Upload folder using huggingface_hub

checkpoint-1/config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 28672,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.55.0",
+  "use_cache": true,
+  "vocab_size": 32016
+}

checkpoint-1/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.55.0"
+}

checkpoint-1/model-00001-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fc914f0686202109415fe8acbd52592873800c6e3aa8c8f748464f13d0bb1f3
+size 4718922456

checkpoint-1/model-00002-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd8714a02fcab84f418162d065db13cccd737f314cd6264af5a6ece8702c1d37
+size 4664167352

checkpoint-1/model-00003-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42c6245a0d19a35d6be65a8326c52831448d074ed6a7fedf0262ef2e323e3f7a
+size 4999711672

checkpoint-1/model-00004-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bf41404c1a62ce2920b3575fb17e0e19febb2fe935a06c98e6366ed10226797
+size 4966157024

checkpoint-1/model-00005-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bff3903f9a1c61e19bcfc36b9fc5208c971fda55334a967ec82edb01f658411
+size 4664134384

checkpoint-1/model-00006-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbe52e66965bca75113dcc123cc58f5316da5c00e03cbff7bc436e08becffd9a
+size 4664167384

checkpoint-1/model-00007-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:006bfeaff222b529cac7d0e6a915b5a9848932f8c77f27d1473ed4bc8f8a35f4
+size 4664167376

checkpoint-1/model-00008-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7aa7d34245278b57326f11fb3366cba20f7d9b94e98e71a8cea0302f6587efd2
+size 4999711704

checkpoint-1/model-00009-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc1afc067015b19212ac1d73b99028c7c39baa763af38595fe0b3554f4ff6ff1
+size 4966157032

checkpoint-1/model-00010-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed320d184e72cce9838e1c4db01b4be0147aa4fd16bf91b7538171b23674d01c
+size 4664134384

checkpoint-1/model-00011-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7b2fb09972a6553c8e1967d6caa10f7b2b2217c7a916ca3e68ea8e79dcdaa0d
+size 4664167384

checkpoint-1/model-00012-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0778a3f85527b9cb3e228cf7591837e451f2bd262b0bc70b2664b6751c63e946
+size 4664167376

checkpoint-1/model-00013-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f24829683f7fbccfeb53f053349e19b7d8fb57eed155c8b713386d8b361646c7
+size 4999711704

checkpoint-1/model-00014-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0ab4b7eab285245caaca0b39abb636d33fb6e9d05f61b4cf2b0638bbae556cc
+size 4966157032

checkpoint-1/model-00015-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:642a005e25b3e7df84ac5fdc9e6d9ca1eaaa164c07d164d6ea87839efaec4273
+size 4664134384

checkpoint-1/model-00016-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4708d50cf062762f88e9411f245146528d63c0eaa8f9a5c13a1ff3985978db2a
+size 4664167384

checkpoint-1/model-00017-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f2c7e0488c5c13f8a612c5853388884b0da8e8777ce2a722953bb0c343fb031
+size 4664167376

checkpoint-1/model-00018-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:391419edfb8639479997da77bbcb29d52be7c8fa4d0cd454bb129e4e41a51c89
+size 4999711704

checkpoint-1/model-00019-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c540ad1ad3859989476660ca36e27f4f218c64fd79f284b8443e549208971ec
+size 4966157032

checkpoint-1/model-00020-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9b5ef3fcdef762e4cdf719e9bf7b96f43e62e2e93c5cc5c9c96a761814fbacb
+size 4664134384

checkpoint-1/model-00021-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dceac750e81d0767fb28409668739120ba790213fd09caede4319cdc1ba81f1
+size 4664167384

checkpoint-1/model-00022-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dd8bcc76452faeb4b236509fc99d1329b990c1bfc4898fbcb3356dbb1cba1b6
+size 4664167376

checkpoint-1/model-00023-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cad07c41268fb2bbc61df903ecdaff5eb1647d4195b71d4d99a377a3d872f37
+size 4999711704

checkpoint-1/model-00024-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d3bb1e96bce1b7c1b89c51fc9ba7a8ce57ad2edbd2fe0cae2d30b93f2d0d22e
+size 4966157032

checkpoint-1/model-00025-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6775f3c0015b01f8e91dcbc614cf078a91b4328f292e1acae6565ed3d2bc0bc
+size 4664134384

checkpoint-1/model-00026-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd432e358119b853a72fb923c64ac61f6ed4e8b4a322f90d9d29458ad1a5d43d
+size 4664167384

