Efficient-Large-Model
/

NVILA-Lite-2B-hf-preview

Model card Files Files and versions

Refactor code to transformers convention

#3

by AndyZijianZhang - opened Apr 7, 2025

base: refs/heads/main

←

from: refs/pr/3

Discussion Files changed

AndyZijianZhang

Efficient-Large-Model org Apr 7, 2025

No description provided.

chore: update .gitattributes9b1a89e6

refactor: a lot782af8d2

chore: gitattributes5fa06526

chore: updatef5b63c61

feat: processorbf6f216f

refactor: minimum changesf681f3f0

feat: update config.sjonac2caa52

feat: add chat template602e681b

feat: finish VILAProcessor73c05562

feat: remove modeling_vila_new.py584808a2

feat: move model code to auto_model.py99e90b84

feat: can generate now but not precise50664435

fix: unable to use cache5c085c35

feat: architecture to VILAForConditionalGeneration5668a8d8

fix: failing to batch infer70a43a28

fix: old VILAForCausalLM attn mask dtype018dab3b

fix: processor classd5e2e9cf

feat: use <|endoftext|> as padding token996e0bec

refactor: keep original files139253d7

fix: revert a potentially troublesome fix8cd11590

revert: changes in modeling_vila.py8d6ee385

feat: pad to final length in VILAProcessor5d084817

feat: new model10d7cc52

refactor: now processing_vila does not depend on any other files4e95a1b4

AndyZijianZhang changed pull request status to closed Apr 23, 2025

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment