Pushed model to hub

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "model_deepseek_33b_racket/checkpoint-410",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 32013,
+  "eos_token_id": 32014,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "intermediate_size": 19200,
+  "max_position_embeddings": 16384,
+  "model_type": "llama",
+  "num_attention_heads": 56,
+  "num_hidden_layers": 62,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "factor": 4.0,
+    "type": "linear"
+  },
+  "rope_theta": 100000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.2",
+  "use_cache": false,
+  "vocab_size": 32256
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 32013,
+  "eos_token_id": 32014,
+  "transformers_version": "4.39.2"
+}

model-00001-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1776c97493fbfc002b1f975ed8df515b84ca3e9df612892c5886df27a477d3e2
+size 4616939328

model-00002-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f80c79ee5f5bf817b7abd734391e97f26bea0c98e05488a29c26c1d47d0619b9
+size 4998736368

model-00003-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ed463590266b0699b3c57316680d023459fc0cec2f234c99cce2242a7490359
+size 4506896776

model-00004-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b52941379ec036ac98291bc4d3874dccd548f09b8befaeae797e501420470d60
+size 4793157784

model-00005-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dba3b109ff69910c31038c73786687710bfd8990d6c1eb41f3748fa33a920a55
+size 4793157800

model-00006-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:481e4b650a9b3982c0611f10c034f9798ca1954621ef526170e751e8d3a7c298
+size 4998736392

model-00007-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54bdaca4750e6be9873e9b5ce27bb84c898bd636b4cfc2afc85fca27663f42eb
+size 4506896792

model-00008-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c982d409b136ab7de68e89f261bcf6862bffe067eeb66c68905f287f5a2e2c6
+size 4793157808

model-00009-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:442473c897affaeb8d11656e048466ce849fb59535ed8a2bfed320d063bfff98
+size 4793157800

model-00010-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5847a793bc2ebab05ba6a43137590fdb0a06dbde874cc9f8d4078592673b481a
+size 4998736392

model-00011-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccedd680db4f4c5c538c655bffcc17bbbe69d45dd794f76d1aa400433bd0148a
+size 4506896792

model-00012-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eaecb62778a992760c874690954df2bf3cb7efdcf0a5cfee68daf286631ad0b
+size 4793157808

model-00013-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db85600c1015fcb10058fd27a35e6adb00c30f72056d08472d3fb1f703cada58
+size 4793157800

model-00014-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0f07a987305f6363f33838a86e8d88e73bb194c7b95e9a9deb6ddc8d8dfdce3
+size 4998736392

model-00015-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c203bd872f8efd9511c3c239aa2eb4963261fbf6f897e0edcd65bd1c5c0e23d
+size 4506896792

model-00016-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3ff245f4013ce2e0bb96eda5a156b660967c68296bd83b2f081dd3ec06a297e
+size 4793157808

model-00017-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:047eed51838d623a2f2b1ca23e711d699aef241d09844943a2a2b1a1bc4a77f0
+size 4793157800

model-00018-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a0e1494f2c8d78037afbb8bd482d5de9b1520c1fce9ad8f9b440418082d81ca
+size 4998736392

model-00019-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc5fbaeee81af0a993ee2af34915e0313a1b35c4c2227d0b6ac11874f7d0b98d
+size 4506896792

model-00020-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7928f063162e40712ca5e9d54cde7bdcb22e26609afeebddc03ab9ad128eb956
+size 4793157808

model-00021-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d85590783af05420e6cd2793a173586bc542b530dfdf6051807657c823d2a9bc
+size 4793157800

model-00022-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4a8355bdd7c6cd44be527d9eb33aa7fe1783657e763b436536e7252de086353
+size 4998736392

model-00023-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14b097295cd5c8e2608db1e500e03a9d8d071f3dd9bef79b8d059bbf152de4ad
+size 4506896792

model-00024-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db333ce14fb36c92e67ce91271c17de6fb0997d175e9589776d3f9680efe6297
+size 4793157808

model-00025-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15559fd16a0dbcff05105baf3997db7eaa665796fda96f27ed4c6b8c8fadb5d0
+size 4793157800

model-00026-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:761f88198d302becb5d9f8ab4e4d1ceb6a4b8d64e71229720b8efc7f7b306019
+size 4998736392

model-00027-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:beecbc0e595c12477fe52724e03aa3fd1fb766fd5c82048b569ba4cc01263422
+size 4506896792

model-00028-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edf7e277572573c88357fe591f810029b4b170ea381bdbe3b1dc1a7389642140
+size 4697765672

model.safetensors.index.json

@@ -0,0 +1,568 @@
+{
+  "metadata": {
+    "total_size": 133371965440
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00028-of-00028.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00028.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00028.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00028.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00028.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00028.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00006-of-00028.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00028.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00006-of-00028.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00028.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00006-of-00028.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00028.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00007-of-00028.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00028.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00007-of-00028.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00028.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00008-of-00028.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00028.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00008-of-00028.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00028.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00009-of-00028.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00028.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00009-of-00028.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00028.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00010-of-00028.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00010-of-00028.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00028.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00028.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00010-of-00028.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00010-of-00028.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00010-of-00028.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00010-of-00028.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00011-of-00028.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00011-of-00028.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00011-of-00028.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00011-of-00028.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00012-of-00028.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00012-of-00028.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00012-of-00028.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00012-of-00028.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00013-of-00028.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00013-of-00028.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00013-of-00028.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00013-of-00028.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00014-of-00028.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00014-of-00028.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00014-of-00028.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00014-of-00028.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00028.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00028.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00014-of-00028.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00014-of-00028.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00015-of-00028.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00015-of-00028.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00015-of-00028.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00015-of-00028.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00016-of-00028.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00016-of-00028.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00016-of-00028.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00016-of-00028.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00017-of-00028.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00017-of-00028.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00017-of-00028.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00017-of-00028.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00018-of-00028.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00018-of-00028.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00018-of-00028.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00018-of-00028.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00018-of-00028.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00018-of-00028.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00003-of-00028.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00028.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00019-of-00028.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00019-of-00028.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00019-of-00028.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00019-of-00028.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00020-of-00028.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00020-of-00028.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00020-of-00028.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00020-of-00028.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00021-of-00028.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00021-of-00028.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00021-of-00028.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00021-of-00028.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00022-of-00028.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00022-of-00028.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00022-of-00028.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00022-of-00028.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00022-of-00028.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00022-of-00028.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00023-of-00028.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00023-of-00028.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00028.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00028.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00023-of-00028.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00023-of-00028.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00024-of-00028.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00024-of-00028.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00024-of-00028.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00024-of-00028.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00025-of-00028.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00025-of-00028.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00025-of-00028.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00025-of-00028.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00026-of-00028.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00026-of-00028.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00026-of-00028.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00026-of-00028.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00026-of-00028.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00026-of-00028.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00027-of-00028.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00027-of-00028.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00027-of-00028.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00027-of-00028.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00004-of-00028.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00028.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00028-of-00028.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00028-of-00028.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00028-of-00028.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00028-of-00028.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00028-of-00028.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00028-of-00028.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00028-of-00028.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00028-of-00028.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00028-of-00028.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00028-of-00028.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00028-of-00028.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00028-of-00028.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00028-of-00028.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00028-of-00028.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00004-of-00028.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00028.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00005-of-00028.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00028.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00005-of-00028.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00028.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00028.safetensors",
+    "model.norm.weight": "model-00028-of-00028.safetensors"
+  }
+}