Upload LlamaForCausalLM

model-00001-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3c61675f9bba13e370dca05fa4f14aeb70eb60fb14419ba16a5f92c6b25ced9
-size 4988259848
+oid sha256:ff134d93f2accf795573e2fe290f7e01e5d9082ef19be8349bc9b3c9d5369cfa
+size 4999780144

model-00002-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0b3d1bfc4f7df38a4e2ecf67112fee3755898a7a041ed79001145069017f478
-size 4899116440
+oid sha256:4c9ad1b7077f299882f652b9a2be2ebf27480898d0679bb693a29006233980df
+size 4999813088

model-00003-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29944b195e81c97f2ded160b78d64d26df957a6025a149d97c4eef980c3eac0e
-size 4999813120
+oid sha256:1ce5fb53011999f140fa0222b6d8dc31d1800ccd4e8c29d6b5015d66e6a05ab2
+size 4999813128

model-00004-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:405ed1c25326ebe910f369586f3cf9f9155925358aae113120d1f1e24868f849
-size 4999813128
+oid sha256:8055c2c119a236a6472b75567c941f336bf5c7d16ccee1b043d77a180f9456b8
+size 4832007496

model-00005-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d9e886a3004144ca12423d0611c723522c00fb43a218ccad57a9678fde97f91
-size 4832007496
+oid sha256:0a61c594127b1e4957f56e672931bf9d39940748d3726f8f043bf022e6fe35f7
+size 4999813120

model-00006-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20b2272940a5c68a836c794029c7aabd0705b2518ddc0eff76d77e1a8ef16844
-size 3724718664
+oid sha256:9ed0dbd499d2ae01537fa84499c12943beaef396b1598673cf292a5951d4e098
+size 3612501712

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",