Hugging Face's logo

zjkarina
/
Matreshka_Llama

Transformers
PyTorch
llama
text-generation-inference
Inference Endpoints
Model card Files Community
zjkarina commited on
Commit
650f314
•
1 Parent(s): 24c01cc

Upload model

Browse files
Files changed (5) hide show
  1. config.json +24 -0
  2. generation_config.json +7 -0
  3. pytorch_model-00001-of-00002.bin +3 -0
  4. pytorch_model-00002-of-00002.bin +3 -0
  5. pytorch_model.bin.index.json +655 -0
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "huggyllama/llama-7b",
3
+ "architectures": [
4
+ "TensorParallelPreTrainedModel"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 11008,
12
+ "max_position_embeddings": 2048,
13
+ "max_sequence_length": 2048,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "pad_token_id": 0,
18
+ "rms_norm_eps": 1e-06,
19
+ "tie_word_embeddings": false,
20
+ "torch_dtype": "float16",
21
+ "transformers_version": "4.28.1",
22
+ "use_cache": true,
23
+ "vocab_size": 32004
24
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.28.1"
7
+ }
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:becd6df19deb2a3abedce5881fb29024a400eca939d8ac97e857e33ef43bca1e
3
+ size 9972990772
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bb9cd4d016529d6286c960477c6710f334feac59ae958c3ef6c56c01173a8f0
3
+ size 3504714934
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,655 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 13477445632
4
+ },
5
+ "weight_map": {
6
+ "wrapped_model._sanity_check_params.0": "pytorch_model-00002-of-00002.bin",
7
+ "wrapped_model._sanity_check_params.1": "pytorch_model-00002-of-00002.bin",
8
+ "wrapped_model.module_shards.0.lm_head.tp_wrapped_module.weight": "pytorch_model-00001-of-00002.bin",
9
+ "wrapped_model.module_shards.0.model.embed_tokens.tp_wrapped_module.weight": "pytorch_model-00001-of-00002.bin",
10
+ "wrapped_model.module_shards.0.model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
11
+ "wrapped_model.module_shards.0.model.layers.0.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
12
+ "wrapped_model.module_shards.0.model.layers.0.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
13
+ "wrapped_model.module_shards.0.model.layers.0.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
14
+ "wrapped_model.module_shards.0.model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
15
+ "wrapped_model.module_shards.0.model.layers.0.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
16
+ "wrapped_model.module_shards.0.model.layers.0.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
17
+ "wrapped_model.module_shards.0.model.layers.0.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
18
+ "wrapped_model.module_shards.0.model.layers.0.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
19
+ "wrapped_model.module_shards.0.model.layers.0.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
20
+ "wrapped_model.module_shards.0.model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
21
+ "wrapped_model.module_shards.0.model.layers.1.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
22
+ "wrapped_model.module_shards.0.model.layers.1.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
23
+ "wrapped_model.module_shards.0.model.layers.1.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
24
+ "wrapped_model.module_shards.0.model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
25
+ "wrapped_model.module_shards.0.model.layers.1.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
26
+ "wrapped_model.module_shards.0.model.layers.1.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
27
+ "wrapped_model.module_shards.0.model.layers.1.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
28
+ "wrapped_model.module_shards.0.model.layers.1.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
29
+ "wrapped_model.module_shards.0.model.layers.1.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
30
+ "wrapped_model.module_shards.0.model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
31
+ "wrapped_model.module_shards.0.model.layers.10.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
32
+ "wrapped_model.module_shards.0.model.layers.10.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
33
+ "wrapped_model.module_shards.0.model.layers.10.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
34
+ "wrapped_model.module_shards.0.model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
35
+ "wrapped_model.module_shards.0.model.layers.10.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
36
+ "wrapped_model.module_shards.0.model.layers.10.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
37
+ "wrapped_model.module_shards.0.model.layers.10.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
38
+ "wrapped_model.module_shards.0.model.layers.10.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
39
+ "wrapped_model.module_shards.0.model.layers.10.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
40
+ "wrapped_model.module_shards.0.model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
41
+ "wrapped_model.module_shards.0.model.layers.11.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
42
+ "wrapped_model.module_shards.0.model.layers.11.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
43
+ "wrapped_model.module_shards.0.model.layers.11.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
44
+ "wrapped_model.module_shards.0.model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
45
+ "wrapped_model.module_shards.0.model.layers.11.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
46
