Model save

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: Qwen/Qwen2.5-3B-Instruct
+base_model: Qwen/Qwen2.5-7B-Instruct
 library_name: transformers
 model_name: mountain_car_continuous-test
 tags:
@@ -11,7 +11,7 @@ licence: license
 
 # Model Card for mountain_car_continuous-test
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct).
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

final/README.md

@@ -1,5 +1,5 @@
 ---
-base_model: Qwen/Qwen2.5-3B-Instruct
+base_model: Qwen/Qwen2.5-7B-Instruct
 library_name: peft
 ---
 

final/adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "Qwen/Qwen2.5-3B-Instruct",
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
@@ -24,8 +24,8 @@
   "revision": null,
   "target_modules": [
     "o_proj",
-    "q_proj",
     "up_proj",
+    "q_proj",
     "down_proj",
     "k_proj"
   ],

final/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a1c8e8fc628b4d0e290ff44d2938034fe3a2dde720ba31dc4f0e9104344c4c0
-size 42219872
+oid sha256:aa504608a6cbb5cfefdc353b93dc5a15b30a4726c40704744a092e1af918de9d
+size 56922184

final/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f902aa09d515dbfffe3618672472748a7e117074388ed1ca0cbb5d2fa77cb3d8
+oid sha256:fff5fde967c1697efecb5dc7ede5b5c7a9379985b398d7f7ae806fc6ab079820
 size 5816