Trained with Unsloth

pytorch_model-00001-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cde958cdf3fadeb39988e8f06757a565e152c947e01ed7ae19b98076336dc66
-size 4957627586
+oid sha256:9db1d62d20b1fb85148fc5a288e47ca4d707283f3479ab9d5561146aaa03d747
+size 4983825789

pytorch_model-00002-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:767a875d33de970532c1233474e218fe8344a7a1c986b69e81f1fee7db54e626
-size 1214384514
+oid sha256:169df8ba9ccb4e93588b382233f8d7daecf5567cbc7f89170f8a307d6142be57
+size 1278363922

pytorch_model.bin.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 6171877376
+    "total_size": 6262054912
   },
   "weight_map": {
     "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
@@ -244,11 +244,11 @@
     "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.26.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
     "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.27.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
     "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.27.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
     "model.layers.27.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
     "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
     "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
@@ -261,13 +261,13 @@
     "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
     "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
     "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.28.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
-    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.28.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
-    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.28.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
-    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.28.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
     "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
     "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
     "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",