+ "wrapped_model.module_shards.0.model.layers.11.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
47
+ "wrapped_model.module_shards.0.model.layers.11.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
48
+ "wrapped_model.module_shards.0.model.layers.11.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
49
+ "wrapped_model.module_shards.0.model.layers.11.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
50
+ "wrapped_model.module_shards.0.model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
51
+ "wrapped_model.module_shards.0.model.layers.12.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
52
+ "wrapped_model.module_shards.0.model.layers.12.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
53
+ "wrapped_model.module_shards.0.model.layers.12.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
54
+ "wrapped_model.module_shards.0.model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
55
+ "wrapped_model.module_shards.0.model.layers.12.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
56
+ "wrapped_model.module_shards.0.model.layers.12.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
57
+ "wrapped_model.module_shards.0.model.layers.12.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
58
+ "wrapped_model.module_shards.0.model.layers.12.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
59
+ "wrapped_model.module_shards.0.model.layers.12.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
60
+ "wrapped_model.module_shards.0.model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
61
+ "wrapped_model.module_shards.0.model.layers.13.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
62
+ "wrapped_model.module_shards.0.model.layers.13.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
63
+ "wrapped_model.module_shards.0.model.layers.13.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
64
+ "wrapped_model.module_shards.0.model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
65
+ "wrapped_model.module_shards.0.model.layers.13.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
66
+ "wrapped_model.module_shards.0.model.layers.13.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
67
+ "wrapped_model.module_shards.0.model.layers.13.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
68
+ "wrapped_model.module_shards.0.model.layers.13.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
69
+ "wrapped_model.module_shards.0.model.layers.13.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
70
+ "wrapped_model.module_shards.0.model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
71
+ "wrapped_model.module_shards.0.model.layers.14.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
72
+ "wrapped_model.module_shards.0.model.layers.14.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
73
+ "wrapped_model.module_shards.0.model.layers.14.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
74
+ "wrapped_model.module_shards.0.model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
75
+ "wrapped_model.module_shards.0.model.layers.14.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
76
+ "wrapped_model.module_shards.0.model.layers.14.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
77
+ "wrapped_model.module_shards.0.model.layers.14.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
78
+ "wrapped_model.module_shards.0.model.layers.14.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
79
+ "wrapped_model.module_shards.0.model.layers.14.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
80
+ "wrapped_model.module_shards.0.model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
81
+ "wrapped_model.module_shards.0.model.layers.15.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
82
+ "wrapped_model.module_shards.0.model.layers.15.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
83
+ "wrapped_model.module_shards.0.model.layers.15.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
84
+ "wrapped_model.module_shards.0.model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
85
+ "wrapped_model.module_shards.0.model.layers.15.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
86
+ "wrapped_model.module_shards.0.model.layers.15.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
87
+ "wrapped_model.module_shards.0.model.layers.15.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
88
+ "wrapped_model.module_shards.0.model.layers.15.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
89
+ "wrapped_model.module_shards.0.model.layers.15.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
90
+ "wrapped_model.module_shards.0.model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
91
+ "wrapped_model.module_shards.0.model.layers.16.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
92
+ "wrapped_model.module_shards.0.model.layers.16.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
93
+ "wrapped_model.module_shards.0.model.layers.16.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
94
+ "wrapped_model.module_shards.0.model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
95
+ "wrapped_model.module_shards.0.model.layers.16.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
96
+ "wrapped_model.module_shards.0.model.layers.16.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
97
+ "wrapped_model.module_shards.0.model.layers.16.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
98
+ "wrapped_model.module_shards.0.model.layers.16.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
99
+ "wrapped_model.module_shards.0.model.layers.16.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
