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

Fix typo layernorm_epsilon should be layer_norm_epsilon

Browse source
This commit is contained in:
Steve Grubb 2024-03-14 12:38:50 -04:00
parent 69ff61397d
commit 059b93f465
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -93,7 +93,7 @@ def main():
gguf_writer.add_head_count(head_count)
gguf_writer.add_head_count_kv(head_count_kv)
gguf_writer.add_rope_freq_base(hparams.rotary_emb_base)
gguf_writer.add_layer_norm_eps(hparams.layernorm_epsilon)
gguf_writer.add_layer_norm_eps(hparams.layer_norm_epsilon)
tokens, scores, toktypes = _get_sentencepiece_tokenizer_info(args.model_dir)
gguf_writer.add_tokenizer_model('llama')