tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-09-05 22:58:12 -04:00
Code Issues Packages Projects Releases Wiki Activity

model : add PLaMo-2 support (#14560)

Browse Source 
* Add PLaMo-2 model using hybrid memory module

* Fix z shape

* Add cmath to include from llama-vocab.h

* Explicitly dequantize normalization weights before RoPE apply

* Revert unnecessary cast because the problem can be solved by excluding attn_k, attn_q when quantizing

* Use ATTN_K/Q_NORM for k,q weights to prevent quantization

* Remove SSM_BCDT that is not used from anywhere

* Do not duplicate embedding weights for output.weight

* Fix tokenizer encoding problem for multibyte strings

* Apply suggestion from @CISC

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

* Update src/llama-model.cpp

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

* Use LLM_FFN_SWIGLU instead of splitting ffn_gate and ffn_up

* Remove unnecessary part for Grouped Query Attention

* Fix how to load special token id to gguf

* Remove unused tensor mapping

* Update src/llama-model.cpp

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

* Remove llama_vocab_plamo2 class and replace it with llm_tokenizer_plamo2_session to follow the other tokenizer implementations

* Update src/llama-vocab.cpp

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Update convert_hf_to_gguf.py

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

* Update src/llama-model.cpp

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

* Update src/llama-model.cpp

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

* Update convert_hf_to_gguf.py

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

* Update convert_hf_to_gguf.py

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

* Fix plamo2 tokenizer session to prevent multiple calls of build()

---------

Co-authored-by: Francis Couture-Harpin <git@compilade.net>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Shunta Saito
2025-07-16 01:11:42 +09:00
committed by GitHub
parent cbc68be51d
commit 68e37a61a7
8 changed files with 1048 additions and 44 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
gguf-py/gguf/constants.py
View File

@@ -317,6 +317,7 @@ class MODEL_ARCH(IntEnum):
PHI3 = auto()
PHIMOE = auto()
PLAMO = auto()
PLAMO2 = auto()
CODESHELL = auto()
ORION = auto()
INTERNLM2 = auto()
@@ -631,6 +632,7 @@ MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = {
MODEL_ARCH.PHI3: "phi3",
MODEL_ARCH.PHIMOE: "phimoe",
MODEL_ARCH.PLAMO: "plamo",
MODEL_ARCH.PLAMO2: "plamo2",
MODEL_ARCH.CODESHELL: "codeshell",
MODEL_ARCH.ORION: "orion",
MODEL_ARCH.INTERNLM2: "internlm2",
@@ -1369,6 +1371,36 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.FFN_DOWN,
MODEL_TENSOR.FFN_UP,
],
MODEL_ARCH.PLAMO2: [
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.OUTPUT_NORM,
MODEL_TENSOR.OUTPUT,
MODEL_TENSOR.ROPE_FREQS,
MODEL_TENSOR.ATTN_NORM,
MODEL_TENSOR.ATTN_QKV,
MODEL_TENSOR.ATTN_Q,
MODEL_TENSOR.ATTN_K,
MODEL_TENSOR.ATTN_OUT,
MODEL_TENSOR.ATTN_ROT_EMBD,
MODEL_TENSOR.ATTN_Q_NORM,
MODEL_TENSOR.ATTN_K_NORM,
MODEL_TENSOR.ATTN_POST_NORM,
MODEL_TENSOR.FFN_NORM,
MODEL_TENSOR.FFN_GATE,
MODEL_TENSOR.FFN_DOWN,
MODEL_TENSOR.FFN_UP,
MODEL_TENSOR.FFN_POST_NORM,
MODEL_TENSOR.SSM_IN,
MODEL_TENSOR.SSM_CONV1D,
MODEL_TENSOR.SSM_X,
MODEL_TENSOR.SSM_DT,
MODEL_TENSOR.SSM_A,
MODEL_TENSOR.SSM_D,
MODEL_TENSOR.SSM_OUT,
MODEL_TENSOR.SSM_DT_NORM,
MODEL_TENSOR.SSM_B_NORM,
MODEL_TENSOR.SSM_C_NORM,
],
MODEL_ARCH.GPT2: [
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.POS_EMBD,