Upload LlamaForSequenceClassification

README.md

@@ -1,7 +1,7 @@
 ---
-license: apache-2.0
 datasets:
 - Skywork/Skywork-Reward-Preference-80K-v0.2
+license: apache-2.0
 pipeline_tag: text-classification
 ---
 

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "Ray2333/GRM_Llama3.1_8B_rewardmodel-ft",
+  "_name_or_path": "/home/ry21/robust_rm/GRM_Llama3.1_8B_sftreg_linear_rewardmodel_ft_v0.2",
   "architectures": [
     "LlamaForSequenceClassification"
   ],
@@ -40,7 +40,7 @@
   },
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.45.2",
   "use_cache": true,
   "vhead_layer_type": "linear",

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5218a44a91c18dc161068a0506da7d4f5f941510b2d6ddd038f3eadb2792470b
-size 4976706784
+oid sha256:d0c70baa38a65e504ab28e449e2a9d4493bfc1ff25cb3c9be58a7e422c614e2f
+size 4976706864

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:230b4da53938e6cfe7de4328fce60f3a99c4f76d1f5ca23cab82e86648de5e8c
-size 4999802616
+oid sha256:9fd43a440ef1c39e14b7dd70ad2a4025bf77472cdfa7cbadfbf73944d2c7f7bd
+size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a80c723badd10779d13ace7e558c119134f7eb4c4ae78ce0bd79272df4934a2
-size 4915916080
+oid sha256:8b857de1c5cb3cceb715fcb5f1adf58b6a4fd669618b5b4d2b2a5b9f9d899850
+size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eed858865c77a38673a053b88b2f36133fbb06a036f95c19caa698ef7a2bd833
-size 117473816
+oid sha256:49b7a7658410b1ca932b91c14161adfd4ddb88516ac7172d99f13dcf18210d95
+size 117473824