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

Fix aya-23 conversion scripts (#7539)

Browse source
This commit is contained in:
Galunid 2024-05-26 16:02:34 +02:00 • committed by GitHub
parent c429b33beb
commit 32a28217f4
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-hf-to-gguf.py
View file

@ -2395,7 +2395,8 @@ class CommandR2Model(Model):
# max_position_embeddings = 8192 in config.json but model was actually
# trained on 128k context length
self.hparams["max_position_embeddings"] = self.hparams["model_max_length"]
# aya-23 models don't have model_max_length specified
self.hparams["max_position_embeddings"] = self.find_hparam(["model_max_length", "max_position_embeddings"])
def set_gguf_parameters(self):
super().set_gguf_parameters()