CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-14 11:07:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

model : Minimax M2 (#16831)

Browse Source 
* Model: Minimax M2

* Cleanup

* Cleanup pt. 2

* Cleanup pt. 3

* Update convert_hf_to_gguf_update.py - merge catch blocks

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Remove vocab models and test

* Remove all redundant hparam settings covered by TextModel

* Move super to start, don't set block_count

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update gguf-py/gguf/constants.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
Piotr Wilkin (ilintar)
2025-10-31 21:20:47 +01:00
committed by GitHub
parent e58d585604
commit 0de0a01576
10 changed files with 284 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
gguf-py/gguf/constants.py
View File

@@ -425,6 +425,7 @@ class MODEL_ARCH(IntEnum):
GROVEMOE = auto()
APERTUS = auto()
COGVLM = auto()
MINIMAXM2 = auto()
class VISION_PROJECTOR_TYPE(IntEnum):
@@ -790,6 +791,7 @@ MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = {
MODEL_ARCH.SEED_OSS: "seed_oss",
MODEL_ARCH.GROVEMOE: "grovemoe",
MODEL_ARCH.APERTUS: "apertus",
MODEL_ARCH.MINIMAXM2: "minimax-m2",
MODEL_ARCH.COGVLM: "cogvlm",
}
@@ -2921,6 +2923,24 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.FFN_DOWN_CHEXP,
MODEL_TENSOR.FFN_UP_CHEXP,
],
MODEL_ARCH.MINIMAXM2: [
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.OUTPUT_NORM,
MODEL_TENSOR.OUTPUT,
MODEL_TENSOR.ATTN_NORM,
MODEL_TENSOR.ATTN_Q,
MODEL_TENSOR.ATTN_Q_NORM,
MODEL_TENSOR.ATTN_K,
MODEL_TENSOR.ATTN_K_NORM,
MODEL_TENSOR.ATTN_V,
MODEL_TENSOR.ATTN_OUT,
MODEL_TENSOR.FFN_NORM,
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.COGVLM: [
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.OUTPUT_NORM,