oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2026-04-06 07:03:37 +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

4
modules/llama_cpp_server.py
View file

@ -403,10 +403,6 @@ class LlamaServer:
if shared.args.cache_type != "fp16" and shared.args.cache_type in llamacpp_valid_cache_types:
cmd += ["--cache-type-k", shared.args.cache_type, "--cache-type-v", shared.args.cache_type]
cache_type = shared.args.cache_type
if shared.args.compress_pos_emb != 1:
cmd += ["--rope-freq-scale", str(1.0 / shared.args.compress_pos_emb)]
if shared.args.rope_freq_base > 0:
cmd += ["--rope-freq-base", str(shared.args.rope_freq_base)]
if shared.args.mmproj not in [None, 'None']:
path = Path(shared.args.mmproj)
if not path.exists():