Upload trained reward model

reference/adapter_config.json

@@ -24,13 +24,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
+    "o_proj",
+    "gate_proj",
     "v_proj",
-    "down_proj",
     "q_proj",
+    "down_proj",
     "k_proj",
-    "o_proj",
-    "gate_proj"
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

reward/adapter_config.json

@@ -27,13 +27,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
+    "o_proj",
+    "gate_proj",
     "v_proj",
-    "down_proj",
     "q_proj",
+    "down_proj",
     "k_proj",
-    "o_proj",
-    "gate_proj"
+    "up_proj"
   ],
   "task_type": "SEQ_CLS",
   "trainable_token_indices": null,

reward/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a89c8fe2fd0848e38f9626594d51248bdee1ffff5dcb1643d357c6dc8e7b30fb
+oid sha256:de10a2bddd01005e2a1381af40d578db4481dc8e2510c7f4b6b0565beea4b4dd
 size 323022816

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7872a7e58bda8f2e58835512e4082a2500996e47b5cb4bdb0e40bb2af599b90
+oid sha256:d7e28f1ac540620765851064c0dc6f759a366a1ec334ebbd393e47651e6fc66e
 size 5496