AkariAsai/self-rag

Issues

• some problem with run_long_form_static.py

  #76 opened 8 months ago by pzwstudy
  1

• CUDA Memory is not enough

  #84 opened 7 months ago by zhongruizhe123
  2

• Multi-card distribution training problem

  #94 opened 2 months ago by fmk345
  0

• What does YOUR_INPUT_FILE look like? Can you provide an example? Thanks very much!

  #65 opened 9 months ago by XiaozhuLove
  3

• Source of the wikipedia documents

  #93 opened 2 months ago by tengerye
  0

• Why could not train the generator directly?

  #92 opened 3 months ago by tengerye
  0

• indexSelectLargeIndex: block: [654,0,0], thread: [32,0,0] Assertion `srcIndex < srcSelectDimSize` failed.

  #91 opened 3 months ago by ahmadmustafaanis
  0

• Cannot reproduce baseline tasks?

  #44 opened a year ago by AllenShow
  5

• Questions about Beam search algorithim

  #90 opened 3 months ago by gabbyzyk
  1

• About bio eval

  #87 opened 3 months ago by aJupyter
  1

• FactScore Inference Fails with KeyError: 'original_splitted_sentences'

  #79 opened 8 months ago by hideaki-j
  2

• dependency

  #82 opened 7 months ago by n-m-h
  2

• Max_logprobs and logprobs value

  #85 opened 6 months ago by ShreyPandit
  1

• question about multi content reference

  #88 opened 5 months ago by 256785
  2

• How can I get initial input file for generator?

  #68 opened 9 months ago by hummingbird2030
  0

• Incorrect setup of Learning Rate Scheduler

  #81 opened 7 months ago by aswathn1
  6

• How to curate the preceding sentences? and Can you inform the distribution of IsUse token (1~5)?

  #86 opened 6 months ago by MSungK
  0

• The meaning of "_w_gs.jsonl" in evaluation data

  #58 opened 10 months ago by qiweijian
  2

• Processed Input Dataset and Flan-3B Critic Generated Dataset

  #70 opened 9 months ago by ShayekhBinIslam
  0

• torch.distributed.elastic.multiprocessing.api: [ERROR] failed (exitcode: -9) local_rank: 0 (pid: 14447) of binary:

  #83 opened 7 months ago by zhongruizhe123
  2

• I have create a virtual enviroment in anaconda. However, something went wrong when i try to 'pip install -r requirement'

  #62 opened 10 months ago by Fangzhou-Code
  2

• The critic model will generate different type of token when I use run_reward_vllm.py to generate tokens

  #75 opened 8 months ago by Teng0828
  1

• Retrieval-augmented baselines - Huggingface models

  #61 opened 10 months ago by mozhu621
  4

• accuracy metric

  #72 opened 9 months ago by zhuzihan728
  3

• How is the jsonl file in the eval_data built, thank you very much!

  #56 opened 10 months ago by Gera001
  5

• Question Regarding Formula Error in Your Paper

  #78 opened 8 months ago by littleblueprince
  0

• Cannot approach the performance of the uploaded self-rag ckpt when finetuning meta/Llama-2 myself

  #57 opened 10 months ago by HazekiahWon
  5

• Data formatting to call the retriever

  #77 opened 8 months ago by lauhaide
  0

• About parameter `max_depth`

  #73 opened 9 months ago by LYCnight
  2

• Doesn't the generator need to call the retriever when training the model?

  #74 opened 8 months ago by liumc14
  0

• About PopQA

  #45 opened a year ago by AllenShow
  1

• Explanation needed for [Continue to Use Evidence]

  #66 opened 9 months ago by zhuzihan728
  1

• Reproducing Self-RAG

  #71 opened 9 months ago by 201736621051
  0

• model issues

  #69 opened 9 months ago by BlackHandsomeLee
  0

• How long does it takes to train an epoch for critic/generator model on llama-7B with 8 A100?

  #64 opened 9 months ago by hummingbird2030
  0

• 4 bit quantized version of 7B?

  #63 opened 10 months ago by djkazic
  0

• custom datset help

  #47 opened a year ago by drewskidang
  2

• Are these two code files the same thing?

  #41 opened 10 months ago by AllenShow
  1

• Question about the pre-given passages

  #51 opened a year ago by WenzhengZhang
  1

• About save_merged_lora_model

  #54 opened 10 months ago by AllenShow
  1

• Questions about Critic model

  #60 opened 10 months ago by leejaehoon1830
  2

• For ASQA, how to reproduce the baseline?

  #43 opened a year ago by AllenShow
  1

• Where does the retrieval done?

  #59 opened 10 months ago by sutakori
  0

• 请问eval_data中的jsonl文件是怎么构建的，非常感谢！

  #55 opened 10 months ago by Gera001
  0

• Build data for critic model

  #49 opened a year ago by freeyangHaha
  2

• How to fix the bug about 'local variable 'pred' referenced before assignment'?

  #50 opened a year ago by AllenShow
  0

• Out of memory at inference in free tier Google Colab

  #48 opened a year ago by sudhir2016
  0

• Is it possible to get custom dataset

  #46 opened a year ago by drewskidang
  1

• About baseline's parameter 'task'

  #42 opened a year ago by AllenShow
  1

• Bug report & Self-RAG never predicts `[Retrieval]` when set `threshold=None`

  #40 opened a year ago by ZhangzihanGit
  0