release v0.2.2, fix #1478 #1466

src/llmtuner/__init__.py

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

src/llmtuner/extras/constants.py

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

src/llmtuner/webui/runner.py

@@ -136,7 +136,7 @@ class Runner:
             args["upcast_layernorm"] = True
 
         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":
             args["dpo_beta"] = get("train.dpo_beta")