Upload trained reward model

reference/adapter_config.json

@@ -25,12 +25,12 @@
   "revision": null,
   "target_modules": [
     "gate_proj",
-    "o_proj",
-    "up_proj",
     "k_proj",
-    "v_proj",
+    "down_proj",
+    "o_proj",
     "q_proj",
-    "down_proj"
+    "v_proj",
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

reward/adapter_config.json

@@ -28,11 +28,11 @@
   "revision": null,
   "target_modules": [
     "gate_proj",
-    "o_proj",
     "k_proj",
     "down_proj",
-    "v_proj",
+    "o_proj",
     "q_proj",
+    "v_proj",
     "up_proj"
   ],
   "task_type": "SEQ_CLS",

reward/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40913392efe9fa98f604c13926068499518ba8e6cdef5d2fa95d0b78ccf54c2f
+oid sha256:5d1d0b3e5c08883117b481cfef43073ab7112e5c17543d375b70090a41cc4bca
 size 323018720

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d47e2eb397104ed176cc05078c98144471ea3a203dc595058ebc55878660f2d
+oid sha256:d0a0f29b308507da95e2765eee680cc9fb31429b3f8969f1334d70b21265b765
 size 5496