mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-06-09 07:16:44 +02:00
Piotr Wilkin (ilintar)
cc7200bf12
* move conversion code to a dedicated conversion directory and split the files akin to the src/models architecture --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
15 lines
409 B
Python
15 lines
409 B
Python
from __future__ import annotations
|
|
|
|
from .base import ModelBase, TextModel, gguf
|
|
|
|
|
|
@ModelBase.register("MaincoderForCausalLM")
|
|
class MaincoderModel(TextModel):
|
|
model_arch = gguf.MODEL_ARCH.MAINCODER
|
|
|
|
def set_gguf_parameters(self):
|
|
super().set_gguf_parameters()
|
|
|
|
if (head_dim := self.hparams.get("head_dim")) is not None:
|
|
self.gguf_writer.add_rope_dimension_count(head_dim)
|