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

convert-hf : add missing ftype to Baichuan and Xverse

Browse source 
I didn't notice these on my first pass.
This commit is contained in:
Francis Couture-Harpin 2024-05-12 12:56:03 -04:00
parent 2b1e5ea37b
commit 65a1a58562
1 changed files with 2 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

2
convert-hf-to-gguf.py
View file

@ -846,6 +846,7 @@ class BaichuanModel(Model):
self.gguf_writer.add_head_count(head_count)
self.gguf_writer.add_head_count_kv(head_count_kv)
self.gguf_writer.add_layer_norm_rms_eps(self.hparams["rms_norm_eps"])
self.gguf_writer.add_file_type(self.ftype)
if self.hparams.get("rope_scaling") is not None and "factor" in self.hparams["rope_scaling"]:
if self.hparams["rope_scaling"].get("type") == "linear":
@ -968,6 +969,7 @@ class XverseModel(Model):
self.gguf_writer.add_head_count(head_count)
self.gguf_writer.add_head_count_kv(head_count_kv)
self.gguf_writer.add_layer_norm_rms_eps(self.hparams["rms_norm_eps"])
self.gguf_writer.add_file_type(self.ftype)
if self.hparams.get("rope_scaling") is not None and "factor" in self.hparams["rope_scaling"]:
if self.hparams["rope_scaling"].get("type") == "linear":