423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-08-04 20:52:59 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #2730 from cx2333-gt/main

Browse Source 
fix flash_attn in train_web

Former-commit-id: 2185855bdb7d4cb55f3af796e35fb1b0e8dce5e3
This commit is contained in:
hoshi-hiyouga 2024-03-07 14:37:18 +08:00 committed by GitHub
commit 90e66c8d94
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/llmtuner/webui/runner.py
View File

@ -113,7 +113,7 @@ 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") == "flash_attn"),
flash_attn=(get("top.booster") == "flashattn"),
use_unsloth=(get("top.booster") == "unsloth"),
dataset_dir=get("train.dataset_dir"),
dataset=",".join(get("train.dataset")),
@ -200,7 +200,7 @@ 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") == "flash_attn"),
flash_attn=(get("top.booster") == "flashattn"),
use_unsloth=(get("top.booster") == "unsloth"),
dataset_dir=get("eval.dataset_dir"),
dataset=",".join(get("eval.dataset")),