Chaeseung commited on
Commit
4259914
1 Parent(s): aa4a95c

Upload OrionForCausalLM

Browse files
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./custom_LLM_log_char",
3
+ "architectures": [
4
+ "OrionForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "auto_map": {
8
+ "AutoConfig": "configuration_orion.OrionConfig",
9
+ "AutoModelForCausalLM": "OrionStarAI/Orion-14B-Base--modeling_orion.OrionForCausalLM"
10
+ },
11
+ "bos_token_id": 1,
12
+ "eos_token_id": 2,
13
+ "hidden_act": "silu",
14
+ "hidden_size": 5120,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 15360,
17
+ "max_position_embeddings": 4096,
18
+ "max_sequence_length": 4096,
19
+ "model_type": "orion",
20
+ "num_attention_heads": 40,
21
+ "num_hidden_layers": 40,
22
+ "num_key_value_heads": 40,
23
+ "pad_token_id": 0,
24
+ "pretraining_tp": 1,
25
+ "rms_norm_eps": 1e-05,
26
+ "rope_scaling": null,
27
+ "rope_theta": 10000.0,
28
+ "tie_word_embeddings": false,
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.37.1",
31
+ "use_cache": true,
32
+ "vocab_size": 84608
33
+ }
configuration_orion.py ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Copyright (c) 2024, OrionStar Inc. All rights reserved.
2
+
3
+ from transformers import PretrainedConfig
4
+
5
+ class OrionConfig(PretrainedConfig):
6
+ model_type = "orion"
7
+ keys_to_ignore_at_inference = ["past_key_values"]
8
+
9
+ def __init__(
10
+ self,
11
+ vocab_size=84608,
12
+ hidden_size=4096,
13
+ intermediate_size=15360,
14
+ num_hidden_layers=40,
15
+ num_attention_heads=40,
16
+ num_key_value_heads=40,
17
+ hidden_act="silu",
18
+ max_position_embeddings=4096,
19
+ initializer_range=0.02,
20
+ rms_norm_eps=1e-5,
21
+ use_cache=True,
22
+ pad_token_id=None,
23
+ bos_token_id=1,
24
+ eos_token_id=2,
25
+ pretraining_tp=1,
26
+ tie_word_embeddings=False,
27
+ rope_theta=10000.0,
28
+ rope_scaling=None,
29
+ attention_bias=False,
30
+ **kwargs,
31
+ ):
32
+ self.vocab_size = vocab_size
33
+ self.max_position_embeddings = max_position_embeddings
34
+ self.hidden_size = hidden_size
35
+ self.intermediate_size = intermediate_size
36
+ self.num_hidden_layers = num_hidden_layers
37
+ self.num_attention_heads = num_attention_heads
38
+
39
+ # for backward compatibility
40
+ if num_key_value_heads is None:
41
+ num_key_value_heads = num_attention_heads
42
+
43
+ self.num_key_value_heads = num_key_value_heads
44
+ self.hidden_act = hidden_act
45
+ self.initializer_range = initializer_range
46
+ self.rms_norm_eps = rms_norm_eps
47
+ self.pretraining_tp = pretraining_tp
48
+ self.use_cache = use_cache
49
+ self.rope_theta = rope_theta
50
+ self.rope_scaling = rope_scaling
51
+ self._rope_scaling_validation()
52
+ self.attention_bias = attention_bias
53
+
54
+ super().__init__(
55
+ pad_token_id=pad_token_id,
56
+ bos_token_id=bos_token_id,
57
+ eos_token_id=eos_token_id,
58
+ tie_word_embeddings=tie_word_embeddings,
59
+ **kwargs,
60
+ )
61
+
62
+ def _rope_scaling_validation(self):
63
+ """
64
+ Validate the `rope_scaling` configuration.
