root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-27 20:04:35 +00:00
Code Issues Actions 3 Packages Projects Releases Wiki Activity

handle rope-theta

Browse Source
This commit is contained in:
Sourab Mangrulkar 2024-03-01 15:29:36 +05:30
parent fdd886f7b4
commit b67b8f6451
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -96,6 +96,8 @@ class Model:
if (n_head_kv := self.hparams.get("num_key_value_heads")) is not None:
self.gguf_writer.add_head_count_kv(n_head_kv)
if (rope_theta := self.hparams.get("rope_theta")) is not None:
self.gguf_writer.add_rope_freq_base(rope_theta)
if (f_rms_eps := self.hparams.get("rms_norm_eps")) is not None:
self.gguf_writer.add_layer_norm_rms_eps(f_rms_eps)
if (f_norm_eps := self.find_hparam(["layer_norm_eps", "layer_norm_epsilon", "norm_epsilon"], optional=True)) is not None: