Add ckpt with 76800 steps

config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "intermediate_size": 20480,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 56,
+  "num_hidden_layers": 60,
+  "num_key_value_heads": 8,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.33.1",
+  "use_cache": true,
+  "vocab_size": 78464
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 2,
+  "transformers_version": "4.33.1"
+}

model-00001-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1945c1b426f49203d814d9c5ee9c42483066dd1d884988eee846dcb76d74442a
+size 2769057512

model-00002-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e27bc00577fc17b868f17471a31c207a67d26b49620975b435f5ca3099bada48
+size 2950781792

model-00003-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13b1f6827fee0f1b8184d1de1ef579b92c1dbc852f6d6f5f48c665eee7c544c9
+size 2921392520

model-00004-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05c419155c1b520ee63360cfe5568ce7ca4ce1b2c7680a26bd3b3758ef7ca5d9
+size 2759940960

model-00005-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb6246908ae797a6b9a7b7d21633d55a9501cabf0c09088289ae6c61c1b202eb
+size 2818631968

model-00006-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b407de4d9dee95574fcf24082d8c7ecae75210c1280a84757352820d317a87ef
+size 2759940984

model-00007-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3be1faec7730ba23ccfff43f4878578f5a45510ada2b6854c144fe973055b95d
+size 2818631976

model-00008-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d80f311eb946e7e4b5ce5d03b9a0358ec21fa9e8470f192588a15b44e01117e
+size 2759940984

model-00009-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70e214943ed9e2274df4a5c0388f51674986f0077aa2838da2f8fe596290bc16
+size 2818631976

model-00010-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:808ec7a58de8c116d1db141de1231e1e2bbed8baf9860122000ba8430e1b2c82
+size 2759940984

model-00011-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d163d17ec72da8edfd68603cdb43e7bd63ded9101ab8d08334b18a2ef3061a91
+size 2818631976

model-00012-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:925156fb45b9a7db976d8064abcc6f31db24f71db91dd9e646733e12960fb1b5
+size 2759940984

model-00013-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da1d189a6eecfa651c51668f0d6736c8b43f425b7601e1076f18796c6c68089b
+size 2818631976

model-00014-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc88c5c72e98c59d98344bd869b15badd2eec20c2ee431f91faff6168b367cfa
+size 2759940984

model-00015-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fec055fbe8e4f9867be1679c363f2be1295bd76a2ada5bcec679003d73e0d801
+size 2818631976

model-00016-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9914f703ef10680bf3c0d024f91a43a8031a473cb96be234adedfe9f5c03dbd
+size 2759940984

model-00017-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57716cd2cd59c768deb68bf37883c398bb81c2be1b3a4c49233346279e6bfb54
+size 2818631976

model-00018-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44547d91ba51c4f36693ccc09f14dacdc494f71b449819a09feb46e98b86b045
+size 2759940984

model-00019-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93f65ad7014514ab2ff6270aa7f3974c4b0bd6c89412e669c3258b85689ddae5
+size 2818631976

model-00020-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:053e05d50e671859fd6401fead129e0e81715e6cb41fecd7109ac40cbbdadf47
+size 2759940984

model-00021-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2aaf9fd58edf4be649b7fc72e6f4b067307993aa58bc4178170cae568df101de
+size 2818631976

model-00022-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20d18d7224977580cedcf7270e7d291e1cf3c76c2597a647196e692c15126dfd
+size 2759940984

model-00023-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7c5df1e65e2570274d572c7426315461efa30026eb0c07e87db0e1422c454c4
+size 2818631976

model-00024-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:053ae68d59a6b8ae4efca9f5629456c2e9e09e241c4042549ecf1f05b02cd01d
+size 2759940984

model-00025-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9082862881fb0382e5ba3115794e6f749aa557a79ffb63405d6f42e5facc6427
+size 2005707552

model.safetensors.index.json

@@ -0,0 +1,550 @@
+{
+  "metadata": {
+    "total_size": 69192546304
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00025-of-00025.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00025.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00025.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00025.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00025.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00025.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00025.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00025.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00025.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00025.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00025.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00025.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00025.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00025.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00025.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00025.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00025.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00025.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00025.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00025.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00005-of-00025.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00025.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00006-of-00025.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00025.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00006-of-00025.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00025.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00006-of-00025.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00025.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00007-of-00025.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00025.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00007-of-00025.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00025.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00008-of-00025.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00025.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00008-of-00025.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00025.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00008-of-00025.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00025.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00009-of-00025.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00025.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00025.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00025.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00025.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00025.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00025.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00025.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00025.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00025.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00025.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00009-of-00025.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00009-of-00025.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00010-of-00025.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00010-of-00025.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00010-of-00025.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00010-of-00025.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00010-of-00025.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00010-of-00025.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00011-of-00025.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00011-of-00025.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00011-of-00025.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00011-of-00025.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00012-of-00025.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00012-of-00025.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00012-of-00025.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00012-of-00025.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00012-of-00025.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00012-of-00025.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00013-of-00025.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00013-of-00025.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00025.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00025.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00025.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00025.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00025.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00025.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00025.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00025.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00025.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00013-of-00025.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00013-of-00025.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00014-of-00025.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00014-of-00025.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00014-of-00025.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00014-of-00025.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00014-of-00025.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00014-of-00025.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00015-of-00025.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00015-of-00025.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00015-of-00025.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00015-of-00025.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00016-of-00025.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00016-of-00025.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00016-of-00025.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00016-of-00025.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00016-of-00025.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00016-of-00025.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00017-of-00025.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00017-of-00025.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00003-of-00025.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00025.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00025.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00025.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00025.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00017-of-00025.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00017-of-00025.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00018-of-00025.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00018-of-00025.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00018-of-00025.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00018-of-00025.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00018-of-00025.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00018-of-00025.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00019-of-00025.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00019-of-00025.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00019-of-00025.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00019-of-00025.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00020-of-00025.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00020-of-00025.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00020-of-00025.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00020-of-00025.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00020-of-00025.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00020-of-00025.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00021-of-00025.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00021-of-00025.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00025.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00025.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00021-of-00025.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00021-of-00025.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00022-of-00025.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00022-of-00025.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00022-of-00025.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00022-of-00025.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00022-of-00025.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00022-of-00025.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00023-of-00025.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00023-of-00025.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00023-of-00025.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00023-of-00025.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00024-of-00025.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00024-of-00025.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00024-of-00025.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00024-of-00025.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00024-of-00025.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00024-of-00025.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00025-of-00025.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00025-of-00025.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00025-of-00025.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00025-of-00025.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00025-of-00025.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00004-of-00025.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00025.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00004-of-00025.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00025.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00004-of-00025.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00025.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00005-of-00025.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00025.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00025.safetensors",
+    "model.norm.weight": "model-00025-of-00025.safetensors"
+  }
+}