sleepy/llama.cpp
1
0
Fork 0
Code Issues 11 Pull Requests Actions 109 Packages Projects Releases Wiki Activity

model: support MiMo-V2-Flash (#18328)

Browse Source 
* 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:
Xuan-Son Nguyen
2025-12-24 23:07:08 +01:00
committed by GitHub
parent c184284230
commit 4cbafad4f0
11 changed files with 324 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
gguf-py/gguf/constants.py
+23 -1
View File
@@ -449,6 +449,7 @@ class MODEL_ARCH(IntEnum):
RND1 = auto()
PANGU_EMBED = auto()
MISTRAL3 = auto()
MIMO2 = auto()
LLAMA_EMBED = auto()
@@ -845,6 +846,7 @@ MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = {
MODEL_ARCH.RND1: "rnd1",
MODEL_ARCH.PANGU_EMBED: "pangu-embedded",
MODEL_ARCH.MISTRAL3: "mistral3",
MODEL_ARCH.MIMO2: "mimo2",
MODEL_ARCH.LLAMA_EMBED: "llama-embed",
}
@@ -3198,6 +3200,26 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.FFN_DOWN_EXP,
MODEL_TENSOR.FFN_UP_EXP,
],
MODEL_ARCH.MIMO2: [
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.OUTPUT_NORM,
MODEL_TENSOR.OUTPUT,
MODEL_TENSOR.ATTN_NORM,
MODEL_TENSOR.ATTN_Q,
MODEL_TENSOR.ATTN_K,
MODEL_TENSOR.ATTN_V,
MODEL_TENSOR.ATTN_SINKS,
MODEL_TENSOR.ATTN_OUT,
MODEL_TENSOR.FFN_NORM,
MODEL_TENSOR.FFN_GATE,
MODEL_TENSOR.FFN_DOWN,
MODEL_TENSOR.FFN_UP,
MODEL_TENSOR.FFN_GATE_INP,
MODEL_TENSOR.FFN_GATE_EXP,
MODEL_TENSOR.FFN_DOWN_EXP,
MODEL_TENSOR.FFN_UP_EXP,
MODEL_TENSOR.FFN_EXP_PROBS_B,
],
MODEL_ARCH.LLAMA_EMBED: [
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.OUTPUT_NORM,
@@ -3217,7 +3239,7 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.FFN_GATE_EXP,
MODEL_TENSOR.FFN_DOWN_EXP,
MODEL_TENSOR.FFN_UP_EXP,
]
],
# TODO
}
gguf-py/gguf/tensor_mapping.py
+1
View File
@@ -320,6 +320,7 @@ class TensorNameMap:
MODEL_TENSOR.ATTN_SINKS: (
"model.layers.{bid}.self_attn.sinks", # openai-moe
"model.layers.{bid}.self_attn.attention_sink_bias", # mimov2
),
MODEL_TENSOR.ATTN_GATE: (