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

model : add support for Seed-OSS (#15490)

Browse Source 
* First draft

* Fix linter errors

* Added missing sinks nullptr

* Don't forget the llama-arch!

* We're through to the generation stage.

* Fix post-attention norm

* Apply suggestions from code review

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Fix RoPE type

* Fix tensor name and reorder llm_types

* Update gguf-py/gguf/constants.py

Remove nonexistent FFN_POST_NORM tensor

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-model.h

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Add basic chat template

* Add chat template tests

* Remake chat template test

* Apply suggestions from code review

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-chat.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Reorder llm type descriptions

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
Piotr Wilkin (ilintar)
2025-08-23 15:21:52 +02:00
committed by GitHub
parent 9ef536907d
commit b1afcab804
9 changed files with 244 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
gguf-py/gguf/constants.py
View File

@@ -385,6 +385,7 @@ class MODEL_ARCH(IntEnum):
DREAM = auto()
SMALLTHINKER = auto()
LLADA = auto()
SEED_OSS = auto()
class VISION_PROJECTOR_TYPE(IntEnum):
@@ -717,6 +718,7 @@ MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = {
MODEL_ARCH.DREAM: "dream",
MODEL_ARCH.SMALLTHINKER: "smallthinker",
MODEL_ARCH.LLADA: "llada",
MODEL_ARCH.SEED_OSS: "seed_oss",
}
VISION_PROJECTOR_TYPE_NAMES: dict[VISION_PROJECTOR_TYPE, str] = {
@@ -1973,6 +1975,20 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.FFN_DOWN,
MODEL_TENSOR.FFN_UP,
],
MODEL_ARCH.SEED_OSS: [
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.ATTN_NORM,
MODEL_TENSOR.ATTN_Q,
MODEL_TENSOR.ATTN_K,
MODEL_TENSOR.ATTN_V,
MODEL_TENSOR.ATTN_OUT,
MODEL_TENSOR.ATTN_POST_NORM,
MODEL_TENSOR.FFN_GATE,
MODEL_TENSOR.FFN_DOWN,
MODEL_TENSOR.FFN_UP,
MODEL_TENSOR.OUTPUT_NORM,
MODEL_TENSOR.OUTPUT,
],
MODEL_ARCH.OLMOE: [
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.OUTPUT_NORM,