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

release v0.2.2, fix #1478 #1466

This commit is contained in:
hiyouga 2023-11-13 23:09:05 +08:00
parent 87390ae3b7
commit 35cc1e28f6
3 changed files with 10 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/llmtuner/__init__.py
View File

@ -7,4 +7,4 @@ from llmtuner.tuner import export_model, run_exp
from llmtuner.webui import create_ui, create_web_demo from llmtuner.webui import create_ui, create_web_demo
__version__ = "0.2.1" __version__ = "0.2.2"

8
src/llmtuner/extras/constants.py
View File

@ -150,6 +150,14 @@ register_model_group(
) )
register_model_group(
models={
"LingoWhale-8B": "deeplang-ai/LingoWhale-8B"
},
module="qkv_proj"
)
register_model_group( register_model_group(
models={ models={
"LLaMA-7B": "huggyllama/llama-7b", "LLaMA-7B": "huggyllama/llama-7b",

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

@ -136,7 +136,7 @@ class Runner:
args["upcast_layernorm"] = True args["upcast_layernorm"] = True
if args["stage"] == "ppo": if args["stage"] == "ppo":
args["reward_model"] = get("train.reward_model") args["reward_model"] = get_save_dir(get("top.model_name"), get("top.finetuning_type"), get("train.reward_model"))
if args["stage"] == "dpo": if args["stage"] == "dpo":
args["dpo_beta"] = get("train.dpo_beta") args["dpo_beta"] = get("train.dpo_beta")