Issues
- 2
- 2
dependency
#82 opened by n-m-h - 1
CUDA Memory is not enough
#84 opened by zhongruizhe123 - 1
Max_logprobs and logprobs value
#85 opened by ShreyPandit - 1
About bio eval
#87 opened by aJupyter - 2
question about multi content reference
#88 opened by 256785 - 0
- 4
Cannot reproduce baseline tasks?
#44 opened by AllenShow - 6
Incorrect setup of Learning Rate Scheduler
#81 opened by aswathn1 - 0
How to curate the preceding sentences? and Can you inform the distribution of IsUse token (1~5)?
#86 opened by MSungK - 2
The meaning of "_w_gs.jsonl" in evaluation data
#58 opened by qiweijian - 0
- 2
torch.distributed.elastic.multiprocessing.api: [ERROR] failed (exitcode: -9) local_rank: 0 (pid: 14447) of binary:
#83 opened 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 by Fangzhou-Code - 1
The critic model will generate different type of token when I use run_reward_vllm.py to generate tokens
#75 opened by Teng0828 - 4
Retrieval-augmented baselines - Huggingface models
#61 opened by mozhu621 - 3
accuracy metric
#72 opened by zhuzihan728 - 5
- 0
- 4
- 5
Cannot approach the performance of the uploaded self-rag ckpt when finetuning meta/Llama-2 myself
#57 opened by HazekiahWon - 0
Data formatting to call the retriever
#77 opened by lauhaide - 0
some problem with run_long_form_static.py
#76 opened by pzwstudy - 2
About parameter `max_depth`
#73 opened by LYCnight - 0
- 10
请问有中文训练语料吗?
#36 opened by mawenju203 - 1
About PopQA
#45 opened by AllenShow - 1
Explanation needed for [Continue to Use Evidence]
#66 opened by zhuzihan728 - 0
Reproducing Self-RAG
#71 opened by 201736621051 - 0
model issues
#69 opened by BlackHandsomeLee - 0
How long does it takes to train an epoch for critic/generator model on llama-7B with 8 A100?
#64 opened by hummingbird2030 - 1
What does YOUR_INPUT_FILE look like? Can you provide an example? Thanks very much!
#65 opened by XiaozhuLove - 0
4 bit quantized version of 7B?
#63 opened by djkazic - 1
- 2
custom datset help
#47 opened by drewskidang - 1
Are these two code files the same thing?
#41 opened by AllenShow - 1
Question about the pre-given passages
#51 opened by WenzhengZhang - 1
About save_merged_lora_model
#54 opened by AllenShow - 2
Questions about Critic model
#60 opened by leejaehoon1830 - 1
For ASQA, how to reproduce the baseline?
#43 opened by AllenShow - 0
Where does the retrieval done?
#59 opened by sutakori - 0
请问eval_data中的jsonl文件是怎么构建的,非常感谢!
#55 opened by Gera001 - 2
Build data for critic model
#49 opened by SC19072 - 0
How to fix the bug about 'local variable 'pred' referenced before assignment'?
#50 opened by AllenShow - 0
- 1
Is it possible to get custom dataset
#46 opened by drewskidang - 1
About baseline's parameter 'task'
#42 opened by AllenShow - 0
Bug report & Self-RAG never predicts `[Retrieval]` when set `threshold=None`
#40 opened by ZhangzihanGit - 4
the logic of NO retrieval in long form inference
#37 opened by fate-ubw - 5
Critic model's special token
#35 opened by xiaowu0162