers

use_cuda = torch.cuda.is_available()
device = torch.device("cuda" if use_cuda else "cpu")

t5_tokenizer = transformers.GPT2Tokenizer.from_pretrained("AlexWortega/FlanFred")
t5_model = transformers.T5ForConditionalGeneration.from_pretrained("AlexWortega/FlanFred")

def generate_text(input_str, tokenizer, model, device, max_length=50):
    # encode the input string to model's input_ids
    input_ids = tokenizer.encode(input_str, return_tensors='pt').to(device)
    
    # generate text
    with torch.no_grad():
        outputs = model.generate(input_ids=input_ids, max_length=max_length, num_return_sequences=1, temperature=0.7, do_sample=True)
    
    # decode the output and return the text
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

# usage:
input_str = "Hello, how are you?"
print(generate_text(input_str, t5_tokenizer, t5_model, device))

Metrics:

| Metric        | flanfred | siberianfred  | fred  |
| ------------- | ----- |------ |----- |
| xnli_en       | 0.51   |0.49  |0.041 |
| xnli_ru       | 0.71   |0.62 |0.55 |
| xwinograd_ru  | 0.66   |0.51 |0.54 |

Citation

@MISC{AlexWortega/flan_translated_300k,
    author  = {Pavel Ilin, Ksenia Zolian,Ilya kuleshov, Egor Kokush, Aleksandr Nikolich},
    title   = {Russian Flan translated},
    url     = {https://huggingface.co/datasets/AlexWortega/flan_translated_300k},
    year    = 2023
}
Downloads last month
5
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Dataset used to train AlexWortega/FlanFred