Public/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-20 01:31:31 +02:00
Code Issues Packages Projects Releases Wiki Activity

Add custom add_ functions

Browse Source
This commit is contained in:
Andrei Betlen
2024-06-28 15:58:02 -04:00
parent d3d3c4eb35
commit d1137c20f1
2 changed files with 8 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
convert-hf-to-gguf.py
+2 -4
View File
@@ -2363,12 +2363,10 @@ class Gemma2Model(Model):
self.gguf_writer.add_key_length(hparams["head_dim"])
self.gguf_writer.add_value_length(hparams["head_dim"])
self.gguf_writer.add_file_type(self.ftype)
self.gguf_writer.add_float32(
gguf.Keys.LLM.ATTN_LOGIT_SOFTCAPPING.format(arch=self.model_arch),
self.gguf_writer.add_attn_logit_softcapping(
self.hparams["attn_logit_softcapping"]
)
self.gguf_writer.add_float32(
gguf.Keys.LLM.FINAL_LOGIT_SOFTCAPPING.format(arch=self.model_arch),
self.gguf_writer.add_final_logit_softcapping(
self.hparams["final_logit_softcapping"]
)
gguf-py/gguf/gguf_writer.py
+6
View File
@@ -516,6 +516,12 @@ class GGUFWriter:
def add_logit_scale(self, value: float) -> None:
self.add_float32(Keys.LLM.LOGIT_SCALE.format(arch=self.arch), value)
def add_attn_logit_softcapping(self, value: float) -> None:
self.add_float32(Keys.LLM.ATTN_LOGIT_SOFTCAPPING.format(arch=self.arch), value)
def add_final_logit_softcapping(self, value: float) -> None:
self.add_float32(Keys.LLM.FINAL_LOGIT_SOFTCAPPING.format(arch=self.arch), value)
def add_expert_count(self, count: int) -> None:
self.add_uint32(Keys.LLM.EXPERT_COUNT.format(arch=self.arch), count)