checkpoint-1/model-00027-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb7c71616906b667a611bc32bd4ad86a945d77f64dcaaf6bc83465a4464e0af5
+size 4664167376

checkpoint-1/model-00028-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55895c4b3500bfacf39547577a0149fc7b85f58a7a8f152438c3de9f619ff11b
+size 4999711704

checkpoint-1/model-00029-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f43ff137ef74924b6bdeb4bb700488702d4a61b8645b7b982ec343017726b2a2
+size 3779413912

checkpoint-1/model.safetensors.index.json

@@ -0,0 +1,731 @@
+{
+  "metadata": {
+    "total_parameters": 68976910336,
+    "total_size": 137953820672
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00029-of-00029.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00004-of-00029.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00029.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00005-of-00029.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00029.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00005-of-00029.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00029.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00007-of-00029.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00029.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00007-of-00029.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00029.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00007-of-00029.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00029.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00029.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00029.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00010-of-00029.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00029.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00010-of-00029.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00010-of-00029.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00029.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00029.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00013-of-00029.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00013-of-00029.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00013-of-00029.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00013-of-00029.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00013-of-00029.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00013-of-00029.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00015-of-00029.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00015-of-00029.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00029.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00029.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00015-of-00029.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00015-of-00029.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00016-of-00029.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00016-of-00029.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00016-of-00029.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00016-of-00029.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00016-of-00029.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00016-of-00029.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00019-of-00029.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00019-of-00029.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00019-of-00029.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00019-of-00029.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00019-of-00029.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00019-of-00029.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00020-of-00029.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00020-of-00029.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00020-of-00029.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00020-of-00029.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00022-of-00029.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00022-of-00029.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00022-of-00029.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00022-of-00029.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00022-of-00029.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00022-of-00029.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.64.input_layernorm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.64.mlp.down_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.64.mlp.gate_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.64.mlp.up_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.64.post_attention_layernorm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.64.self_attn.k_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.64.self_attn.o_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.64.self_attn.q_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.64.self_attn.v_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.65.input_layernorm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.65.mlp.down_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.65.mlp.gate_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.65.mlp.up_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.65.post_attention_layernorm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.65.self_attn.k_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.65.self_attn.o_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.65.self_attn.q_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.65.self_attn.v_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.66.input_layernorm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.66.mlp.down_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.66.mlp.gate_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.66.mlp.up_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.66.post_attention_layernorm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.66.self_attn.k_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.66.self_attn.o_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.66.self_attn.q_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.66.self_attn.v_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.67.input_layernorm.weight": "model-00025-of-00029.safetensors",
+    "model.layers.67.mlp.down_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.67.mlp.gate_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.67.mlp.up_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.67.post_attention_layernorm.weight": "model-00025-of-00029.safetensors",
+    "model.layers.67.self_attn.k_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.67.self_attn.o_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.67.self_attn.q_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.67.self_attn.v_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.68.input_layernorm.weight": "model-00025-of-00029.safetensors",
+    "model.layers.68.mlp.down_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.68.mlp.gate_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.68.mlp.up_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.68.post_attention_layernorm.weight": "model-00025-of-00029.safetensors",
+    "model.layers.68.self_attn.k_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.68.self_attn.o_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.68.self_attn.q_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.68.self_attn.v_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.69.input_layernorm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.69.mlp.down_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.69.mlp.gate_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.69.mlp.up_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.69.post_attention_layernorm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.69.self_attn.k_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.69.self_attn.o_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.69.self_attn.q_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.69.self_attn.v_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.70.input_layernorm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.70.mlp.down_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.70.mlp.gate_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.70.mlp.up_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.70.post_attention_layernorm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.70.self_attn.k_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.70.self_attn.o_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.70.self_attn.q_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.70.self_attn.v_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.71.input_layernorm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.71.mlp.down_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.71.mlp.gate_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.71.mlp.up_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.71.post_attention_layernorm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.71.self_attn.k_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.71.self_attn.o_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.71.self_attn.q_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.71.self_attn.v_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.72.input_layernorm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.72.mlp.down_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.72.mlp.gate_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.72.mlp.up_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.72.post_attention_layernorm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.72.self_attn.k_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.72.self_attn.o_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.72.self_attn.q_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.72.self_attn.v_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.73.input_layernorm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.73.mlp.down_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.73.mlp.gate_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.73.mlp.up_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.73.post_attention_layernorm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.73.self_attn.k_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.73.self_attn.o_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.73.self_attn.q_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.73.self_attn.v_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.74.input_layernorm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.74.mlp.down_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.74.mlp.gate_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.74.mlp.up_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.74.post_attention_layernorm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.74.self_attn.k_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.74.self_attn.o_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.74.self_attn.q_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.74.self_attn.v_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.75.input_layernorm.weight": "model-00028-of-00029.safetensors",
+    "model.layers.75.mlp.down_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.75.mlp.gate_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.75.mlp.up_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.75.post_attention_layernorm.weight": "model-00028-of-00029.safetensors",
+    "model.layers.75.self_attn.k_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.75.self_attn.o_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.75.self_attn.q_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.75.self_attn.v_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.76.input_layernorm.weight": "model-00028-of-00029.safetensors",
+    "model.layers.76.mlp.down_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.76.mlp.gate_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.76.mlp.up_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.76.post_attention_layernorm.weight": "model-00028-of-00029.safetensors",
+    "model.layers.76.self_attn.k_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.76.self_attn.o_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.76.self_attn.q_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.76.self_attn.v_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.77.input_layernorm.weight": "model-00028-of-00029.safetensors",
+    "model.layers.77.mlp.down_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.77.mlp.gate_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.77.mlp.up_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.77.post_attention_layernorm.weight": "model-00028-of-00029.safetensors",
+    "model.layers.77.self_attn.k_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.77.self_attn.o_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.77.self_attn.q_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.77.self_attn.v_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.78.input_layernorm.weight": "model-00029-of-00029.safetensors",
+    "model.layers.78.mlp.down_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.78.mlp.gate_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.78.mlp.up_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.78.post_attention_layernorm.weight": "model-00029-of-00029.safetensors",
+    "model.layers.78.self_attn.k_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.78.self_attn.o_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.78.self_attn.q_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.78.self_attn.v_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.79.input_layernorm.weight": "model-00029-of-00029.safetensors",
+    "model.layers.79.mlp.down_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.79.mlp.gate_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.79.mlp.up_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.79.post_attention_layernorm.weight": "model-00029-of-00029.safetensors",
+    "model.layers.79.self_attn.k_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.79.self_attn.o_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.79.self_attn.q_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.79.self_attn.v_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00004-of-00029.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00029.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00004-of-00029.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00029.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00029.safetensors",
+    "model.norm.weight": "model-00029-of-00029.safetensors"
+  }
+}

