Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / AkariAsai/self-rag issues and pull requests
#98 - After insert special tokens,Have changed lm_head dimension?
Issue -
State: open - Opened by wyclike about 1 month ago
- 1 comment
#97 - ARC accuracy metric Reproduction
Issue -
State: open - Opened by jiaweif3ng about 2 months ago
#96 - query about PopQA Wikipedia corpus
Issue -
State: open - Opened by lauhaide about 2 months ago
#95 - training_special_tokens skip loss
Issue -
State: open - Opened by Hanzhang-lang 2 months ago
#94 - Multi-card distribution training problem
Issue -
State: open - Opened by fmk345 3 months ago
#93 - Source of the wikipedia documents
Issue -
State: open - Opened by tengerye 3 months ago
#92 - Why could not train the generator directly?
Issue -
State: open - Opened by tengerye 3 months ago
#91 - indexSelectLargeIndex: block: [654,0,0], thread: [32,0,0] Assertion `srcIndex < srcSelectDimSize` failed.
Issue -
State: open - Opened by ahmadmustafaanis 4 months ago
- 2 comments
#90 - Questions about Beam search algorithim
Issue -
State: open - Opened by gabbyzyk 4 months ago
- 1 comment
#89 - Update chatgpt_groundness.py
Pull Request -
State: open - Opened by yanfangli85 5 months ago
#88 - question about multi content reference
Issue -
State: open - Opened by 256785 6 months ago
- 2 comments
#87 - About bio eval
Issue -
State: open - Opened by aJupyter 7 months ago
- 1 comment
#87 - About bio eval
Issue -
State: closed - Opened by aJupyter 7 months ago
- 1 comment
#86 - How to curate the preceding sentences? and Can you inform the distribution of IsUse token (1~5)?
Issue -
State: open - Opened by MSungK 7 months ago
#86 - How to curate the preceding sentences? and Can you inform the distribution of IsUse token (1~5)?
Issue -
State: open - Opened by MSungK 7 months ago
#85 - Max_logprobs and logprobs value
Issue -
State: open - Opened by ShreyPandit 7 months ago
- 1 comment
#85 - Max_logprobs and logprobs value
Issue -
State: open - Opened by ShreyPandit 7 months ago
- 1 comment
#84 - CUDA Memory is not enough
Issue -
State: open - Opened by zhongruizhe123 8 months ago
- 2 comments
#83 - torch.distributed.elastic.multiprocessing.api: [ERROR] failed (exitcode: -9) local_rank: 0 (pid: 14447) of binary:
Issue -
State: open - Opened by zhongruizhe123 8 months ago
- 2 comments
#82 - dependency
Issue -
State: open - Opened by n-m-h 8 months ago
- 2 comments
#82 - dependency
Issue -
State: open - Opened by n-m-h 8 months ago
- 2 comments
#81 - Incorrect setup of Learning Rate Scheduler
Issue -
State: open - Opened by aswathn1 8 months ago
- 6 comments
#81 - Incorrect setup of Learning Rate Scheduler
Issue -
State: open - Opened by aswathn1 8 months ago
- 6 comments
#80 - Update run_short_form.py
Pull Request -
State: open - Opened by ai-leehm 9 months ago
#80 - Update run_short_form.py
Pull Request -
State: open - Opened by ai-leehm 9 months ago
#79 - FactScore Inference Fails with KeyError: 'original_splitted_sentences'
Issue -
State: open - Opened by hideaki-j 9 months ago
- 2 comments
#79 - FactScore Inference Fails with KeyError: 'original_splitted_sentences'
Issue -
State: open - Opened by hideaki-j 9 months ago
- 2 comments
#78 - Question Regarding Formula Error in Your Paper
Issue -
State: open - Opened by littleblueprince 9 months ago
#77 - Data formatting to call the retriever
Issue -
State: open - Opened by lauhaide 9 months ago
#76 - some problem with run_long_form_static.py
Issue -
State: closed - Opened by pzwstudy 9 months ago
- 1 comment
#75 - The critic model will generate different type of token when I use run_reward_vllm.py to generate tokens
Issue -
State: open - Opened by Teng0828 9 months ago
- 1 comment
#75 - The critic model will generate different type of token when I use run_reward_vllm.py to generate tokens
Issue -
State: open - Opened by Teng0828 9 months ago
- 1 comment
#74 - Doesn't the generator need to call the retriever when training the model?
