Update models_settings.py: add default alpha_value, add proper compress_pos_emb for newer GGUFs (#6111)

This commit is contained in:
mefich 2024-06-27 06:17:56 +05:00 committed by GitHub
parent b1187fc9a5
commit a85749dcbe
WARNING! Although there is a key with this ID in the database it does not verify this commit! This commit is SUSPICIOUS.
GPG key ID: B5690EEEBB952194

View file

@ -16,6 +16,7 @@ def get_fallback_settings():
'n_ctx': 2048,
'rope_freq_base': 0,
'compress_pos_emb': 1,
'alpha_value': 1,
'truncation_length': shared.settings['truncation_length'],
'skip_special_tokens': shared.settings['skip_special_tokens'],
'custom_stopping_strings': shared.settings['custom_stopping_strings'],
@ -58,6 +59,8 @@ def get_model_metadata(model):
model_settings['rope_freq_base'] = metadata[k]
elif k.endswith('rope.scale_linear'):
model_settings['compress_pos_emb'] = metadata[k]
elif k.endswith('rope.scaling.factor'):
model_settings['compress_pos_emb'] = metadata[k]
elif k.endswith('block_count'):
model_settings['n_gpu_layers'] = metadata[k] + 1