65
+ """
66
+ if self.rope_scaling is None:
67
+ return
68
+
69
+ if not isinstance(self.rope_scaling, dict) or len(self.rope_scaling) != 2:
70
+ raise ValueError(
71
+ "`rope_scaling` must be a dictionary with with two fields, `type` and `factor`, "
72
+ f"got {self.rope_scaling}"
73
+ )
74
+ rope_scaling_type = self.rope_scaling.get("type", None)
75
+ rope_scaling_factor = self.rope_scaling.get("factor", None)
76
+ if rope_scaling_type is None or rope_scaling_type not in ["linear", "dynamic"]:
77
+ raise ValueError(
78
+ f"`rope_scaling`'s type field must be one of ['linear', 'dynamic'], got {rope_scaling_type}"
79
+ )
80
+ if rope_scaling_factor is None or not isinstance(rope_scaling_factor, float) or rope_scaling_factor <= 1.0:
81
+ raise ValueError(f"`rope_scaling`'s factor field must be an float > 1, got {rope_scaling_factor}")
82
+
generation_config.json CHANGED
@@ -2,6 +2,6 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
- "pad_token_id": 2,
6
  "transformers_version": "4.37.1"
7
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
  "transformers_version": "4.37.1"
7
  }
model-00001-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b466bc3d79da5c369fb734a10eaf1a90879126d6423016833e44370da1fa1b0
3
+ size 4878666800
model-00002-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a978db83cfe9f7d1b1519977d77bbf2054112e4633cfe831e0f509dc84d500dc
3
+ size 4718841760
model-00003-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cae94f7cda1c91642fa7c4bccf93a27f204c818ff78214f6da24a607ea93eb52
3
+ size 4823782088
model-00004-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6277730aacdbb90695bcccaf6f879d305f4e74b95c36a3ed0f9efe79210b0f5
3
+ size 4718841792
model-00005-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:821f222aabe5f2da8b45f7a1500547f420830a87df99d47de46ad3ddbedb9e9a
3
+ size 4823782128
model-00006-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:440e99d9ce9c015247a7d65765836670dda80174d1d29291e54e25c62422ce0e
3
+ size 4718841792
model-00007-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e22f21b821d081842f367d237bc50dca35593528b6790f622d7ed56118ccfcb9
3
+ size 4823782128
model-00008-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d9aefa0ed4bbb04245d53e0a4327eb153d3dabfc343c4ee73567a3fc44bbc38
3
+ size 4718841792
model-00009-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64ce8c4c8024303942fa62df25522e0625255849eb6218957da943ecf4f5fd6d
3
+ size 4823782128
model-00010-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5500f1a153dce3b8a29cb0d5a6574e394c941ff59a6512d17c843ddd3bf943b
3
+ size 4718841792
model-00011-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f328115bfe7d37a09ae9c227eb23c3e16ae8e47a909b92f969d5be6101c65d2
3
+ size 4823782128
model-00012-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6edd0cab2b25bc4c63ca2508c5de0a4a6655cadb7103e4e852eae3b2c1daac95
3
+ size 3670306240
model-00013-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62cac05daca3d997d2f7a8699783005e587a4697c3eac6dd3515ed8c73b3d677
3
+ size 1732771968
model.safetensors.index.json ADDED
@@ -0,0 +1,451 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 57994813440
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00013-of-00013.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00013.safetensors",
8
+ "model.layers.0.input_layernorm.bias": "model-00001-of-00013.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00013.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00013.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00013.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00013.safetensors",
13
+ "model.layers.0.post_attention_layernorm.bias": "model-00001-of-00013.safetensors",
14
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
15
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
16
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
18
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
19
+ "model.layers.1.input_layernorm.bias": "model-00001-of-00013.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00013.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00013.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00013.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00013.safetensors",
24
+ "model.layers.1.post_attention_layernorm.bias": "model-00001-of-00013.safetensors",
25
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
28
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
29
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
30
+ "model.layers.10.input_layernorm.bias": "model-00004-of-00013.safetensors",
31
+ "model.layers.10.input_layernorm.weight": "model-00004-of-00013.safetensors",
32
+ "model.layers.10.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
33
+ "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
34
+ "model.layers.10.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
35
+ "model.layers.10.post_attention_layernorm.bias": "model-00004-of-00013.safetensors",
36
+ "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
37
+ "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
38
+ "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
39
+ "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
40
+ "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
41
+ "model.layers.11.input_layernorm.bias": "model-00004-of-00013.safetensors",
42
+ "model.layers.11.input_layernorm.weight": "model-00004-of-00013.safetensors",
43
+ "model.layers.11.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
44
+ "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
45
+ "model.layers.11.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
46
+ "model.layers.11.post_attention_layernorm.bias": "model-00004-of-00013.safetensors",
47
+ "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
48
+ "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
49
+ "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
50
+ "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
51
+ "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
52
+ "model.layers.12.input_layernorm.bias": "model-00005-of-00013.safetensors",
53
+ "model.layers.12.input_layernorm.weight": "model-00005-of-00013.safetensors",
54
+ "model.layers.12.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
55
+ "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
56
+ "model.layers.12.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
57
+ "model.layers.12.post_attention_layernorm.bias": "model-00005-of-00013.safetensors",
58
+ "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
59
+ "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
60
+ "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
61
+ "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
62
+ "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
63
+ "model.layers.13.input_layernorm.bias": "model-00005-of-00013.safetensors",
64
+ "model.layers.13.input_layernorm.weight": "model-00005-of-00013.safetensors",
65
