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

llama : fix Gemma-2 Query scaling factors (#8473)

Browse source 
* 9B - query_pre_attn_scalar = 256 not 224

See 03e657582d

Gemma 9b should use 256 and not 224 (self.config.hidden_size // self.config.num_attention_heads)

* llama : fix Gemma-2 Query scaling factor

ggml-ci

---------

Co-authored-by: Daniel Han <danielhanchen@gmail.com>
This commit is contained in:
Georgi Gerganov 2024-07-14 14:05:09 +03:00 • committed by GitHub
parent e236528e76
commit 73cf442e7b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 6 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

5
convert_hf_to_gguf.py
View file

@ -2504,11 +2504,6 @@ class Gemma2Model(Model):
)
self.gguf_writer.add_sliding_window(self.hparams["sliding_window"])
# sanity check
attn_scalar = self.hparams["query_pre_attn_scalar"]
if attn_scalar != hparams["hidden_size"] / hparams["num_attention_heads"]:
raise ValueError("query_pre_attn_scalar must be equal to n_embd / n_head")
def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iterable[tuple[str, Tensor]]:
del bid # unused