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

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

6
convert-hf-to-gguf.py
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"]
)