google-research / FLAN

google-research/FLAN Issues

[Question] What license is used for this FLAN dataset(not the code).
Updated a month ago10
Question about data source splits
Updated 2 months ago
Links to Enrico Shippole FLAN dataset are missing
Updated 5 months ago1
Broken Dataset Links in FLAN Repository
Updated 5 months ago1
Datafile AESLC-master.zip meet non_matching_checksum_error
Updated 6 months ago
Where can I find the test mixture and its templates to reproduce the results in the paper?
Closed 7 months ago
Where can I obtain a generated dataset that includes an options column
Updated 8 months ago7
Finetuning is definitely better than zero-shot, this is inevitable. So how should I understand the title of this paper?
Updated 9 months ago
AESLC Checksum error
Updated 9 months ago4
Too many threads created
Closed a year ago1
How many samples were used to train Flan-T5?
Updated 9 months ago
some Enrico COT entries seem odd
Updated 10 months ago
No train split in `adversarial_qa_dbert_answer_the_following_q_template_0to10_no_opt_x_shot`
Updated 10 months ago
Does anyone know which 282 tasks are used?
Closed 10 months ago1
How to cache my mixture
Updated 10 months ago2
Issue generating flan2021 submix
Closed 10 months ago1
Pin versions for flan/v2/requirements.txt
Updated 10 months ago1
Code for mixing Enrico sets?
Updated a year ago2
Questions about the Flan Held-Out Tasks (pubmed_qa) and experiment details in the flan collection paper
Closed a year ago
Doubt about the TARGET parameter in the dataset
Updated a year ago
[Question] Training data formatting for other custom models
Updated a year ago
All attempts to get a Google authentication bearer token failed
Closed a year ago7
Could you share the training loss to improve reproducibility?
Updated a year ago4
Request for Training Code for Reproducibility and Research Purposes
Closed a year ago3
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?
Updated a year ago1
Reproducing the flan_v2 results of T5-xl
Updated a year ago3
Trying to access `splits['train']` but `splits` is empty
Closed a year ago
Links in Flan V2 README broken
Updated a year ago
T0 FS OPT - unable to process.
Closed a year ago2
seqio.get_mixture_or_task('ag_news_subset_template_0_five_shot') failed
Updated a year ago1
[Question] What environment did you use for fetching large data set like dialog_mixture
Updated a year ago5
How to include metadata from flan_collection_info.csv in each data entry?
Closed a year ago2
How do I get only the CoT related data?
Closed a year ago1
Prompt for multiple choice question with quote extraction
Closed a year ago2
How to get a specific dataset, such as SST-2
Closed a year ago
[Question] How much memory is required to generate wiki_dialog?
Closed a year ago5
Arabic tokenization is broken
Closed a year ago2
ERROR:absl:Failed to load task 'tfds_natural_instructions_template_0to10_zero_shot' as part of mixture 'palmflan_niv2_zs_opt'
Closed a year ago4
niv2 few-shots are returning single shot examples
Closed a year ago2
Held-in validation set details
Closed a year ago3
Is Inversion used for the Few-Shot case?
Closed a year ago3
Recommended caching method
Closed a year ago1
TypeError: Invalid `datasets`. `datasets` must have compatible element specs.
Closed a year ago11
[BUG] get_dataset for flan2021_submix taking hours, while flan_zsnoopt takes 5m
Closed a year ago1
How were the Held-In and Held-Out splits created?
Closed a year ago1
BBH causal judgment reasoning
Closed a year ago5
tfds version issue
Closed a year ago1
base model for self-query?
Closed a year ago3
[Question] Code Synthesis eval functions?
Closed a year ago10
[BUG] Cache is empty with FLAN, but not with seqio
Closed a year ago2