Upload trained reward model

reference/adapter_config.json

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

reward/adapter_config.json

@@ -27,13 +27,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "q_proj",
-    "up_proj",
     "k_proj",
     "down_proj",
+    "up_proj",
     "v_proj",
-    "o_proj"
+    "o_proj",
+    "gate_proj",
+    "q_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:c1047d03a91231a9d54df4f5506f39f31e59eec1b276a525dd605e5bf2084b4c
-size 6627220768
+oid sha256:b5e6009e06907722e501a459063a8fd3ca0ebb290012d2c7159ce0a51e3b9006
+size 6627188000

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7499f43c74b3efcd0f10f00ccfdf4f235fb2836b04ea67996ebdbc43190d356
+oid sha256:20d1d2dc5117efa913e6cd787bc97e711be47d7e947c4855cb7539f773a6b8c3
 size 5560