+ "model.layers.13.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
66
+ "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
67
+ "model.layers.13.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
68
+ "model.layers.13.post_attention_layernorm.bias": "model-00005-of-00013.safetensors",
69
+ "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
70
+ "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
71
+ "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
72
+ "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
73
+ "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
74
+ "model.layers.14.input_layernorm.bias": "model-00005-of-00013.safetensors",
75
+ "model.layers.14.input_layernorm.weight": "model-00005-of-00013.safetensors",
76
+ "model.layers.14.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
77
+ "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
78
+ "model.layers.14.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
79
+ "model.layers.14.post_attention_layernorm.bias": "model-00005-of-00013.safetensors",
80
+ "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
81
+ "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
82
+ "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
83
+ "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
84
+ "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
85
+ "model.layers.15.input_layernorm.bias": "model-00005-of-00013.safetensors",
86
+ "model.layers.15.input_layernorm.weight": "model-00005-of-00013.safetensors",
87
+ "model.layers.15.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
88
+ "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
89
+ "model.layers.15.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
90
+ "model.layers.15.post_attention_layernorm.bias": "model-00005-of-00013.safetensors",
91
+ "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
92
+ "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
93
+ "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
94
+ "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
95
+ "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
96
+ "model.layers.16.input_layernorm.bias": "model-00006-of-00013.safetensors",
97
+ "model.layers.16.input_layernorm.weight": "model-00006-of-00013.safetensors",
98
+ "model.layers.16.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
99
+ "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
100
+ "model.layers.16.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
101
+ "model.layers.16.post_attention_layernorm.bias": "model-00006-of-00013.safetensors",
102
+ "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
103
+ "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
104
+ "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
105
+ "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
106
+ "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
107
+ "model.layers.17.input_layernorm.bias": "model-00006-of-00013.safetensors",
108
+ "model.layers.17.input_layernorm.weight": "model-00006-of-00013.safetensors",
109
+ "model.layers.17.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
110
+ "model.layers.17.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
111
+ "model.layers.17.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
112
+ "model.layers.17.post_attention_layernorm.bias": "model-00006-of-00013.safetensors",
113
+ "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
114
+ "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
115
+ "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
116
+ "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
117
+ "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
118
+ "model.layers.18.input_layernorm.bias": "model-00006-of-00013.safetensors",
119
+ "model.layers.18.input_layernorm.weight": "model-00006-of-00013.safetensors",
120
+ "model.layers.18.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
121
+ "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
122
+ "model.layers.18.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
123
+ "model.layers.18.post_attention_layernorm.bias": "model-00006-of-00013.safetensors",
124
+ "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
125
+ "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
126
+ "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
127
+ "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
128
+ "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
129
+ "model.layers.19.input_layernorm.bias": "model-00007-of-00013.safetensors",
130
+ "model.layers.19.input_layernorm.weight": "model-00007-of-00013.safetensors",
131
+ "model.layers.19.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
132
+ "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
133
+ "model.layers.19.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
134
+ "model.layers.19.post_attention_layernorm.bias": "model-00007-of-00013.safetensors",
135
+ "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
136
+ "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
137
+ "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
138
+ "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
139
+ "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
140
+ "model.layers.2.input_layernorm.bias": "model-00002-of-00013.safetensors",
141
+ "model.layers.2.input_layernorm.weight": "model-00002-of-00013.safetensors",
142
+ "model.layers.2.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
143
+ "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
144
+ "model.layers.2.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
145
+ "model.layers.2.post_attention_layernorm.bias": "model-00002-of-00013.safetensors",
146
+ "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
147
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
148
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
149
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
150
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
151
+ "model.layers.20.input_layernorm.bias": "model-00007-of-00013.safetensors",
152
+ "model.layers.20.input_layernorm.weight": "model-00007-of-00013.safetensors",
153
+ "model.layers.20.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
154
+ "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
155
+ "model.layers.20.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
156
+ "model.layers.20.post_attention_layernorm.bias": "model-00007-of-00013.safetensors",
157
+ "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
158
+ "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
159
+ "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
160
+ "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
161
+ "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
162
+ "model.layers.21.input_layernorm.bias": "model-00007-of-00013.safetensors",
163
+ "model.layers.21.input_layernorm.weight": "model-00007-of-00013.safetensors",
164
+ "model.layers.21.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
165
