-
Notifications
You must be signed in to change notification settings - Fork 2.1k
Pull requests: kyegomez/OpenMythos
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Add ablation flags (disable_act, break_recurrence, etc.) to enable depth-extrapolation training
#58
opened Apr 23, 2026 by
tonyzdev
Loading…
3 tasks done
docs: fix incorrect spectral radius computation in README example
#50
opened Apr 22, 2026 by
sunnyc0206
Loading…
feat: add MiniMax-M2.7 architecture config and tokenizer support
#49
opened Apr 22, 2026 by
octo-patch
Loading…
PAI review: install fixes, numerical correctness, MLA cache, generate hardening (+ roadmap)
#45
opened Apr 22, 2026 by
baseflux
Loading…
Remediation: router-bias wiring, EOS packing, numerical stability, trainer hardening, tests
#41
opened Apr 21, 2026 by
supernavyl
Loading…
6 of 8 tasks
Added comprehensive graphs and diagrams to the README to enhance readability
#39
opened Apr 21, 2026 by
Purshh
Loading…
fix: normalize torch version to >=2.1.0 across all dependency files
#37
opened Apr 21, 2026 by
spoturno
Loading…
fix: remove phantom exports load_tokenizer and get_vocab_size from __all__
#35
opened Apr 21, 2026 by
spoturno
Loading…
Add experiments/ suite for inference-time loop scaling validation
#27
opened Apr 21, 2026 by
tonyzdev
Loading…
5 tasks done
feat(tests): add 29 model tests for forward pass, LTI stability, generation, RMSNorm, causal mask, LoRA and loop-index embedding
#22
opened Apr 20, 2026 by
miheer-smk
Loading…
Align training recipe and add validation logging
#15
opened Apr 20, 2026 by
FrankHui
Loading…
2 tasks done
Optimize MoE routing dispatch and add diagnostics
#14
opened Apr 20, 2026 by
FrankHui
Loading…
2 tasks
fix(lora): clamp loop index so depth-extrapolation does not crash
#10
opened Apr 20, 2026 by
jorgevazquez-vagojo
Loading…
4 tasks done
fix: Autoregressive KV-cache RoPE initialization and HF kwargs support
#4
opened Apr 19, 2026 by
aniruddhaadak80
Loading…
feat: Flash Attention, Hugging Face integration, MoE loss, and core exports
#3
opened Apr 19, 2026 by
aniruddhaadak80
Loading…
[FEAT] F.scaled_dot_product_attention backend for GQA/MLA
#2
opened Apr 19, 2026 by
mvanhorn
Loading…
Previous Next
ProTip!
Follow long discussions with comments:>50.