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 ExLlamaV2 backend

Browse source 
- archived upstream: 7dc12af3a8
- replaced by ExLlamaV3, which has much better quantization accuracy
This commit is contained in:
oobabooga 2026-03-05 13:57:21 -08:00
parent 134ac8fc29
commit 2f08dce7b0
19 changed files with 22 additions and 713 deletions
Download patch file Download diff file Expand all files Collapse all files

4
modules/evaluate.py
View file

@ -46,10 +46,6 @@ def calculate_perplexity(models, input_dataset, stride, _max_length):
logger.error("Perplexity evaluation is not implemented for the llama.cpp loader.")
raise ValueError
if shared.args.loader == "ExLlamav2":
logger.error("ExLlamav2_HF is required for perplexity evaluation with EXL2 models. Please reload the model with ExLlamav2_HF instead of ExLlamav2.")
raise ValueError
if not shared.args.no_use_fast:
logger.warning("--no_use_fast is not set. If tokenizing the input dataset takes a long time, try reloading the model with that option set/checked.")