Upload OrionForCausalLM

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "./custom_LLM_log_char",
+  "architectures": [
+    "OrionForCausalLM"
+  ],
+  "attention_bias": false,
+  "auto_map": {
+    "AutoConfig": "configuration_orion.OrionConfig",
+    "AutoModelForCausalLM": "OrionStarAI/Orion-14B-Base--modeling_orion.OrionForCausalLM"
+  },
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 15360,
+  "max_position_embeddings": 4096,
+  "max_sequence_length": 4096,
+  "model_type": "orion",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.1",
+  "use_cache": true,
+  "vocab_size": 84608
+}

configuration_orion.py

@@ -0,0 +1,82 @@
+# Copyright (c) 2024, OrionStar Inc. All rights reserved.
+
+from transformers import PretrainedConfig
+
+class OrionConfig(PretrainedConfig):
+    model_type = "orion"
+    keys_to_ignore_at_inference = ["past_key_values"]
+
+    def __init__(
+        self,
+        vocab_size=84608,
+        hidden_size=4096,
+        intermediate_size=15360,
+        num_hidden_layers=40,
+        num_attention_heads=40,
+        num_key_value_heads=40,
+        hidden_act="silu",
+        max_position_embeddings=4096,
+        initializer_range=0.02,
+        rms_norm_eps=1e-5,
+        use_cache=True,
+        pad_token_id=None,
+        bos_token_id=1,
+        eos_token_id=2,
+        pretraining_tp=1,
+        tie_word_embeddings=False,
+        rope_theta=10000.0,
+        rope_scaling=None,
+        attention_bias=False,
+        **kwargs,
+    ):
+        self.vocab_size = vocab_size
+        self.max_position_embeddings = max_position_embeddings
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+
+        # for backward compatibility
+        if num_key_value_heads is None:
+            num_key_value_heads = num_attention_heads
+
+        self.num_key_value_heads = num_key_value_heads
+        self.hidden_act = hidden_act
+        self.initializer_range = initializer_range
+        self.rms_norm_eps = rms_norm_eps
+        self.pretraining_tp = pretraining_tp
+        self.use_cache = use_cache
+        self.rope_theta = rope_theta
+        self.rope_scaling = rope_scaling
+        self._rope_scaling_validation()
+        self.attention_bias = attention_bias
+
+        super().__init__(
+            pad_token_id=pad_token_id,
+            bos_token_id=bos_token_id,
+            eos_token_id=eos_token_id,
+            tie_word_embeddings=tie_word_embeddings,
+            **kwargs,
+        )
+
+    def _rope_scaling_validation(self):
+        """
+        Validate the `rope_scaling` configuration.
+        """
+        if self.rope_scaling is None:
+            return
+
+        if not isinstance(self.rope_scaling, dict) or len(self.rope_scaling) != 2:
+            raise ValueError(
+                "`rope_scaling` must be a dictionary with with two fields, `type` and `factor`, "
+                f"got {self.rope_scaling}"
+            )
+        rope_scaling_type = self.rope_scaling.get("type", None)
+        rope_scaling_factor = self.rope_scaling.get("factor", None)
+        if rope_scaling_type is None or rope_scaling_type not in ["linear", "dynamic"]:
+            raise ValueError(
+                f"`rope_scaling`'s type field must be one of ['linear', 'dynamic'], got {rope_scaling_type}"
+            )
+        if rope_scaling_factor is None or not isinstance(rope_scaling_factor, float) or rope_scaling_factor <= 1.0:
+            raise ValueError(f"`rope_scaling`'s factor field must be an float > 1, got {rope_scaling_factor}")
+

generation_config.json

@@ -2,6 +2,6 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "pad_token_id": 2,
+  "pad_token_id": 0,
   "transformers_version": "4.37.1"
 }

model-00001-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b466bc3d79da5c369fb734a10eaf1a90879126d6423016833e44370da1fa1b0
+size 4878666800

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a978db83cfe9f7d1b1519977d77bbf2054112e4633cfe831e0f509dc84d500dc
+size 4718841760

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cae94f7cda1c91642fa7c4bccf93a27f204c818ff78214f6da24a607ea93eb52
+size 4823782088

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6277730aacdbb90695bcccaf6f879d305f4e74b95c36a3ed0f9efe79210b0f5
+size 4718841792

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:821f222aabe5f2da8b45f7a1500547f420830a87df99d47de46ad3ddbedb9e9a
+size 4823782128

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:440e99d9ce9c015247a7d65765836670dda80174d1d29291e54e25c62422ce0e
+size 4718841792

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e22f21b821d081842f367d237bc50dca35593528b6790f622d7ed56118ccfcb9
+size 4823782128

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d9aefa0ed4bbb04245d53e0a4327eb153d3dabfc343c4ee73567a3fc44bbc38
+size 4718841792

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64ce8c4c8024303942fa62df25522e0625255849eb6218957da943ecf4f5fd6d
+size 4823782128

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5500f1a153dce3b8a29cb0d5a6574e394c941ff59a6512d17c843ddd3bf943b
+size 4718841792

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f328115bfe7d37a09ae9c227eb23c3e16ae8e47a909b92f969d5be6101c65d2
+size 4823782128

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6edd0cab2b25bc4c63ca2508c5de0a4a6655cadb7103e4e852eae3b2c1daac95
+size 3670306240