+ "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
166
+ "model.layers.21.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
167
+ "model.layers.21.post_attention_layernorm.bias": "model-00007-of-00013.safetensors",
168
+ "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
169
+ "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
170
+ "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
171
+ "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
172
+ "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
173
+ "model.layers.22.input_layernorm.bias": "model-00007-of-00013.safetensors",
174
+ "model.layers.22.input_layernorm.weight": "model-00007-of-00013.safetensors",
175
+ "model.layers.22.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
176
+ "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
177
+ "model.layers.22.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
178
+ "model.layers.22.post_attention_layernorm.bias": "model-00007-of-00013.safetensors",
179
+ "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
180
+ "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
181
+ "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
182
+ "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
183
+ "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
184
+ "model.layers.23.input_layernorm.bias": "model-00008-of-00013.safetensors",
185
+ "model.layers.23.input_layernorm.weight": "model-00008-of-00013.safetensors",
186
+ "model.layers.23.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
187
+ "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
188
+ "model.layers.23.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
189
+ "model.layers.23.post_attention_layernorm.bias": "model-00008-of-00013.safetensors",
190
+ "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
191
+ "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
192
+ "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
193
+ "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
194
+ "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
195
+ "model.layers.24.input_layernorm.bias": "model-00008-of-00013.safetensors",
196
+ "model.layers.24.input_layernorm.weight": "model-00008-of-00013.safetensors",
197
+ "model.layers.24.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
198
+ "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
199
+ "model.layers.24.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
200
+ "model.layers.24.post_attention_layernorm.bias": "model-00008-of-00013.safetensors",
201
+ "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
202
+ "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
203
+ "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
204
+ "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
205
+ "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
206
+ "model.layers.25.input_layernorm.bias": "model-00008-of-00013.safetensors",
207
+ "model.layers.25.input_layernorm.weight": "model-00008-of-00013.safetensors",
208
+ "model.layers.25.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
209
+ "model.layers.25.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
210
+ "model.layers.25.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
211
+ "model.layers.25.post_attention_layernorm.bias": "model-00008-of-00013.safetensors",
212
+ "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
213
+ "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
214
+ "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
215
+ "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
216
+ "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
217
+ "model.layers.26.input_layernorm.bias": "model-00009-of-00013.safetensors",
218
+ "model.layers.26.input_layernorm.weight": "model-00009-of-00013.safetensors",
219
+ "model.layers.26.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
220
+ "model.layers.26.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
221
+ "model.layers.26.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
222
+ "model.layers.26.post_attention_layernorm.bias": "model-00009-of-00013.safetensors",
223
+ "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
224
+ "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
225
+ "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
226
+ "model.layers.26.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
227
+ "model.layers.26.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
228
+ "model.layers.27.input_layernorm.bias": "model-00009-of-00013.safetensors",
229
+ "model.layers.27.input_layernorm.weight": "model-00009-of-00013.safetensors",
230
+ "model.layers.27.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
231
+ "model.layers.27.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
232
+ "model.layers.27.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
233
+ "model.layers.27.post_attention_layernorm.bias": "model-00009-of-00013.safetensors",
234
+ "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
235
+ "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
236
+ "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
237
+ "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
238
+ "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
239
+ "model.layers.28.input_layernorm.bias": "model-00009-of-00013.safetensors",
240
+ "model.layers.28.input_layernorm.weight": "model-00009-of-00013.safetensors",
241
+ "model.layers.28.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
242
+ "model.layers.28.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
243
+ "model.layers.28.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
244
+ "model.layers.28.post_attention_layernorm.bias": "model-00009-of-00013.safetensors",
245
+ "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
246
+ "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
247
+ "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
248
+ "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
249
+ "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
250
+ "model.layers.29.input_layernorm.bias": "model-00009-of-00013.safetensors",
251
+ "model.layers.29.input_layernorm.weight": "model-00009-of-00013.safetensors",
252
+ "model.layers.29.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
253
+ "model.layers.29.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
254
+ "model.layers.29.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
255
+ "model.layers.29.post_attention_layernorm.bias": "model-00009-of-00013.safetensors",
256
+ "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
257
+ "model.layers.29.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
258
+ "model.layers.29.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
259
+ "model.layers.29.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
260
+ "model.layers.29.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
261
+ "model.layers.3.input_layernorm.bias": "model-00002-of-00013.safetensors",
262
