CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

mtmd : support InternVL 2.5 and 3 (#13422)

Browse Source 
* convert : internvl support

* InternVL3-1B working

* fix regression

* rm mobilevlm from test

* fix conversion

* add test for internvl

* add to list of pre-quant

* restore boi/eoi check

* add clarify comment for norm eps
This commit is contained in:
Xuan-Son Nguyen
2025-05-10 16:26:42 +02:00
committed by GitHub
parent d8919424f1
commit 053367d149
9 changed files with 243 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
gguf-py/gguf/constants.py
View File

@@ -491,6 +491,8 @@ class MODEL_TENSOR(IntEnum):
V_ENC_FFN_UP = auto()
V_ENC_FFN_GATE = auto()
V_ENC_FFN_DOWN = auto()
V_LAYER_SCALE_1 = auto()
V_LAYER_SCALE_2 = auto()
V_PRE_NORM = auto()
V_POST_NORM = auto()
V_MM_INP_NORM = auto()
@@ -748,6 +750,8 @@ TENSOR_NAMES: dict[MODEL_TENSOR, str] = {
MODEL_TENSOR.V_ENC_FFN_UP: "v.blk.{bid}.ffn_up",
MODEL_TENSOR.V_ENC_FFN_GATE: "v.blk.{bid}.ffn_gate",
MODEL_TENSOR.V_ENC_FFN_DOWN: "v.blk.{bid}.ffn_down",
MODEL_TENSOR.V_LAYER_SCALE_1: "v.blk.{bid}.ls1",
MODEL_TENSOR.V_LAYER_SCALE_2: "v.blk.{bid}.ls2",
MODEL_TENSOR.V_PRE_NORM: "v.pre_ln",
MODEL_TENSOR.V_POST_NORM: "v.post_ln",
MODEL_TENSOR.V_MM_INP_PROJ: "mm.input_projection",
@@ -786,6 +790,8 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.V_ENC_FFN_UP,
MODEL_TENSOR.V_ENC_FFN_GATE,
MODEL_TENSOR.V_ENC_FFN_DOWN,
MODEL_TENSOR.V_LAYER_SCALE_1,
MODEL_TENSOR.V_LAYER_SCALE_2,
MODEL_TENSOR.V_PRE_NORM,
MODEL_TENSOR.V_POST_NORM,
MODEL_TENSOR.V_MM_INP_PROJ,
@@ -2167,6 +2173,7 @@ class VisionProjectorType:
PIXTRAL = "pixtral"
QWEN2VL = "qwen2vl_merger"
QWEN25VL = "qwen2.5vl_merger"
INTERNVL = "internvl"
# Items here are (block size, type size)