Upload PhiForCausalLM

config.json

@@ -33,5 +33,5 @@
   "torch_dtype": "float32",
   "transformers_version": "4.39.1",
   "use_cache": true,
-  "vocab_size": 70980
+  "vocab_size": 80979
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdda8684ea54eed60e454c6b472fe2445ae2f4568023cda7b5a172b8174c8510
-size 4922665472
+oid sha256:be10fcf4ff5c4ed03ff0cccde11177d35aabbf0fbff0b293fbbd17688a970f98
+size 4998830376

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4611cf8a3b6115b324cdcbc51b6b8ebc595f10453766b7e3c83e8951b44ed9d
-size 4982541992
+oid sha256:00b5645eb87e4496c1094919b5808ed2600afdabda06b71ce5ad6f2de689f717
+size 4982541984

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc88ae76118b844f76aeb260927891c77594cda92df1653649b59f336746d89b
-size 1618751200
+oid sha256:5b114bea52001937245908f743bd55ce63d716a8e232637c2fb9257866eb35d9
+size 1747405836

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 11523908880
+    "total_size": 11728728396
   },
   "weight_map": {
     "lm_head.bias": "model-00003-of-00003.safetensors",
@@ -84,8 +84,8 @@
     "model.layers.13.mlp.fc1.weight": "model-00002-of-00003.safetensors",
     "model.layers.13.mlp.fc2.bias": "model-00002-of-00003.safetensors",
     "model.layers.13.mlp.fc2.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.dense.bias": "model-00001-of-00003.safetensors",
-    "model.layers.13.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.dense.weight": "model-00002-of-00003.safetensors",
     "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
     "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
@@ -324,8 +324,8 @@
     "model.layers.29.mlp.fc2.weight": "model-00003-of-00003.safetensors",
     "model.layers.29.self_attn.dense.bias": "model-00003-of-00003.safetensors",
     "model.layers.29.self_attn.dense.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
     "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.29.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",