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00013.safetensors",
263
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
264
+ "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
265
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
266
+ "model.layers.3.post_attention_layernorm.bias": "model-00002-of-00013.safetensors",
267
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
268
+ "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
269
+ "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
270
+ "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
271
+ "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
272
+ "model.layers.30.input_layernorm.bias": "model-00010-of-00013.safetensors",
273
+ "model.layers.30.input_layernorm.weight": "model-00010-of-00013.safetensors",
274
+ "model.layers.30.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
275
+ "model.layers.30.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
276
+ "model.layers.30.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
277
+ "model.layers.30.post_attention_layernorm.bias": "model-00010-of-00013.safetensors",
278
+ "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
279
+ "model.layers.30.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
280
+ "model.layers.30.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
281
+ "model.layers.30.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
282
+ "model.layers.30.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
283
+ "model.layers.31.input_layernorm.bias": "model-00010-of-00013.safetensors",
284
+ "model.layers.31.input_layernorm.weight": "model-00010-of-00013.safetensors",
285
+ "model.layers.31.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
286
+ "model.layers.31.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
287
+ "model.layers.31.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
288
+ "model.layers.31.post_attention_layernorm.bias": "model-00010-of-00013.safetensors",
289
+ "model.layers.31.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
290
+ "model.layers.31.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
291
+ "model.layers.31.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
292
+ "model.layers.31.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
293
+ "model.layers.31.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
294
+ "model.layers.32.input_layernorm.bias": "model-00010-of-00013.safetensors",
295
+ "model.layers.32.input_layernorm.weight": "model-00010-of-00013.safetensors",
296
+ "model.layers.32.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
297
+ "model.layers.32.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
298
+ "model.layers.32.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
299
+ "model.layers.32.post_attention_layernorm.bias": "model-00010-of-00013.safetensors",
300
+ "model.layers.32.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
301
+ "model.layers.32.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
302
+ "model.layers.32.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
303
+ "model.layers.32.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
304
+ "model.layers.32.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
305
+ "model.layers.33.input_layernorm.bias": "model-00011-of-00013.safetensors",
306
+ "model.layers.33.input_layernorm.weight": "model-00011-of-00013.safetensors",
307
+ "model.layers.33.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
308
+ "model.layers.33.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
309
+ "model.layers.33.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
310
+ "model.layers.33.post_attention_layernorm.bias": "model-00011-of-00013.safetensors",
311
+ "model.layers.33.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
312
+ "model.layers.33.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
313
+ "model.layers.33.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
314
+ "model.layers.33.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
315
+ "model.layers.33.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
316
+ "model.layers.34.input_layernorm.bias": "model-00011-of-00013.safetensors",
317
+ "model.layers.34.input_layernorm.weight": "model-00011-of-00013.safetensors",
318
+ "model.layers.34.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
319
+ "model.layers.34.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
320
+ "model.layers.34.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
321
+ "model.layers.34.post_attention_layernorm.bias": "model-00011-of-00013.safetensors",
322
+ "model.layers.34.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
323
+ "model.layers.34.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
324
+ "model.layers.34.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
325
+ "model.layers.34.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
326
+ "model.layers.34.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
327
+ "model.layers.35.input_layernorm.bias": "model-00011-of-00013.safetensors",
328
+ "model.layers.35.input_layernorm.weight": "model-00011-of-00013.safetensors",
329
+ "model.layers.35.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
330
+ "model.layers.35.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
331
+ "model.layers.35.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
332
+ "model.layers.35.post_attention_layernorm.bias": "model-00011-of-00013.safetensors",
333
+ "model.layers.35.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
334
+ "model.layers.35.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
335
+ "model.layers.35.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
336
+ "model.layers.35.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
337
+ "model.layers.35.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
338
+ "model.layers.36.input_layernorm.bias": "model-00011-of-00013.safetensors",
339
+ "model.layers.36.input_layernorm.weight": "model-00011-of-00013.safetensors",
340
+ "model.layers.36.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
341
+ "model.layers.36.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
342
+ "model.layers.36.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
343
+ "model.layers.36.post_attention_layernorm.bias": "model-00011-of-00013.safetensors",
344
+ "model.layers.36.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
345
+ "model.layers.36.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
346
+ "model.layers.36.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
347
+ "model.layers.36.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
348
+ "model.layers.36.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
349
+ "model.layers.37.input_layernorm.bias": "model-00012-of-00013.safetensors",
350
+ "model.layers.37.input_layernorm.weight": "model-00012-of-00013.safetensors",
351
+ "model.layers.37.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
352
+ "model.layers.37.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
