oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2026-04-07 23:53:40 +00:00
Code Issues Projects Releases Packages Wiki Activity

Remove the rope scaling parameters

Browse source 
Now models have 131k+ context length. The parameters can still be
passed to llama.cpp through --extra-flags.
This commit is contained in:
oobabooga 2026-03-14 19:35:12 -07:00
parent 2d3a3794c9
commit f0c16813ef
8 changed files with 10 additions and 68 deletions
Download patch file Download diff file Expand all files Collapse all files

7
modules/transformers_loader.py
View file

@ -136,8 +136,6 @@ def load_model_HF(model_name):
shared.args.load_in_4bit,
shared.args.disk,
shared.args.cpu_memory is not None,
shared.args.compress_pos_emb > 1,
shared.args.alpha_value > 1,
])
# Load the model without any special settings
@ -200,11 +198,6 @@ def load_model_HF(model_name):
if shared.args.disk:
params['offload_folder'] = str(Path(shared.args.disk_cache_dir))
if shared.args.compress_pos_emb > 1:
params['rope_scaling'] = {'type': 'linear', 'factor': shared.args.compress_pos_emb}
elif shared.args.alpha_value > 1:
params['rope_scaling'] = {'type': 'dynamic', 'factor': shared.args.alpha_value}
logger.info("TRANSFORMERS_PARAMS=")
pprint.PrettyPrinter(indent=4, sort_dicts=False).pprint(params)
print()