vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

llama : add EXAONE model support (#9025)

Browse source 
* add exaone model support

* add chat template

* fix whitespace

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

* add ftype

* add exaone pre-tokenizer in `llama-vocab.cpp`

Co-Authored-By: compilade <113953597+compilade@users.noreply.github.com>

* fix lint

Co-Authored-By: compilade <113953597+compilade@users.noreply.github.com>

* add `EXAONE` to supported models in `README.md`

* fix space

Co-authored-by: compilade <git@compilade.net>

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: compilade <113953597+compilade@users.noreply.github.com>
Co-authored-by: compilade <git@compilade.net>
This commit is contained in:
Minsoo Cheong 2024-08-16 15:35:18 +09:00 • committed by GitHub
parent fb487bb567
commit c679e0cb5c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
8 changed files with 320 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -220,6 +220,7 @@ class MODEL_ARCH(IntEnum):
T5ENCODER = auto()
JAIS = auto()
NEMOTRON = auto()
EXAONE = auto()
class MODEL_TENSOR(IntEnum):
@ -349,6 +350,7 @@ MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = {
MODEL_ARCH.T5ENCODER: "t5encoder",
MODEL_ARCH.JAIS: "jais",
MODEL_ARCH.NEMOTRON: "nemotron",
MODEL_ARCH.EXAONE: "exaone",
}
TENSOR_NAMES: dict[MODEL_TENSOR, str] = {
@ -1082,6 +1084,22 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.FFN_DOWN,
MODEL_TENSOR.FFN_UP,
],
MODEL_ARCH.EXAONE: [
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
}