Upload MistralForCausalLM

config.json

@@ -12,7 +12,7 @@
   "max_position_embeddings": 32768,
   "model_type": "mistral",
   "num_attention_heads": 32,
-  "num_hidden_layers": 31,
+  "num_hidden_layers": 32,
   "num_key_value_heads": 8,
   "rms_norm_eps": 1e-05,
   "rope_theta": 100000,

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06f2c06100d22009d139c764c10f73d67762fc198df9e8a6eedb76eb9397dc12
+oid sha256:645d3a085a80e1d69795fb247a166f72002ac60b8727068a679239490a4fe050
 size 4943178624

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c7707ddd6bf13370930f6fbebcb8a1b93d923171e549bbbe1b7360f3de94e58
+oid sha256:613844c6264bcafb6d79ba297b99c7eed91267c86c374b36ef802dc2d2e46b26
 size 4999819232

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ccb9ea1f858e6e3bef22f3d80529a9be46c70b23d1ee7925f2dd9b70257c6fe
-size 4104307600
+oid sha256:e12da8c2069a6bb3deb3ed98e0de071a880babc3267e7ca8b14c7f4aafae4a23
+size 4540532640

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 14047272960
+    "total_size": 14483496960
   },
   "weight_map": {
     "lm_head.weight": "model-00003-of-00003.safetensors",
@@ -230,6 +230,15 @@
     "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",