facebookresearch/DPR
Dense Passage Retriever - is a set of tools and models for open domain Q&A task.
PythonNOASSERTION
Issues
- 6
Missing required positional arguments
#237 opened by grossmanm - 2
'dpr_all_documents' is not defined
#249 opened by golubovic - 0
nanoDPR: simple replication of DPR
#251 opened by Hannibal046 - 0
- 1
A possible bug: Wrong hard_neg_ctx_indices
#248 opened by zhiyuanpeng - 1
Training DPR with different language
#240 opened by shahad2099 - 2
an error occurred in Retriever inference
#211 opened by juyoung228 - 1
How to enter model_file in dense_retriever.py?
#241 opened by tkabir1 - 1
Having error while running train_extractive_reader.py
#242 opened by tkabir1 - 12
IndexError: Dimension out of range
#213 opened by mary-octavia - 0
error about python dense_retriever.py
#245 opened by CodingPeasantzgl - 3
IndexError: Dimension out of range (expected to be in range of [-1, 0], but got 1)
#225 opened by ZiluLii - 0
question: reader loss
#244 opened by PaulLerner - 2
Retriever does not train properly on a custom dataset with empty negative_ctxs and hard_negative_ctxs
#243 opened by yu-rovikov - 1
Data from retriever is not working with reader
#229 opened by UmerTariq1 - 0
Can we get wiki page url by passage id?
#239 opened by heya5 - 0
About dataset generation
#238 opened by Heisenberg-Yin - 1
Unable to reproduce table 3 (Gold-127N) from scratch
#236 opened by xhluca - 0
Passages with multiple answer spans
#233 opened by TZeng20 - 0
`cosine_scores` defined in biencoder.py does not work
#232 opened by xhluca - 1
Question in training reader model.
#231 opened by gaishun - 0
Doubt regarding all_gather_list in case of DDP
#230 opened by bhattg - 0
RuntimeError: Missing key(s) in state_dict: "encoder.embeddings.position_ids"
#228 opened by NehaNishikant - 0
- 1
- 2
Unable to install dependencies
#223 opened by jigsaw2212 - 0
how to test the prediction?
#217 opened by liuchiente - 0
Question about Wikipedia Corpus Preprocessing
#222 opened by manveertamber - 1
NQ Dataset
#221 opened by varshakishore - 1
- 1
Seek Wikipedia corresponding passage ID or dump
#219 opened by jzhoubu - 2
Loss across the nodes....[multi-gpu training]
#218 opened by gabinguo - 3
Hard Negative Indices Issue
#212 opened by khuangaf - 2
How to get ctx_encoder from the checkpoint?
#216 opened by ali-abz - 1
error when python dense_retriever.py
#214 opened by ztx313 - 1
Why does the tokenization part need to set the last token position to sep_token_id?
#210 opened by kwang2049 - 1
- 1
About 'speech_data.py' file in dpr/data
#209 opened by xyltt - 1
Converting checkpoints to HuggingFace format
#207 opened by tanay2001 - 2
Importerror
#206 opened by Facico - 1
Question about reader training
#204 opened by TZeng20 - 2
Weird discontinuities in training
#205 opened by emilysilcock - 1
TypeError: string indices must be integers
#198 opened by Suki-m730026038 - 2
- 2
Question on 'gradient_accumulation_steps'
#201 opened by jzhoubu - 4
Question about answer quality quantification
#200 opened by churinga - 2
Questions about the path of the dev files
#199 opened by unw9527 - 1
about fix_ctx_encoder
#196 opened by wuyaoxuehun - 1
- 2