tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-14 12:19:48 -04:00
Code Issues Packages Projects Releases Wiki Activity

model : add hunyuan dense (#14878)

Browse Source 
* support hunyuan_v1_dense

Signed-off-by: stevenkuang <stevenkuang@tencent.com>

* update hunyuan_moe to hunyuan_v1_moe

Signed-off-by: stevenkuang <stevenkuang@tencent.com>

* fix rope alpha assert and bos token

Signed-off-by: stevenkuang <stevenkuang@tencent.com>

* add blank line

Signed-off-by: stevenkuang <stevenkuang@tencent.com>

* Revert "update hunyuan_moe to hunyuan_v1_moe"

This reverts commit aa973ca219.

* use hunyuan_dense instead of hunyuan_v1_dense

Signed-off-by: stevenkuang <stevenkuang@tencent.com>

* fix hunyuan_moe chat template

Signed-off-by: stevenkuang <stevenkuang@tencent.com>

* remove leftover code

Signed-off-by: stevenkuang <stevenkuang@tencent.com>

* update hunyuan dense chat template

Signed-off-by: stevenkuang <stevenkuang@tencent.com>

* fix hunyuan dense vocab and chat template

Signed-off-by: stevenkuang <stevenkuang@tencent.com>

---------

Signed-off-by: stevenkuang <stevenkuang@tencent.com>
This commit is contained in:
stevenkuang
2025-08-01 21:31:12 +08:00
committed by GitHub
parent 1c872f71fb
commit 0f5ccd6fd1
10 changed files with 351 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
gguf-py/gguf/constants.py
View File

@@ -376,6 +376,7 @@ class MODEL_ARCH(IntEnum):
ERNIE4_5 = auto()
ERNIE4_5_MOE = auto()
HUNYUAN_MOE = auto()
HUNYUAN_DENSE = auto()
SMOLLM3 = auto()
LFM2 = auto()
DREAM = auto()
@@ -697,6 +698,7 @@ MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = {
MODEL_ARCH.ERNIE4_5_MOE: "ernie4_5-moe",
MODEL_ARCH.FALCON_H1: "falcon-h1",
MODEL_ARCH.HUNYUAN_MOE: "hunyuan-moe",
MODEL_ARCH.HUNYUAN_DENSE: "hunyuan-dense",
MODEL_ARCH.SMOLLM3: "smollm3",
MODEL_ARCH.LFM2: "lfm2",
MODEL_ARCH.DREAM: "dream",
@@ -2471,6 +2473,22 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.FFN_DOWN_SHEXP,
MODEL_TENSOR.FFN_UP_SHEXP,
],
MODEL_ARCH.HUNYUAN_DENSE: [
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,
MODEL_TENSOR.FFN_DOWN,
MODEL_TENSOR.FFN_UP,
],
MODEL_ARCH.SMOLLM3: [
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.OUTPUT_NORM,