wylab/llama.cpp
1
0
Fork 1
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-06-09 07:16:44 +02:00
Code Issues Packages Projects Releases Wiki Activity

mtp: support for gemma-4 E2B and E4B assistants (#24282)

Browse Source 
* models: update converter to support smaller assistants

* models: add masked_embd tensors to gemma4-assist arch

* gemma-4: remove temp debug for conversion

* gemma-4-mtp: filter out masked_embedding tensors during conversion
This commit is contained in:
Max Krasnyansky
2026-06-08 13:48:52 -07:00
committed by GitHub
parent 42a0afd594
commit 7d2b45b4f7
6 changed files with 34 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
gguf-py/gguf/constants.py
+6
View File
@@ -538,6 +538,8 @@ class VISION_PROJECTOR_TYPE(IntEnum):
class MODEL_TENSOR(IntEnum):
TOKEN_EMBD = auto()
TOKEN_EMBD_NORM = auto()
MASKED_EMBD_CENTROIDS= auto()
MASKED_EMBD_ORDERING = auto()
TOKEN_TYPES = auto()
POS_EMBD = auto()
OUTPUT = auto()
@@ -1087,6 +1089,8 @@ TENSOR_NAMES: dict[MODEL_TENSOR, str] = {
MODEL_TENSOR.TOKEN_EMBD: "token_embd",
MODEL_TENSOR.TOKEN_EMBD_NORM: "token_embd_norm",
MODEL_TENSOR.TOKEN_TYPES: "token_types",
MODEL_TENSOR.MASKED_EMBD_CENTROIDS: "masked_embd_centroids",
MODEL_TENSOR.MASKED_EMBD_ORDERING: "masked_embd_ordering",
MODEL_TENSOR.POS_EMBD: "position_embd",
MODEL_TENSOR.OUTPUT_NORM: "output_norm",
MODEL_TENSOR.OUTPUT: "output",
@@ -2586,6 +2590,8 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_ARCH.GEMMA4_ASSISTANT: [
MODEL_TENSOR.ROPE_FREQS,
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.MASKED_EMBD_CENTROIDS,
MODEL_TENSOR.MASKED_EMBD_ORDERING,
MODEL_TENSOR.OUTPUT_NORM,
MODEL_TENSOR.NEXTN_PROJ_PRE,
MODEL_TENSOR.NEXTN_PROJ_POST,
gguf-py/gguf/tensor_mapping.py
+8
View File
@@ -37,6 +37,14 @@ class TensorNameMap:
"model.embed", # talkie
),
# Masked embeddings
MODEL_TENSOR.MASKED_EMBD_CENTROIDS: (
"masked_embedding.centroids", # gemma-4 E2B/E4B assistants
),
MODEL_TENSOR.MASKED_EMBD_ORDERING: (
"masked_embedding.token_ordering", # gemma-4 E2B/E4B assistants
),
# Token type embeddings
MODEL_TENSOR.TOKEN_TYPES: (
"embeddings.token_type_embeddings", # bert nomic-bert