Upload LlamaForCausalLM

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "ds33b_self_align_codeqwen",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 32013,
+  "eos_token_id": 32014,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "intermediate_size": 19200,
+  "max_position_embeddings": 16384,
+  "model_type": "llama",
+  "num_attention_heads": 56,
+  "num_hidden_layers": 62,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "factor": 4.0,
+    "type": "linear"
+  },
+  "rope_theta": 100000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "use_cache": true,
+  "vocab_size": 32256
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 32013,
+  "eos_token_id": 32014,
+  "transformers_version": "4.40.1"
+}

model-00001-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:859b42bbe08cae8ab3c8b3eaddf4d53f72d675337fe79133296f03c4f046e560
+size 4616939328

model-00002-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c92a3e7015d86b385e04f400b836c57d4a6a18e5bc0dd3999dc29dbcd645bf9
+size 4998736368

model-00003-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3260e708fcf379bc8a03f794e0644d8c3cbc82ad09995352c70ecb31e95cb49
+size 4506896776

model-00004-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:658f6a4d081b4b4dcb982adc29bd14f012fb08e2f1bb15fa99357705884769ab
+size 4793157784

model-00005-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abed143060ef268886d254b6f13508a2c071ee9fc31bf80a243e9749ca582319
+size 4793157800

model-00006-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7f6c24e520cc88df92c1ad274f694087b71264a090226d966292702cf83b980
+size 4998736392

model-00007-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ce1ff03bcda844be410a3de062c8609533de13b7c90970cee87286fb57518a5
+size 4506896792

model-00008-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c315be0dcd0dff239d801928905859982998b155a6e0bf172cd199e3db901117
+size 4793157808

model-00009-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed3c87f7cc84873aa0d46fd0854e123996277f5a532dffb83d8cc5652428df76
+size 4793157800

model-00010-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50283156e5459768627731b074c45a47b27287746c21226f393f4d946e804f0d
+size 4998736392

model-00011-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81ae8a58c9f0c23104e256907abf749ff05a75da8d0ff04fcd55cb318f2945d4
+size 4506896792

model-00012-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98be82c6ed08dee6acfb8aaa8fee3f26e2aa8a6761eabd9931030598387fa90f
+size 4793157808

model-00013-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f686a601fc298b840b7829a3729347b71c44c8c1ecfe85fcf1e545402f69649
+size 4793157800

model-00014-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dc125062dc631c30e799c7a90e60e7ac71df3f9ba87b9843eafece731ffa1e0
+size 4998736392

model-00015-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4812103fd1d6eae0d334600314ab72e1a5dda8055e069d40fc585da4c17c37a
+size 4506896792

model-00016-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61b86e593bda8724bf3523043edab15700ffc5e5c5c32176cfd0e166fd341987
+size 4793157808

model-00017-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa7bcf9acf3b05976075254ea98828ca05c61c9dd787ac1562aadc8617e84c86
+size 4793157800

model-00018-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7333a0e9025054055b7c5c41bec15371a12007e04b3e72d61ccae029a2bbf3a3
+size 4998736392

model-00019-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ffce0e4ec1a45a7fc0ae35b9ee340d5e3c80ffe3462a8eeb572605a296f1bd9
+size 4506896792

model-00020-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87f0384d280d4fecc6dde6ab1cb251ffcc5d6c9c682e06764e12c27b198b91d4
+size 4793157808

model-00021-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e1d1e02901f08c08dad4c80719346a59de4d6a7bae7c8d5a40bcac450486b07
+size 4793157800

model-00022-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca4a66cbe2475d7302a4249767ddd84740f905d66612ce3f221f7bead598f2f9
+size 4998736392

model-00023-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be25c726a41b3a4e3ba724924ce32f1fdcead0451dce45237eb9c14450171d68
+size 4506896792

model-00024-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd97cee1d399d660530fe98ba13654e8a6a19617ca4e799d91c53bc020ecba4d
+size 4793157808

model-00025-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acf3f2b87c457525daa48260f0689926aee0d496da8b422a18ed6b07ce565a2a
+size 4793157800

model-00026-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8e8493a6da28615604dba1c440365eeba7b9127fc587f89365997cf56c65852
+size 4998736392

model-00027-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49e3adf3dcad5ed2a9a5d80406d7489f93337b5b8d3129aeeb59590285afb17e
+size 4506896792

model-00028-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0918d23095a9a7905aa49c6eaa50e5ebd4d67ab1c25e254a5cdc6b08d5598b18
+size 4697765672

model.safetensors.index.json

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