Upload LlamaForCausalLM

model-00001-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7291c81f082daae87f89db409c81fd1b736b0947a96b2f0e3ad52d84c2518e6
-size 4988268040
+oid sha256:ab1a32f2da2cb9c25e470973da04c23586862dd5df7a4601800910fee13b7620
+size 4999780232

model-00002-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9adcce97542c503c18fd941dba06635c70634109c6b7412ae3100ae1273e68b4
-size 4899116440
+oid sha256:d2b36613f7216ddc233fe35de1957f01edae4b4957032031da5d106e7c075456
+size 4999813088

model-00003-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:768899c5287442423f89aadf97a0bb7bd4adc99d048e15bc5a275b5b55e00fe5
-size 4999813120
+oid sha256:9a982fac8ff7b8e4ef20d16d7cd8fe860dc16cf9b3194ea3da1a9f42d77cdca2
+size 4999813128

model-00004-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdb0cdc0e2e5c8f483241d35d87b77531714ae44a31bc41d6596c4312e032c32
-size 4999813128
+oid sha256:ac1fe92e982d83286be2aea70d36240906526d8ad88b4342b99d91366b14dc5b
+size 4832007496

model-00005-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f279697f829023fd4b083bfeb23b86cd78a94830d1e891ca83cbf3a4596c688
-size 4832007496
+oid sha256:3e0097a779d637daa7185c77f6ecaa923faf696529957c5558f44060ca80ae24
+size 4999813120

model-00006-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9353090c6a173b5c1fcf2fb6948d3dd368b333f21ac9c58ebca8c2fd05186a5
-size 3724710464
+oid sha256:28b2abac72945e800599f0b710f6acefff3d8263601dd06d408c487aff20757f
+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"
   }
 }