Commit History
-
Adding `safetensors` variant of this model (#3)
- Adding `safetensors` variant of this model (c895e9c8ec3fd16849d2cbdb1dcf3db13591a46a) Co-authored-by: Safetensors convertbot <SFconvertbot@users.noreply.huggingface.co>b0859c2
-
Update README.md
55175ab -
Update README.md
779f6a7 -
Upload pytorch_model.bin
5482e38 -
Update README.md
2d90b23 -
Update README.md
8cade7d -
Update README.md
1b55c8a -
Upload 6 files
3ef18c9 -
Update README.md
0310dda -
Update README.md
b1d6579 -
Update README.md
c1d685f -
Update README.md
Hey there ***This model is intended for non-commercial use only. If you wish to use it for commercial purposes, please make sure to refer to this LinkedIn address. "Viravirast" is an editor based on transformer algorithms. By visiting the Viravirast.com, you can use a Persian semantic and structural text editor. usage from transformers import ( T5Tokenizer, MT5ForConditionalGeneration, Text2TextGenerationPipeline, ) path = "" pipe = Text2TextGenerationPipeline( model=MT5ForConditionalGeneration.from_pretrained(path), tokenizer=T5Tokenizer.from_pretrained(path), ) sentence = "ویراویراست یک نرم افزار ویرایش متن ساختاری و معنایی زبان فارسی است چیزی شبیه به گرامرلی در زبان انگلیسی" #res = pipe(sentence, max_length=100, num_beams=4) res = pipe(sentence, max_length=100) print(res[0]['generated_text']) n_epochs = 4 train_batch_size = 8 eval_batch_size = 4 lr = 5e-4 Training loss = 0.005501 Validation loss= 0.052046054affb -
initial commit
2fda366