PR #14771 Add LLaDA 8b Diffusion model

Add LLaDA 8b Diffusion model #14771

am17an merged 12 commits into ggml-org:master from am17an:add_llada_8b

github-actions added examples

github-actions added python

am17an force pushed 1 year ago

am17an requested a review from

ggerganov 1 year ago

am17an force pushed 1 year ago

am17an requested a review from

CISC 1 year ago

am17an force pushed 1 year ago

CISC commented on 2025-07-19

am17an force pushed 1 year ago

CISC commented on 2025-07-20

am17an force pushed 1 year ago

ggerganov commented on 2025-07-26

am17an force pushed 1 year ago

CISC commented on 2025-07-28

Add support for Llada-8b: diffusion model

bef6c2d0

Add README

0fa8b866

Fix README and convert_hf_to_gguf

267a09df

convert_hf_to_gguf.py: address review comments

812bc383

Make everything in a single example

6bb00936

am17an force pushed 1 year ago

Remove model-specific sampling

3e7efcba

am17an force pushed to 3e7efcba 1 year ago

am17an requested a review from

ggerganov 1 year ago

Remove unused argmax

a50547c9

ggerganov approved these changes on 2025-07-31

Remove braced initializers, improve README.md a bit

e864a496

am17an force pushed to e864a496 1 year ago

CISC approved these changes on 2025-07-31

Add diffusion specific gguf params in set_vocab, remove setting rope_…

9691f4ed

am17an force pushed to 9691f4ed 1 year ago

CISC commented on 2025-07-31

Remove adding the mask token

57201ccb

CISC commented on 2025-07-31

Move add_add_bos_token to set_vocab

a326b130

CISC commented on 2025-07-31

use add_bool in gguf_writer.py

ac3f91fe

am17an force pushed to ac3f91fe 1 year ago

am17an merged 8a4a8562 into master 1 year ago

am17an deleted the add_llada_8b branch 1 year ago

Reviewers

CISC

ggerganov

Assignees

No one assigned

Labels

examples python

Milestone

No milestone

llama.cpp Add LLaDA 8b Diffusion model #14771 Merged

Add LLaDA 8b Diffusion model #14771

llama.cpp
Add LLaDA 8b Diffusion model
#14771

Merged