model: support MiMo-V2-Flash (#18328)
* mimov2: convert ok * rename mimov2 --> mimo2 * fix conversion * runnable not incorrect * use sink * add_sliding_window_pattern * add swa and per-layer n_head_kv * correct params * somewhat working * correct gating func * nits * mimo2: wire RMS eps + MoE bias + converter guards * add co-author Co-authored-by: Aaryan-Kapoor <Aaryan-Kapoor@users.noreply.github.com> * use add_rope_freq_base_swa --------- Co-authored-by: Aaryan Kapoor <aaryankapoor2006@gmail.com> Co-authored-by: Aaryan-Kapoor <Aaryan-Kapoor@users.noreply.github.com>
This commit is contained in:
co-authored by
Aaryan-Kapoor
Aaryan Kapoor
parent
c184284230
commit
4cbafad4f0
@@ -119,6 +119,7 @@ enum llm_arch {
|
||||
LLM_ARCH_RND1,
|
||||
LLM_ARCH_PANGU_EMBED,
|
||||
LLM_ARCH_MISTRAL3,
|
||||
LLM_ARCH_MIMO2,
|
||||
LLM_ARCH_LLAMA_EMBED,
|
||||
LLM_ARCH_UNKNOWN,
|
||||
};
|
||||
|
||||
Reference in New Issue
Block a user