Issue -
State: open - Opened by liumc14 9 months ago
#74 - Doesn't the generator need to call the retriever when training the model?
Issue -
State: open - Opened by liumc14 9 months ago
#73 - About parameter `max_depth`
Issue -
State: open - Opened by LYCnight 10 months ago
- 2 comments
#73 - About parameter `max_depth`
Issue -
State: open - Opened by LYCnight 10 months ago
- 2 comments
#72 - accuracy metric
Issue -
State: open - Opened by zhuzihan728 10 months ago
- 3 comments
#72 - accuracy metric
Issue -
State: open - Opened by zhuzihan728 10 months ago
- 3 comments
#71 - Reproducing Self-RAG
Issue -
State: open - Opened by 201736621051 10 months ago
#71 - Reproducing Self-RAG
Issue -
State: open - Opened by 201736621051 10 months ago
#70 - Processed Input Dataset and Flan-3B Critic Generated Dataset
Issue -
State: open - Opened by ShayekhBinIslam 10 months ago
#69 - model issues
Issue -
State: open - Opened by BlackHandsomeLee 10 months ago
#69 - model issues
Issue -
State: open - Opened by BlackHandsomeLee 10 months ago
#68 - How can I get initial input file for generator?
Issue -
State: open - Opened by hummingbird2030 10 months ago
#68 - How can I get initial input file for generator?
Issue -
State: open - Opened by hummingbird2030 10 months ago
#67 - Creatsed and edited Dockerfile
Pull Request -
State: closed - Opened by limsanky 10 months ago
#66 - Explanation needed for [Continue to Use Evidence]
Issue -
State: closed - Opened by zhuzihan728 10 months ago
- 1 comment
#65 - What does YOUR_INPUT_FILE look like? Can you provide an example? Thanks very much!
Issue -
State: open - Opened by XiaozhuLove 10 months ago
- 3 comments
#64 - How long does it takes to train an epoch for critic/generator model on llama-7B with 8 A100?
Issue -
State: closed - Opened by hummingbird2030 10 months ago
#64 - How long does it takes to train an epoch for critic/generator model on llama-7B with 8 A100?
Issue -
State: closed - Opened by hummingbird2030 10 months ago
#63 - 4 bit quantized version of 7B?
Issue -
State: open - Opened by djkazic 11 months ago
#63 - 4 bit quantized version of 7B?
Issue -
State: open - Opened by djkazic 11 months ago
#62 - I have create a virtual enviroment in anaconda. However, something went wrong when i try to 'pip install -r requirement'
Issue -
State: open - Opened by Fangzhou-Code 11 months ago
- 2 comments
#61 - Retrieval-augmented baselines - Huggingface models
Issue -
State: open - Opened by mozhu621 11 months ago
- 4 comments
#60 - Questions about Critic model
Issue -
State: open - Opened by leejaehoon1830 11 months ago
- 2 comments
#60 - Questions about Critic model
Issue -
State: open - Opened by leejaehoon1830 11 months ago
- 2 comments
#59 - Where does the retrieval done?
Issue -
State: open - Opened by sutakori 11 months ago
#58 - The meaning of "_w_gs.jsonl" in evaluation data
Issue -
State: open - Opened by qiweijian 11 months ago
- 2 comments
#58 - The meaning of "_w_gs.jsonl" in evaluation data
Issue -
State: open - Opened by qiweijian 11 months ago
- 2 comments
#57 - Cannot approach the performance of the uploaded self-rag ckpt when finetuning meta/Llama-2 myself
Issue -
State: open - Opened by HazekiahWon 11 months ago
- 5 comments
#56 - How is the jsonl file in the eval_data built, thank you very much!
Issue -
State: open - Opened by Gera001 11 months ago
- 5 comments
#55 - 请问eval_data中的jsonl文件是怎么构建的,非常感谢!
Issue -
State: open - Opened by Gera001 11 months ago
#55 - 请问eval_data中的jsonl文件是怎么构建的,非常感谢!