353
+ "model.layers.37.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
354
+ "model.layers.37.post_attention_layernorm.bias": "model-00012-of-00013.safetensors",
355
+ "model.layers.37.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
356
+ "model.layers.37.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
357
+ "model.layers.37.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
358
+ "model.layers.37.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
359
+ "model.layers.37.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
360
+ "model.layers.38.input_layernorm.bias": "model-00012-of-00013.safetensors",
361
+ "model.layers.38.input_layernorm.weight": "model-00012-of-00013.safetensors",
362
+ "model.layers.38.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
363
+ "model.layers.38.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
364
+ "model.layers.38.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
365
+ "model.layers.38.post_attention_layernorm.bias": "model-00012-of-00013.safetensors",
366
+ "model.layers.38.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
367
+ "model.layers.38.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
368
+ "model.layers.38.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
369
+ "model.layers.38.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
370
+ "model.layers.38.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
371
+ "model.layers.39.input_layernorm.bias": "model-00012-of-00013.safetensors",
372
+ "model.layers.39.input_layernorm.weight": "model-00012-of-00013.safetensors",
373
+ "model.layers.39.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
374
+ "model.layers.39.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
375
+ "model.layers.39.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
376
+ "model.layers.39.post_attention_layernorm.bias": "model-00012-of-00013.safetensors",
377
+ "model.layers.39.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
378
+ "model.layers.39.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
379
+ "model.layers.39.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
380
+ "model.layers.39.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
381
+ "model.layers.39.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
382
+ "model.layers.4.input_layernorm.bias": "model-00002-of-00013.safetensors",
383
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00013.safetensors",
384
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
385
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
386
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
387
+ "model.layers.4.post_attention_layernorm.bias": "model-00002-of-00013.safetensors",
388
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
389
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
390
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
391
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
392
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
393
+ "model.layers.5.input_layernorm.bias": "model-00003-of-00013.safetensors",
394
+ "model.layers.5.input_layernorm.weight": "model-00003-of-00013.safetensors",
395
+ "model.layers.5.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
396
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
397
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
398
+ "model.layers.5.post_attention_layernorm.bias": "model-00003-of-00013.safetensors",
399
+ "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
400
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
401
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
402
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
403
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
404
+ "model.layers.6.input_layernorm.bias": "model-00003-of-00013.safetensors",
405
+ "model.layers.6.input_layernorm.weight": "model-00003-of-00013.safetensors",
406
+ "model.layers.6.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
407
+ "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
408
+ "model.layers.6.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
409
+ "model.layers.6.post_attention_layernorm.bias": "model-00003-of-00013.safetensors",
410
+ "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
411
+ "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
412
+ "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
413
+ "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
414
+ "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
415
+ "model.layers.7.input_layernorm.bias": "model-00003-of-00013.safetensors",
416
+ "model.layers.7.input_layernorm.weight": "model-00003-of-00013.safetensors",
417
+ "model.layers.7.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
418
+ "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
419
+ "model.layers.7.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
420
+ "model.layers.7.post_attention_layernorm.bias": "model-00003-of-00013.safetensors",
421
+ "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
422
+ "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
423
+ "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
424
+ "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
425
+ "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
426
+ "model.layers.8.input_layernorm.bias": "model-00003-of-00013.safetensors",
427
+ "model.layers.8.input_layernorm.weight": "model-00003-of-00013.safetensors",
428
+ "model.layers.8.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
429
+ "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
430
+ "model.layers.8.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
431
+ "model.layers.8.post_attention_layernorm.bias": "model-00003-of-00013.safetensors",
432
+ "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
433
+ "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
434
+ "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
435
+ "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
436
+ "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
437
+ "model.layers.9.input_layernorm.bias": "model-00004-of-00013.safetensors",
438
+ "model.layers.9.input_layernorm.weight": "model-00004-of-00013.safetensors",
439
+ "model.layers.9.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
440
+ "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
441
+ "model.layers.9.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
442
+ "model.layers.9.post_attention_layernorm.bias": "model-00004-of-00013.safetensors",
443
+ "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
444
+ "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
445
+ "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
446
+ "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
447
+ "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
448
+ "model.norm.bias": "model-00012-of-00013.safetensors",
449
+ "model.norm.weight": "model-00012-of-00013.safetensors"
450
+ }
451
+ }