nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 20 Packages Projects Releases Wiki Activity

dflash: refactor draft model conversion (#25110)

Browse Source 
* dflash: refactor draft model conversion

* apply fix for eagle3 convert
This commit is contained in:
Ruixiang Wang
2026-06-28 20:31:48 +02:00
committed by GitHub
parent c818263f2a
commit fa72bc6826
5 changed files with 31 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files
gguf-py/gguf/gguf_writer.py
+12
View File
@@ -940,6 +940,18 @@ class GGUFWriter:
def add_sliding_window(self, value: int) -> None:
self.add_uint32(Keys.Attention.SLIDING_WINDOW.format(arch=self.arch), value)
def add_block_size(self, value: int) -> None:
self.add_uint32(Keys.LLM.BLOCK_SIZE.format(arch=self.arch), value)
def add_target_layers(self, value: Sequence[int]) -> None:
self.add_array(Keys.LLM.TARGET_LAYERS.format(arch=self.arch), value)
def add_target_hidden_size(self, value: int) -> None:
self.add_uint32(Keys.LLM.TARGET_HIDDEN_SIZE.format(arch=self.arch), value)
def add_norm_before_residual(self, value: bool) -> None:
self.add_bool(Keys.LLM.NORM_BEFORE_RESIDUAL.format(arch=self.arch), value)
def add_attention_scale(self, value: float) -> None:
self.add_float32(Keys.Attention.SCALE.format(arch=self.arch), value)