Issues
- 5
AESLC Checksum error
#89 opened by imoneoi - 1
some Enrico COT entries seem odd
#91 opened by i-am-neo - 10
- 0
Question about data source splits
#104 opened by psinger - 1
- 1
Broken Dataset Links in FLAN Repository
#102 opened by JhonDan1999 - 0
- 0
Where can I find the test mixture and its templates to reproduce the results in the paper?
#96 opened by nanyyyyyy - 7
- 0
Finetuning is definitely better than zero-shot, this is inevitable. So how should I understand the title of this paper?
#94 opened by guotong1988 - 1
Too many threads created
#70 opened by kiriharulxh - 0
How many samples were used to train Flan-T5?
#92 opened by rohan-mehta - 0
No train split in `adversarial_qa_dbert_answer_the_following_q_template_0to10_no_opt_x_shot`
#90 opened by imoneoi - 1
Does anyone know which 282 tasks are used?
#88 opened by ntubiolin - 2
How to cache my mixture
#69 opened by renmengjie7 - 1
Issue generating flan2021 submix
#87 opened by Bondrake - 1
Pin versions for flan/v2/requirements.txt
#61 opened by takiholadi - 2
Code for mixing Enrico sets?
#81 opened by takiholadi - 0
Questions about the Flan Held-Out Tasks (pubmed_qa) and experiment details in the flan collection paper
#85 opened by nanyyyyyy - 0
Doubt about the TARGET parameter in the dataset
#86 opened by igor17400 - 0
- 7
- 4
- 3
- 1
Thank you for your efforts. This is a great job!I have a problem. Why is there only 70 tasks in this FLAN2021_submix_original, and it seems that there are over 140 in the paper?
#82 opened by flyinghpluo - 3
Reproducing the flan_v2 results of T5-xl
#80 opened by danczs - 0
- 0
Links in Flan V2 README broken
#77 opened by sia-cerebras - 2
T0 FS OPT - unable to process.
#65 opened by AadSah - 1
- 5
[Question] What environment did you use for fetching large data set like dialog_mixture
#66 opened by quq99 - 2
- 1
How do I get only the CoT related data?
#59 opened by timothylimyl - 2
- 0
How to get a specific dataset, such as SST-2
#68 opened by renmengjie7 - 5
- 2
Arabic tokenization is broken
#52 opened by gahdritz - 4
ERROR:absl:Failed to load task 'tfds_natural_instructions_template_0to10_zero_shot' as part of mixture 'palmflan_niv2_zs_opt'
#49 opened by AadSah - 2
- 3
Held-in validation set details
#56 opened by gahdritz - 3
Is Inversion used for the Few-Shot case?
#54 opened by AadSah - 1
Recommended caching method
#51 opened by gahdritz - 11
- 1
[BUG] get_dataset for flan2021_submix taking hours, while flan_zsnoopt takes 5m
#48 opened by TheExGenesis - 1
How were the Held-In and Held-Out splits created?
#46 opened by AadSah - 5
BBH causal judgment reasoning
#42 opened by i-am-neo - 1
tfds version issue
#41 opened by joocjun - 3
base model for self-query?
#39 opened by i-am-neo - 10
[Question] Code Synthesis eval functions?
#45 opened by TheExGenesis - 2