model weights init

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1e3c63517c0b6bf1260100c3ea05277ef52b66a8d10ebc6afa50419d27e2e05
+size 4932667368

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c987704ed6fe458ddffdb1cf00a23319a0c059571f9b6f124c908497d49a4f6
+size 4915961640

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfd156bc10bac4a38beeb2c559ac4f420d7ee85ae772a29acbac32479a5ab7fc
+size 4983069760

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a591fd0e24a6476a800f2ab1a1cb7b503a0b1e91e322bb81e7b282e7ab13be8e
+size 2148040304

model.safetensors.index.json

@@ -0,0 +1,471 @@
+{
+  "metadata": {
+    "total_parameters": 8489841664,
+    "total_size": 16979683328
+  },
+  "weight_map": {
+    "emb_ext.0.weight": "model-00004-of-00004.safetensors",
+    "emb_ext.1.weight": "model-00004-of-00004.safetensors",
+    "emb_ext.10.weight": "model-00004-of-00004.safetensors",
+    "emb_ext.11.weight": "model-00004-of-00004.safetensors",
+    "emb_ext.12.weight": "model-00004-of-00004.safetensors",
+    "emb_ext.13.weight": "model-00004-of-00004.safetensors",
+    "emb_ext.14.weight": "model-00004-of-00004.safetensors",
+    "emb_ext.15.weight": "model-00004-of-00004.safetensors",
+    "emb_ext.16.weight": "model-00004-of-00004.safetensors",
+    "emb_ext.17.weight": "model-00004-of-00004.safetensors",
+    "emb_ext.18.weight": "model-00004-of-00004.safetensors",
+    "emb_ext.19.weight": "model-00004-of-00004.safetensors",
+    "emb_ext.2.weight": "model-00004-of-00004.safetensors",
+    "emb_ext.20.weight": "model-00004-of-00004.safetensors",
+    "emb_ext.21.weight": "model-00004-of-00004.safetensors",
+    "emb_ext.22.weight": "model-00004-of-00004.safetensors",
+    "emb_ext.23.weight": "model-00004-of-00004.safetensors",
+    "emb_ext.24.weight": "model-00004-of-00004.safetensors",
+    "emb_ext.25.weight": "model-00004-of-00004.safetensors",
+    "emb_ext.26.weight": "model-00004-of-00004.safetensors",
+    "emb_ext.27.weight": "model-00004-of-00004.safetensors",
+    "emb_ext.28.weight": "model-00004-of-00004.safetensors",
+    "emb_ext.29.weight": "model-00004-of-00004.safetensors",
+    "emb_ext.3.weight": "model-00004-of-00004.safetensors",
+    "emb_ext.30.weight": "model-00004-of-00004.safetensors",
+    "emb_ext.31.weight": "model-00004-of-00004.safetensors",
+    "emb_ext.4.weight": "model-00004-of-00004.safetensors",
+    "emb_ext.5.weight": "model-00004-of-00004.safetensors",
+    "emb_ext.6.weight": "model-00004-of-00004.safetensors",
+    "emb_ext.7.weight": "model-00004-of-00004.safetensors",
+    "emb_ext.8.weight": "model-00004-of-00004.safetensors",
+    "emb_ext.9.weight": "model-00004-of-00004.safetensors",
+    "language_model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "language_model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "language_model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "language_model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.norm.weight": "model-00004-of-00004.safetensors",
+    "lm_heads.0.weight": "model-00004-of-00004.safetensors",
+    "lm_heads.1.weight": "model-00004-of-00004.safetensors",
+    "lm_heads.10.weight": "model-00004-of-00004.safetensors",
+    "lm_heads.11.weight": "model-00004-of-00004.safetensors",
+    "lm_heads.12.weight": "model-00004-of-00004.safetensors",
+    "lm_heads.13.weight": "model-00004-of-00004.safetensors",
+    "lm_heads.14.weight": "model-00004-of-00004.safetensors",
+    "lm_heads.15.weight": "model-00004-of-00004.safetensors",
+    "lm_heads.16.weight": "model-00004-of-00004.safetensors",
+    "lm_heads.17.weight": "model-00004-of-00004.safetensors",
+    "lm_heads.18.weight": "model-00004-of-00004.safetensors",
+    "lm_heads.19.weight": "model-00004-of-00004.safetensors",
+    "lm_heads.2.weight": "model-00004-of-00004.safetensors",
+    "lm_heads.20.weight": "model-00004-of-00004.safetensors",
+    "lm_heads.21.weight": "model-00004-of-00004.safetensors",
+    "lm_heads.22.weight": "model-00004-of-00004.safetensors",
+    "lm_heads.23.weight": "model-00004-of-00004.safetensors",
+    "lm_heads.24.weight": "model-00004-of-00004.safetensors",
+    "lm_heads.25.weight": "model-00004-of-00004.safetensors",
+    "lm_heads.26.weight": "model-00004-of-00004.safetensors",
+    "lm_heads.27.weight": "model-00004-of-00004.safetensors",
+    "lm_heads.28.weight": "model-00004-of-00004.safetensors",
+    "lm_heads.29.weight": "model-00004-of-00004.safetensors",
+    "lm_heads.3.weight": "model-00004-of-00004.safetensors",
+    "lm_heads.30.weight": "model-00004-of-00004.safetensors",
+    "lm_heads.31.weight": "model-00004-of-00004.safetensors",
+    "lm_heads.32.weight": "model-00004-of-00004.safetensors",
+    "lm_heads.4.weight": "model-00004-of-00004.safetensors",
+    "lm_heads.5.weight": "model-00004-of-00004.safetensors",
+    "lm_heads.6.weight": "model-00004-of-00004.safetensors",
+    "lm_heads.7.weight": "model-00004-of-00004.safetensors",
+    "lm_heads.8.weight": "model-00004-of-00004.safetensors",
+    "lm_heads.9.weight": "model-00004-of-00004.safetensors"
+  }
+}