Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

model : add support for MiniMaxText01ForCausalLM and MiniMaxM1ForCausalLM (#27018)

Browse Source 
* llama : support for MiniMax-Text-01 model

* chore : renames to match the other MiniMax models

* model : add logits mask as MiniMax-Text-01 embeddings tensor has zero-valued embeddings for tokens >= 200032 that produce zero logits disrupting the token sampling process

* llama : replace hardcoded conditions with hparams.is_recr()

* model : used build_rs() for recurrent state management

* chore : code cleanup

* model : optimized MiniMax-Text-01 by removing the state tranpose operations

* chore : removed unnecessary ggml_cont() in MiniMax-Text-01 implementation

* llama : add generic logits mask graph input

* model : permuted diag_decay dimensions to avoid doing it inside MiniMax-Text-01 graph

* chore : code cleanup

* chore : code cleanup

* model : use token positions when calculating MiniMax-Text-01 decay tensors

* convert : add support for MiniMaxM1ForCausalLM as it seems to be the same as MiniMaxText01ForCausalLM

* chat : add jinja template for MiniMax-M1

Co-authored-by: QscQ <qscqesze@gmail.com>

* chore : code cleanup

* tests : MINIMAX_01-related fixes

* chore : silence Python lint errors

* vocab : remove unnecessary vocab type

* convert : update MiniMaxText01Model conversion to use yield when modifying tensors

* convert : suppress tokens with zero-valued embeddings during MiniMax-Text-01 conversion

* llama : removed logits mask - no longer necessary as token suppression is used instead

* model : use common functions to make MiniMax-Text-01 implementation more concise

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>

* model : use common functions to make MiniMax-Text-01 implementation more concise

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>

* convert : override non-working built-in chat template during conversion

* tests : skip arch MINIMAX_01 tests for WebGPU backend (it breaks again)

---------

Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>
Co-authored-by: QscQ <qscqesze@gmail.com>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
This commit is contained in:
fairydreaming
2026-08-15 00:02:38 +02:00
committed by GitHub
co-authored by QscQ Sigbjørn Skjæret Stanisław Szymczyk
parent 6fed9f6ff7
commit 16d222fc5e
15 changed files with 784 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
gguf-py/gguf/constants.py
+20
View File
@@ -565,6 +565,7 @@ class MODEL_ARCH(IntEnum):
GROVEMOE = auto()
APERTUS = auto()
COGVLM = auto()
MINIMAX01 = auto()
MINIMAXM2 = auto()
MINIMAXM3 = auto()
RND1 = auto()
@@ -1271,6 +1272,7 @@ MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = {
MODEL_ARCH.SEED_OSS: "seed_oss",
MODEL_ARCH.GROVEMOE: "grovemoe",
MODEL_ARCH.APERTUS: "apertus",
MODEL_ARCH.MINIMAX01: "minimax-01",
MODEL_ARCH.MINIMAXM2: "minimax-m2",
MODEL_ARCH.MINIMAXM3: "minimax-m3",
MODEL_ARCH.COGVLM: "cogvlm",
@@ -4592,6 +4594,24 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.FFN_DOWN_CHEXP,
MODEL_TENSOR.FFN_UP_CHEXP,
],
MODEL_ARCH.MINIMAX01: [
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.OUTPUT_NORM,
MODEL_TENSOR.OUTPUT,
MODEL_TENSOR.ATTN_NORM,
MODEL_TENSOR.ATTN_NORM_2,
MODEL_TENSOR.ATTN_QKV,
MODEL_TENSOR.ATTN_Q,
MODEL_TENSOR.ATTN_K,
MODEL_TENSOR.ATTN_V,
MODEL_TENSOR.ATTN_OUT,
MODEL_TENSOR.ATTN_GATE,
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_ARCH.MINIMAXM2: [
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.OUTPUT_NORM,
gguf-py/gguf/tensor_mapping.py
+3 -1
View File
@@ -225,6 +225,7 @@ class TensorNameMap:
"rwkv.blocks.{bid}.ln2", # rwkv6
"model.layers.{bid}.ln2", # rwkv7
"model.layers.{bid}.post_attention_layernorm", # cogvlm
"model.layers.{bid}.self_attn.norm", # minimax-01
),
# Attention query-key-value
@@ -321,7 +322,7 @@ class TensorNameMap:
"h.{bid}.self_attention.dense", # bloom
"model.layers.{bid}.self_attn.o_proj", # llama-hf nemotron olmoe olmo2 phimoe
"layers.{bid}.self_attn.o_proj", # embeddinggemma
"model.layers.{bid}.self_attn.out_proj", # lfm2
"model.layers.{bid}.self_attn.out_proj", # lfm2 minimax-01
"model.layers.{bid}.self_attn.linear_attn", # deci
"layers.{bid}.attention.wo", # llama-pth
"encoder.layer.{bid}.attention.output.dense", # bert
@@ -385,6 +386,7 @@ class TensorNameMap:
"model.layers.{bid}.self_attn.gate_proj", # afmoe muse-glimmer
"model.layers.{bid}.linear_attn.in_proj_z", # qwen3.5
"model.layers.{bid}.self_attn.g_proj", # step3.5 head-wise attention gate
"model.layers.{bid}.self_attn.output_gate", # minimax-01
),
# Feed-forward norm