HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

flan-t5-base

google/flan-t5-base

kind
original
quant
bf16 (16-bit)
family
misc
modality
—
root model
google/flan-t5-base
provider
google
license
apache-2.0
language
en, fr, ro, de, multilingual
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
1,880,855
likes
1,089
created
—
last modified
2023-07-17T12:48:39+00:00 (2023)
huggingface
https://huggingface.co/google/flan-t5-base
tags
transformerspytorchtfjaxsafetensorst5text2text-generationenfrrodemultilingualdataset:svakulenk0/qreccdataset:taskmaster2dataset:djaym7/wiki_dialogdataset:deepmind/code_contestsdataset:lambadadataset:gsm8kdataset:aqua_ratdataset:esnlidataset:quascdataset:qedarxiv:2210.11416arxiv:1910.09700

Benchmark scores (1)

benchmarkcategoryscorecontextconfevidence
BoolQknowledge16.75mediumboolq=16.75

Discussions (41)

titleauthorstatuscommentstype
Question: edge/mobile deployment — anyone tested?3morixdopen0disc
New architecture: TemporalMesh Transformer — dynamic kNN graph attention + per-token exit routing, 29.4 PPL at 48% computevigneshwar234open0disc
TensorFlow issuekgrabkoopen0disc
PyTorch issue .kgrabkoopen0disc
Request: DOIdenish4848open0disc
Potential Inconsistencies Model and Datasets Licenseyueyangchenopen0disc
Create NYchat_17EvelynMilagrosclosed0disc
Use from DJL (Deep Java Library)?kwalcockopen0disc
Language translation to Hindi, Bengali is not working , Does anyone have any resolution or better alternative for this ?r-rahulsinghopen0disc
Couldn't generate bengali text with Flan Models.asif00open0disc
Create halloFoobABclosed0disc
Rename config.json to adapter_config.jsonAmrit05closed0disc
[AUTOMATED] Model Memory Requirementsmodel-sizer-botopen0disc
Upload T5ForConditionalGenerationCactussopen0disc
Upload T5ForConditionalGenerationCactussclosed0disc
Upload T5ForConditionalGenerationCactussclosed0disc
Adding ONNX file of this modeluvgprojectsopen0disc
Add Core ML conversionOmkar008open0disc
TestGgcallopen0disc
Where to find the token ids of the tokenizer ?MohamedDhouib1open0disc
Flax checkpoint with float16 dtype outputs nangigantclosed0disc
Maximum sequence length of flan-t5 base , large , xl ,xxl ? ali-issaopen0disc
Issue with Flan-T5 in Huggingface LangflowAnkitab-6open0disc
does not appear to have a file named config.jsonnaylenopen0disc
Weight tyingcbock90open0disc
Issue with t5 tokenizer inconsistency. Lvegnaopen0disc
Does FLAN-T5 support masked language modeling (similar to how t5 does)?ToasterLeavinopen0disc
nans while fine tuningedmondclosed0disc
Issues in fine tuning flan T5 model?mihirinamdaropen0disc
Update README.mdybelkadaopen0disc
Update README.mdybelkadamerged0disc
Evaluation results for google/flan-t5-base model as a base model for other taskseladvenmerged0disc
Adding `safetensors` variant of this modellucatacomerged0disc
Update correct `gelu` functionybelkadamerged0disc
Update README.mdybelkadamerged0disc
Wrong screenshot in "Testing Data, Factors & Metrics" sectionattekeiclosed0disc
Turkish language supportSercanopen0disc
Does the model supported Thai language?new5558closed0disc
Update README.mdybelkadamerged0disc
Cab you do text summary with this just like with T5?Stromalopen0disc
Fix model namemrm8488merged0disc
Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.