update model

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b49426aff7a6d72b05154b5654aa84a1252e60196cb377aa69a50f1acc40633c
-size 4915916176
+oid sha256:bd35c1076ccd1dcc87d616d05511289bb94bbbeefc47198c8545b36736dca64f
+size 1168138808

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd35c1076ccd1dcc87d616d05511289bb94bbbeefc47198c8545b36736dca64f
-size 1168138808
+oid sha256:b49426aff7a6d72b05154b5654aa84a1252e60196cb377aa69a50f1acc40633c
+size 4915916176

model.safetensors.index.json

@@ -3,7 +3,7 @@
     "total_size": 16060522496
   },
   "weight_map": {
-    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "lm_head.weight": "model-00002-of-00004.safetensors",
     "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
     "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
@@ -122,96 +122,96 @@
     "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
     "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
     "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
@@ -221,24 +221,24 @@
     "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.30.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
     "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
@@ -293,6 +293,6 @@
     "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.norm.weight": "model-00004-of-00004.safetensors"
+    "model.norm.weight": "model-00002-of-00004.safetensors"
   }
 }