checkpoint-1/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3f28cf15889c0bc501b6613bd6affeb7c8fbb38fd5fcd3caa51dd859df4e251
+size 141675740968

checkpoint-1/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d9cd6a0487226e5bd30d1846894c82af483733ab4381b75bae9c0745e05d405
+size 14244

checkpoint-1/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6da16eefab22daee3fb0999c7651be192feb36b73810bf419e9165c7023ec02
+size 1064

checkpoint-1/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-1/trainer_state.json

@@ -0,0 +1,41 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 790.0,
+      "learning_rate": 0.001,
+      "loss": 6.6451,
+      "step": 1
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 13193209970688.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f685a8c0edb4d54f7e24efcf0fb1dcccc8d23fbbd03c51615d13bc030ba7a28e
+size 5304

config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 28672,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.55.0",
+  "use_cache": true,
+  "vocab_size": 32016
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.55.0"
+}

model-00001-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fc914f0686202109415fe8acbd52592873800c6e3aa8c8f748464f13d0bb1f3
+size 4718922456

model-00002-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd8714a02fcab84f418162d065db13cccd737f314cd6264af5a6ece8702c1d37
+size 4664167352

model-00003-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42c6245a0d19a35d6be65a8326c52831448d074ed6a7fedf0262ef2e323e3f7a
+size 4999711672

model-00004-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bf41404c1a62ce2920b3575fb17e0e19febb2fe935a06c98e6366ed10226797
+size 4966157024

model-00005-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bff3903f9a1c61e19bcfc36b9fc5208c971fda55334a967ec82edb01f658411
+size 4664134384

model-00006-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbe52e66965bca75113dcc123cc58f5316da5c00e03cbff7bc436e08becffd9a
+size 4664167384

model-00007-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:006bfeaff222b529cac7d0e6a915b5a9848932f8c77f27d1473ed4bc8f8a35f4
+size 4664167376

model-00008-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7aa7d34245278b57326f11fb3366cba20f7d9b94e98e71a8cea0302f6587efd2
+size 4999711704