Added bf16 tensors

config.json

@@ -25,7 +25,7 @@
   "rope_scaling": null,
   "rope_theta": 10000000.0,
   "tie_word_embeddings": true,
-  "torch_dtype": "float32",
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.47.0",
   "use_cache": true,
   "vocab_size": 49155

model-00001-of-00007.safetensors → model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60d7a3196719d9b0af5920837c7c2ce7e253ccbfab90a7ddcb5eeb04723d6954
-size 4957886080
+oid sha256:191c4e9c6263d9cf591104f2d16ab2c39dcc43c1ad0680cc5a34d5c86d61ee41
+size 4974661520

model-00002-of-00007.safetensors → model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06baa3e2287f93319be9e047e068ec630819036b53074595285842d66a2c3f31
-size 4991424704
+oid sha256:c7c38b0d5a436775b09d764465ed6e6eb7a8c4e302d05e301e151c96e3076f22
+size 4991447808

model-00003-of-00007.safetensors → model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3a7772488565ef83a6c93f36aceb3388c1f357614ec970df31c12df0e1452ab
-size 4991424744
+oid sha256:f02784b72391fa04e9b986313c1a1720ce88f0eb40f7ae81fa0daadc93049457
+size 4970460032

model-00004-of-00007.safetensors → model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd133fa5fc76dbd525312dec707bd38023ef9fa8d24e81fce12635877461319f
-size 4991457736
+oid sha256:9d86d201ff8e73d8a46e92b543c9dd44f133e60b35ccada4a76439af62f22212
+size 1405169256

model-00005-of-00007.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c1d0bf59a059ea4dc5a15881d6853ebac49ad63ca08f5423ee2f7c37ed220621
-size 4949482056

model-00006-of-00007.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:de92273dcab3be21fa7b6c4de268b0b2b673abba0cdcdb8b72da8c809ddee5f4
-size 4991424744

model-00007-of-00007.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:880ed6e2243a857add482997c4e8a3b1f4d1404a870c25af80ce99739e5c48cf
-size 2810334824

model.safetensors.index.json

@@ -1,369 +1,369 @@
 {
   "metadata": {
-    "total_size": 32683393024
+    "total_size": 16341696512
   },
   "weight_map": {
-    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.28.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.29.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.29.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.31.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.32.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.32.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.32.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.33.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.33.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.33.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.33.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.34.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.34.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.34.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.34.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.34.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.34.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.34.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.34.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.35.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.35.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.35.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.35.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.35.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.35.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.35.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.36.input_layernorm.weight": "model-00007-of-00007.safetensors",
-    "model.layers.36.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.36.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.36.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.36.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
-    "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.37.input_layernorm.weight": "model-00007-of-00007.safetensors",
-    "model.layers.37.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.37.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.37.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
-    "model.layers.37.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.37.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.37.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.37.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.38.input_layernorm.weight": "model-00007-of-00007.safetensors",
-    "model.layers.38.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.38.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.38.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.38.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
-    "model.layers.38.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.38.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.38.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.38.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.39.input_layernorm.weight": "model-00007-of-00007.safetensors",
-    "model.layers.39.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.39.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.39.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.39.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
-    "model.layers.39.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.39.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.39.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.39.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "model.norm.weight": "model-00007-of-00007.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",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "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.mlp.gate_proj.weight": "model-00002-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.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-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-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-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",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "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-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.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",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
   }
 }