Upload LlamaForCausalLM

model-00001-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca7ac7a9e5c1567fa5ed7365a4444a1abbe682c164502ea710e4af17c8599ce3
-size 4988268040
+oid sha256:e4329746d1f9e6010043afbca11462aee10a68d9966ffe142f814e89ee955176
+size 4999780232

model-00002-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b85f42812aab6e661ae6ef30a3d67bfe07807b49ea2e5c722ebbf1d20fa26902
-size 4899116440
+oid sha256:70f638831735dcfee418ae0363db010fe342aef649d0eaeb808bcb7720e70d61
+size 4999813088

model-00003-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb4180d949bfc4c0df3dc72d93a7b30c7783d833cb9ce44ff64d2ed4a8680b5c
-size 4999813120
+oid sha256:3128278f537323a2f384a511907c44d16efea5addab68ea90057084d747b9546
+size 4999813128

model-00004-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5458b0665ab20f2262623ae839270b55186fbcb3654136775b79724478e83c34
-size 4999813128
+oid sha256:c29a2c62843c49898e43af5ab32ec1c5b7c291e8f8552df517249d7b42becbb8
+size 4832007496

model-00005-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f4a242834684ea51a8f471878aec1b230494b683577d5e1e2dccc94b1cf4f96
-size 4832007496
+oid sha256:69198c0b34ad27800dde40a014b635f1b92a6cda5dbd7f7595a65dac4c3a4540
+size 4999813120

model-00006-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e68a32b2cef80e9a752578eb416b24201c60da71d6dff005000a226e30bdbf0e
-size 3724710464
+oid sha256:1538e3c78f8613450ef8195a8013a59f4d391ca9a00c0ba49b6677d84fd5d777
+size 3612501616

model.safetensors.index.json

@@ -23,24 +23,24 @@
     "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
     "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
     "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
     "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
@@ -77,11 +77,11 @@
     "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
     "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
@@ -91,10 +91,10 @@
     "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
     "model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
@@ -142,8 +142,8 @@
     "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.22.input_layernorm.weight": "model-00005-of-00006.safetensors",
     "model.layers.22.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
     "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
@@ -185,24 +185,24 @@
     "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
     "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.28.input_layernorm.weight": "model-00006-of-00006.safetensors",
     "model.layers.28.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.28.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
     "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
     "model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
     "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
@@ -250,11 +250,11 @@
     "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
     "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
     "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
@@ -293,6 +293,6 @@
     "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "model.norm.weight": "model-00006-of-00006.safetensors"
+    "model.norm.weight": "model-00001-of-00006.safetensors"
   }
 }