Issue -
State: open - Opened by Gera001 11 months ago
#54 - About save_merged_lora_model
Issue -
State: closed - Opened by AllenShow 11 months ago
- 1 comment
#54 - About save_merged_lora_model
Issue -
State: closed - Opened by AllenShow 11 months ago
- 1 comment
#53 - typos and missing dependency
Pull Request -
State: closed - Opened by notoookay 11 months ago
- 1 comment
#53 - typos and missing dependency
Pull Request -
State: closed - Opened by notoookay 11 months ago
- 1 comment
#52 - conda environment creation error
Pull Request -
State: closed - Opened by notoookay 11 months ago
#52 - conda environment creation error
Pull Request -
State: closed - Opened by notoookay 11 months ago
#51 - Question about the pre-given passages
Issue -
State: open - Opened by WenzhengZhang 12 months ago
- 1 comment
#51 - Question about the pre-given passages
Issue -
State: open - Opened by WenzhengZhang 12 months ago
- 1 comment
#50 - How to fix the bug about 'local variable 'pred' referenced before assignment'?
Issue -
State: open - Opened by AllenShow 12 months ago
#50 - How to fix the bug about 'local variable 'pred' referenced before assignment'?
Issue -
State: open - Opened by AllenShow 12 months ago
#49 - Build data for critic model
Issue -
State: open - Opened by SC19072 12 months ago
- 2 comments
#49 - Build data for critic model
Issue -
State: open - Opened by SC19072 12 months ago
- 2 comments
#48 - Out of memory at inference in free tier Google Colab
Issue -
State: open - Opened by sudhir2016 12 months ago
#48 - Out of memory at inference in free tier Google Colab
Issue -
State: open - Opened by sudhir2016 12 months ago
#47 - custom datset help
Issue -
State: open - Opened by drewskidang 12 months ago
- 2 comments
#47 - custom datset help
Issue -
State: open - Opened by drewskidang 12 months ago
- 2 comments
#46 - Is it possible to get custom dataset
Issue -
State: closed - Opened by drewskidang almost 1 year ago
- 1 comment
#46 - Is it possible to get custom dataset
Issue -
State: closed - Opened by drewskidang almost 1 year ago
- 1 comment
#45 - About PopQA
Issue -
State: open - Opened by AllenShow about 1 year ago
- 1 comment
#45 - About PopQA
Issue -
State: open - Opened by AllenShow about 1 year ago
- 1 comment
#44 - Cannot reproduce baseline tasks?
Issue -
State: open - Opened by AllenShow about 1 year ago
- 4 comments
#44 - Cannot reproduce baseline tasks?
Issue -
State: open - Opened by AllenShow about 1 year ago
- 5 comments
#43 - For ASQA, how to reproduce the baseline?
Issue -
State: open - Opened by AllenShow about 1 year ago
- 1 comment
#43 - For ASQA, how to reproduce the baseline?
Issue -
State: open - Opened by AllenShow about 1 year ago
- 1 comment
#42 - About baseline's parameter 'task'
Issue -
State: open - Opened by AllenShow about 1 year ago
- 1 comment
#42 - About baseline's parameter 'task'
Issue -
State: open - Opened by AllenShow about 1 year ago
- 1 comment
#41 - Are these two code files the same thing?
Issue -
State: closed - Opened by AllenShow about 1 year ago
- 1 comment
#41 - Are these two code files the same thing?
Issue -
State: closed - Opened by AllenShow about 1 year ago
- 1 comment
#40 - Bug report & Self-RAG never predicts `[Retrieval]` when set `threshold=None`
Issue -
State: open - Opened by ZhangzihanGit about 1 year ago
#40 - Bug report & Self-RAG never predicts `[Retrieval]` when set `threshold=None`
Issue -
State: open - Opened by ZhangzihanGit about 1 year ago
#39 - max_depth argument in retrieval_lm/run_short_form.py
Issue -
State: open - Opened by AllenShow about 1 year ago
- 2 comments
#38 - The selfrag_llama2_7b model does not come out as in the example
Issue -
State: open - Opened by leejaehoon1830 about 1 year ago
- 4 comments
#37 - the logic of NO retrieval in long form inference
Issue -
State: open - Opened by fate-ubw about 1 year ago
- 4 comments
#36 - 请问有中文训练语料吗?
Issue -
State: closed - Opened by mawenju203 about 1 year ago
- 10 comments
#35 - Critic model's special token
Issue -
State: open - Opened by xiaowu0162 about 1 year ago
- 5 comments
#34 - Question about Algorithm 1 table in self rag paper download from ariv
Issue -
State: closed - Opened by fate-ubw about 1 year ago
- 1 comment
#33 - If it's possible to use LoRA to train critic and generator
Issue -
State: closed - Opened by phoenixqaq about 1 year ago
- 6 comments