microsoft/ProphetNet
A research project for natural language generation, containing the official implementations by MSRA NLC team.
PythonMIT
Issues
- 0
- 0
AI Augmented Cloud Administration Of Justice
#85 opened by RonWiseAI - 0
- 2
Unable to load the GENIE model
#64 opened by CSerxy - 1
- 3
(AR-Diffusion) RuntimeError: Error(s) in loading state_dict for CrossAttention_Diffusion_LM
#78 opened by hwaseem04 - 4
- 1
The datasets have no dev set?
#65 opened by lcc0504 - 2
AR-Diffusion data.name and exp.name
#75 opened by AIgods - 3
- 3
- 0
Request the execution code of llama2
#76 opened by AnonymousLYZYY - 1
- 1
Unable to run Genie_Finetune.py
#70 opened by xiang-xiang-zhu - 1
Question for GENIE Finetuning, how to specify epochs for training/finetuning?
#72 opened by SpaceHunterInf - 1
Missing key documents for AR-Diffusion
#68 opened by BiinRw - 1
where is "mbr_select.py" in AR-Diffusion
#69 opened by Jeongwan-Shin - 4
It seems that the core code of CRITIC, particularly the part involving Google API search, is not implemented
#67 opened by zyg18181818 - 1
- 5
Where to obtain the test.tgt for CNN/DM data
#56 opened by BaohaoLiao - 1
- 0
Character level
#62 opened by striver123456 - 1
Why is the GENIE result in AR-diffusion very different from the original paper? Also, you come from a team.
#61 opened by zhaijianyang - 0
Can use_fp16 be used?
#59 opened by zhaijianyang - 2
- 1
The reported scores of GENIE are not fair
#57 opened by BaohaoLiao - 1
KeyError during inference with dialog-en model
#49 opened by raviteja5 - 1
Train new model
#46 opened by stoicity - 0
How to pretrain the ProphetNet?
#54 opened by thomas-li-sjtu - 0
- 0
How to use ProphetNetX in other languages like Vietnamese? How to preprocess the data?
#45 opened by stoicity - 0
- 0
Wrong Tokenization in SquadQG Evaluation Scripts
#50 opened by hzhwcmhf - 2
- 1
- 0
Where can I get the evaluation script for English Dialog, including the AVG?
#47 opened by FlyingCat-fa - 3
KeyError: 'best_loss' at inference while using prophetnet code pretrained checkpoints.
#44 opened by anks12297 - 0
Official implementation of Huggingface version
#42 opened by Doragd - 0
- 5
Is there any instructions to create models for text summarization in other languages (Vietnamese for example)?
#41 opened by stoicity - 3
Train model for Vietnamese summarization
#36 opened by stoicity - 1
About ProphetNet_Code's README
#40 opened by ppaulggit - 0
Inference AttributeError: 'Namespace' object has no attribute 'max_source_positions'
#39 opened by LuRuz - 0
Variables needed for gradient computation should be modified by an inplace operation.
#38 opened by aleversn - 2
- 0
How I can build models for other languages?
#34 opened by stoicity - 0
- 0
chinese
#33 opened by Wang-Yufei - 2
Assertion Error in fine-tuning of Gigaword
#31 opened by takase - 0