tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-18 00:27:31 +00:00
Code Issues Packages Projects Releases Wiki Activity

model : add SmolLM3 (#14581)

Browse Source 
* Init - first pass.

* Model -> ModelBase.

* fix errors in conversion.

* Update the graph.

* up.

* up.

* wip

* cgraph ok

* rm redundant code

---------

Co-authored-by: Vaibhavs10 <vaibhavs10@gmail.com>
This commit is contained in:
Xuan-Son Nguyen
2025-07-08 18:07:01 +02:00
committed by GitHub
parent bb4f7a9e4e
commit 08382869a2
6 changed files with 233 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@ -358,6 +358,7 @@ class MODEL_ARCH(IntEnum):
ARCEE = auto()
ERNIE4_5 = auto()
HUNYUAN_MOE = auto()
SMOLLM3 = auto()
class VISION_PROJECTOR_TYPE(IntEnum):
@ -662,6 +663,7 @@ MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = {
MODEL_ARCH.ARCEE: "arcee",
MODEL_ARCH.ERNIE4_5: "ernie4_5",
MODEL_ARCH.HUNYUAN_MOE: "hunyuan-moe",
MODEL_ARCH.SMOLLM3: "smollm3",
}
VISION_PROJECTOR_TYPE_NAMES: dict[VISION_PROJECTOR_TYPE, str] = {
@ -2234,6 +2236,22 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.FFN_DOWN_SHEXP,
MODEL_TENSOR.FFN_UP_SHEXP,
],
MODEL_ARCH.SMOLLM3: [
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.OUTPUT_NORM,
MODEL_TENSOR.OUTPUT,
MODEL_TENSOR.ROPE_FREQS,
MODEL_TENSOR.ATTN_NORM,
MODEL_TENSOR.ATTN_Q,
MODEL_TENSOR.ATTN_K,
MODEL_TENSOR.ATTN_V,
MODEL_TENSOR.ATTN_OUT,
MODEL_TENSOR.ATTN_ROT_EMBD,
MODEL_TENSOR.FFN_NORM,
MODEL_TENSOR.FFN_GATE,
MODEL_TENSOR.FFN_DOWN,
MODEL_TENSOR.FFN_UP,
],
# TODO
}