root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-25 02:44:36 +00:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity

py : fix persimmon n_rot conversion (#5460)

Browse Source 
* convert : fix persimmon offical weight conversion to write correct n_rot.

* Update convert-persimmon-to-gguf.py

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Lee 2024-02-13 01:29:57 +08:00 committed by GitHub
parent 43fe07c1a4
commit dbd8828eb0
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
convert-persimmon-to-gguf.py
View File

@ -88,7 +88,8 @@ def main():
gguf_writer.add_embedding_length(hidden_size)
gguf_writer.add_block_count(block_count)
gguf_writer.add_feed_forward_length(hparams.ffn_hidden_size)
gguf_writer.add_rope_dimension_count(hidden_size // head_count)
# ref: https://github.com/ggerganov/llama.cpp/pull/4889/commits/eea19039fc52ea2dbd1aab45b59ab4e3e29a3443
gguf_writer.add_rope_dimension_count(hidden_size // head_count // 2)
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)