Upload model.safetensors.index.json with huggingface_hub

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 16959981696
+    "total_size": 17859440896
   },
   "weight_map": {
     "language_model.lm_head.weight": "model-00004-of-00004.safetensors",
@@ -77,33 +77,33 @@
     "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
     "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
     "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
     "language_model.model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "language_model.model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "language_model.model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
     "language_model.model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
     "language_model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
     "language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "language_model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "language_model.model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
@@ -185,33 +185,33 @@
     "language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
     "language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
     "language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
     "language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
     "language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
     "language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.28.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.28.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.28.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.28.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.28.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
     "language_model.model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
     "language_model.model.layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "language_model.model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
     "language_model.model.layers.29.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
     "language_model.model.layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "language_model.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.model.layers.29.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
     "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
     "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
@@ -239,33 +239,33 @@
     "language_model.model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
     "language_model.model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
     "language_model.model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
     "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
     "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
     "language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
     "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",