CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-03 09:22:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix head count kv

Browse Source
This commit is contained in:
Meng Zhang
2023-09-15 12:56:20 +08:00
parent 77c7ec179c
commit 0be15e162c
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
convert-starcoder-hf-to-gguf.py
View File

@@ -109,6 +109,7 @@ gguf_writer.add_max_position_embeddings(hparams["n_positions"])
gguf_writer.add_feed_forward_length(4 * hparams["n_embd"]) gguf_writer.add_feed_forward_length(4 * hparams["n_embd"])
gguf_writer.add_block_count(block_count) gguf_writer.add_block_count(block_count)
gguf_writer.add_head_count(hparams["n_head"]) gguf_writer.add_head_count(hparams["n_head"])
gguf_writer.add_head_count_kv(1)
gguf_writer.add_layer_norm_eps(hparams["layer_norm_epsilon"]) gguf_writer.add_layer_norm_eps(hparams["layer_norm_epsilon"])
gguf_writer.add_file_type(ftype) gguf_writer.add_file_type(ftype)