p04798526
/
LLaMA-Factory-310P3
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fix inference in llamaboard

This commit is contained in:
hoshi-hiyouga 2024-04-24 13:53:39 +08:00 committed by GitHub
parent 44a43ee152
commit f36057ea03
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/llmtuner/webui/runner.py
View File

@ -222,7 +222,7 @@ class Runner:
quantization_bit=int(get("top.quantization_bit")) if get("top.quantization_bit") in ["8", "4"] else None,
template=get("top.template"),
rope_scaling=get("top.rope_scaling") if get("top.rope_scaling") in ["linear", "dynamic"] else None,
flash_attn=(get("top.booster") == "flashattn"),
flash_attn="fa2" if get("top.booster") == "flashattn2" else "auto",
use_unsloth=(get("top.booster") == "unsloth"),
dataset_dir=get("eval.dataset_dir"),
dataset=",".join(get("eval.dataset")),