Skip to content

implemented mimo model#42995

Closed
Aaraviitkgp wants to merge 4 commits intohuggingface:mainfrom
Aaraviitkgp:mimo-integration-clean_new
Closed

implemented mimo model#42995
Aaraviitkgp wants to merge 4 commits intohuggingface:mainfrom
Aaraviitkgp:mimo-integration-clean_new

Conversation

@Aaraviitkgp
Copy link
Copy Markdown
Contributor

Issue : #42954

I have implemented mimo model,
I have just changed rope_type as it was default which was causing error so now it is none by default also changed and have made some changes in class MiMoV2FlashRotaryEmbedding, added files for mimo integration.

@ArthurZucker

@github-actions
Copy link
Copy Markdown
Contributor

[For maintainers] Suggested jobs to run (before merge)

run-slow: auto

@Aaraviitkgp
Copy link
Copy Markdown
Contributor Author

@ArthurZucker The setup and quality workflow seems to fail, I am not able to understand why it is coming.

@Liuweixiong0118
Copy link
Copy Markdown

@Aaraviitkgp hello, i found your transformers github, https://github.com/Aaraviitkgp/transformers, have four mimo-v2-flash implemented branch.
which one is the trainable final version of mimo-v2-flash.
can i use the origin repo https://huggingface.co/XiaomiMiMo/MiMo-V2-Flash model to train?
Thank you for sharing and look forward to your reply

@vasqu vasqu mentioned this pull request Jan 19, 2026
5 tasks
@casinca casinca mentioned this pull request Mar 31, 2026
6 tasks
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants