Upload folder using huggingface_hub

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:920101ef445341261c32267787209868fd47c529abbea30c0726b53839d60bb3
+size 4988032848

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1df700e1de159311417205444bb334ff4817169199b079d5475a00a19db3418e
+size 4660036776

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 6174857216
+    "total_size": 9648033280
   },
   "weight_map": {
     "embed_tokens.weight": "model-00001-of-00002.safetensors",
@@ -52,102 +52,102 @@
     "layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.12.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.12.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
     "layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.13.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.13.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.13.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.13.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.14.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.14.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.14.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.15.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.15.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.15.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.16.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.16.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.16.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.17.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.17.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.17.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.18.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.18.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.18.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.19.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.19.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.19.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
@@ -160,30 +160,30 @@
     "layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896