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62cac05daca3d997d2f7a8699783005e587a4697c3eac6dd3515ed8c73b3d677
+size 1732771968

model.safetensors.index.json

@@ -0,0 +1,451 @@
+{
+  "metadata": {
+    "total_size": 57994813440
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00013-of-00013.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.input_layernorm.bias": "model-00001-of-00013.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.post_attention_layernorm.bias": "model-00001-of-00013.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.input_layernorm.bias": "model-00001-of-00013.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.post_attention_layernorm.bias": "model-00001-of-00013.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.10.input_layernorm.bias": "model-00004-of-00013.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.10.post_attention_layernorm.bias": "model-00004-of-00013.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.11.input_layernorm.bias": "model-00004-of-00013.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.11.post_attention_layernorm.bias": "model-00004-of-00013.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.12.input_layernorm.bias": "model-00005-of-00013.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.12.post_attention_layernorm.bias": "model-00005-of-00013.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.13.input_layernorm.bias": "model-00005-of-00013.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.13.post_attention_layernorm.bias": "model-00005-of-00013.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.14.input_layernorm.bias": "model-00005-of-00013.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.14.post_attention_layernorm.bias": "model-00005-of-00013.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.15.input_layernorm.bias": "model-00005-of-00013.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.15.post_attention_layernorm.bias": "model-00005-of-00013.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.16.input_layernorm.bias": "model-00006-of-00013.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.16.post_attention_layernorm.bias": "model-00006-of-00013.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.17.input_layernorm.bias": "model-00006-of-00013.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.17.post_attention_layernorm.bias": "model-00006-of-00013.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.18.input_layernorm.bias": "model-00006-of-00013.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.18.post_attention_layernorm.bias": "model-00006-of-00013.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.19.input_layernorm.bias": "model-00007-of-00013.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.19.post_attention_layernorm.bias": "model-00007-of-00013.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.2.input_layernorm.bias": "model-00002-of-00013.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.2.post_attention_layernorm.bias": "model-00002-of-00013.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.20.input_layernorm.bias": "model-00007-of-00013.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.20.post_attention_layernorm.bias": "model-00007-of-00013.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.21.input_layernorm.bias": "model-00007-of-00013.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.21.post_attention_layernorm.bias": "model-00007-of-00013.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.22.input_layernorm.bias": "model-00007-of-00013.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.22.post_attention_layernorm.bias": "model-00007-of-00013.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.23.input_layernorm.bias": "model-00008-of-00013.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.23.post_attention_layernorm.bias": "model-00008-of-00013.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.24.input_layernorm.bias": "model-00008-of-00013.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.24.post_attention_layernorm.bias": "model-00008-of-00013.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.25.input_layernorm.bias": "model-00008-of-00013.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.25.post_attention_layernorm.bias": "model-00008-of-00013.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.26.input_layernorm.bias": "model-00009-of-00013.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.26.post_attention_layernorm.bias": "model-00009-of-00013.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.27.input_layernorm.bias": "model-00009-of-00013.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.27.post_attention_layernorm.bias": "model-00009-of-00013.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.28.input_layernorm.bias": "model-00009-of-00013.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.28.post_attention_layernorm.bias": "model-00009-of-00013.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.29.input_layernorm.bias": "model-00009-of-00013.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.29.post_attention_layernorm.bias": "model-00009-of-00013.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.3.input_layernorm.bias": "model-00002-of-00013.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.post_attention_layernorm.bias": "model-00002-of-00013.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.30.input_layernorm.bias": "model-00010-of-00013.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.30.post_attention_layernorm.bias": "model-00010-of-00013.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.31.input_layernorm.bias": "model-00010-of-00013.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.31.post_attention_layernorm.bias": "model-00010-of-00013.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.32.input_layernorm.bias": "model-00010-of-00013.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.32.post_attention_layernorm.bias": "model-00010-of-00013.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.33.input_layernorm.bias": "model-00011-of-00013.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.33.post_attention_layernorm.bias": "model-00011-of-00013.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.34.input_layernorm.bias": "model-00011-of-00013.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.34.post_attention_layernorm.bias": "model-00011-of-00013.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.35.input_layernorm.bias": "model-00011-of-00013.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.35.post_attention_layernorm.bias": "model-00011-of-00013.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.36.input_layernorm.bias": "model-00011-of-00013.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.36.post_attention_layernorm.bias": "model-00011-of-00013.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.37.input_layernorm.bias": "model-00012-of-00013.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.37.post_attention_layernorm.bias": "model-00012-of-00013.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.38.input_layernorm.bias": "model-00012-of-00013.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.38.post_attention_layernorm.bias": "model-00012-of-00013.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.39.input_layernorm.bias": "model-00012-of-00013.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.39.post_attention_layernorm.bias": "model-00012-of-00013.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.4.input_layernorm.bias": "model-00002-of-00013.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.4.post_attention_layernorm.bias": "model-00002-of-00013.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.5.input_layernorm.bias": "model-00003-of-00013.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.5.post_attention_layernorm.bias": "model-00003-of-00013.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.6.input_layernorm.bias": "model-00003-of-00013.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.post_attention_layernorm.bias": "model-00003-of-00013.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.7.input_layernorm.bias": "model-00003-of-00013.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.7.post_attention_layernorm.bias": "model-00003-of-00013.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.8.input_layernorm.bias": "model-00003-of-00013.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.8.post_attention_layernorm.bias": "model-00003-of-00013.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.9.input_layernorm.bias": "model-00004-of-00013.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.9.post_attention_layernorm.bias": "model-00004-of-00013.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+    "model.norm.bias": "model-00012-of-00013.safetensors",
+    "model.norm.weight": "model-00012-of-00013.safetensors"
+  }
+}