423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-16 20:00:36 +08:00
Code Issues Packages Projects Releases Wiki Activity

update arg name

Browse Source
This commit is contained in:
hiyouga
2024-07-03 23:23:24 +08:00
parent 575a02a23d
commit 8a6a7b9c8a
3 changed files with 20 additions and 34 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
src/llamafactory/extras/constants.py
View File

@@ -78,22 +78,22 @@ TRAINING_STAGES = {
STAGES_USE_PAIR_DATA = {"rm", "dpo"}
SUPPORTED_CLASS_FOR_S2ATTN = {"llama"}
SUPPORTED_CLASS_EFFECIENT_PACKING = [
SUPPORTED_CLASS_FOR_BLOCK_DIAG_ATTN = {
"falcon",
"gemma",
"gemma2",
"jamba",
"llama",
"mistral",
"mixtral",
"qwen2",
"qwen2_moe",
"falcon",
"phi",
"phi3",
"gemma",
"gemmoe",
"qwen2",
"qwen2_moe",
"starcoder2",
"jamba"
]
}
SUPPORTED_CLASS_FOR_S2ATTN = {"llama"}
V_HEAD_WEIGHTS_NAME = "value_head.bin"