mirror of
https://github.com/oobabooga/text-generation-webui.git
synced 2024-11-22 16:17:57 +01:00
Update models_settings.py: add default alpha_value, add proper compress_pos_emb for newer GGUFs (#6111)
This commit is contained in:
parent
b1187fc9a5
commit
a85749dcbe
@ -16,6 +16,7 @@ def get_fallback_settings():
|
|||||||
'n_ctx': 2048,
|
'n_ctx': 2048,
|
||||||
'rope_freq_base': 0,
|
'rope_freq_base': 0,
|
||||||
'compress_pos_emb': 1,
|
'compress_pos_emb': 1,
|
||||||
|
'alpha_value': 1,
|
||||||
'truncation_length': shared.settings['truncation_length'],
|
'truncation_length': shared.settings['truncation_length'],
|
||||||
'skip_special_tokens': shared.settings['skip_special_tokens'],
|
'skip_special_tokens': shared.settings['skip_special_tokens'],
|
||||||
'custom_stopping_strings': shared.settings['custom_stopping_strings'],
|
'custom_stopping_strings': shared.settings['custom_stopping_strings'],
|
||||||
@ -58,6 +59,8 @@ def get_model_metadata(model):
|
|||||||
model_settings['rope_freq_base'] = metadata[k]
|
model_settings['rope_freq_base'] = metadata[k]
|
||||||
elif k.endswith('rope.scale_linear'):
|
elif k.endswith('rope.scale_linear'):
|
||||||
model_settings['compress_pos_emb'] = metadata[k]
|
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'):
|
elif k.endswith('block_count'):
|
||||||
model_settings['n_gpu_layers'] = metadata[k] + 1
|
model_settings['n_gpu_layers'] = metadata[k] + 1
|
||||||
|
|
||||||
|
Loading…
Reference in New Issue
Block a user