100
+ "wrapped_model.module_shards.0.model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
101
+ "wrapped_model.module_shards.0.model.layers.17.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
102
+ "wrapped_model.module_shards.0.model.layers.17.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
103
+ "wrapped_model.module_shards.0.model.layers.17.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
104
+ "wrapped_model.module_shards.0.model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
105
+ "wrapped_model.module_shards.0.model.layers.17.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
106
+ "wrapped_model.module_shards.0.model.layers.17.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
107
+ "wrapped_model.module_shards.0.model.layers.17.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
108
+ "wrapped_model.module_shards.0.model.layers.17.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
109
+ "wrapped_model.module_shards.0.model.layers.17.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
110
+ "wrapped_model.module_shards.0.model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
111
+ "wrapped_model.module_shards.0.model.layers.18.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
112
+ "wrapped_model.module_shards.0.model.layers.18.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
113
+ "wrapped_model.module_shards.0.model.layers.18.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
114
+ "wrapped_model.module_shards.0.model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
115
+ "wrapped_model.module_shards.0.model.layers.18.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
116
+ "wrapped_model.module_shards.0.model.layers.18.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
117
+ "wrapped_model.module_shards.0.model.layers.18.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
118
+ "wrapped_model.module_shards.0.model.layers.18.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
119
+ "wrapped_model.module_shards.0.model.layers.18.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
120
+ "wrapped_model.module_shards.0.model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
121
+ "wrapped_model.module_shards.0.model.layers.19.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
122
+ "wrapped_model.module_shards.0.model.layers.19.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
123
+ "wrapped_model.module_shards.0.model.layers.19.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
124
+ "wrapped_model.module_shards.0.model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
125
+ "wrapped_model.module_shards.0.model.layers.19.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
126
+ "wrapped_model.module_shards.0.model.layers.19.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
127
+ "wrapped_model.module_shards.0.model.layers.19.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
128
+ "wrapped_model.module_shards.0.model.layers.19.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
129
+ "wrapped_model.module_shards.0.model.layers.19.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
130
+ "wrapped_model.module_shards.0.model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
131
+ "wrapped_model.module_shards.0.model.layers.2.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
132
+ "wrapped_model.module_shards.0.model.layers.2.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
133
+ "wrapped_model.module_shards.0.model.layers.2.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
134
+ "wrapped_model.module_shards.0.model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
135
+ "wrapped_model.module_shards.0.model.layers.2.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
136
+ "wrapped_model.module_shards.0.model.layers.2.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
137
+ "wrapped_model.module_shards.0.model.layers.2.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
138
+ "wrapped_model.module_shards.0.model.layers.2.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
139
+ "wrapped_model.module_shards.0.model.layers.2.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
140
+ "wrapped_model.module_shards.0.model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
141
+ "wrapped_model.module_shards.0.model.layers.20.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
142
+ "wrapped_model.module_shards.0.model.layers.20.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
143
+ "wrapped_model.module_shards.0.model.layers.20.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
144
+ "wrapped_model.module_shards.0.model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
145
+ "wrapped_model.module_shards.0.model.layers.20.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
146
+ "wrapped_model.module_shards.0.model.layers.20.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
147
+ "wrapped_model.module_shards.0.model.layers.20.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
148
+ "wrapped_model.module_shards.0.model.layers.20.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
149
+ "wrapped_model.module_shards.0.model.layers.20.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
150
+ "wrapped_model.module_shards.0.model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
151
+ "wrapped_model.module_shards.0.model.layers.21.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
152
+ "wrapped_model.module_shards.0.model.layers.21.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
153
+ "wrapped_model.module_shards.0.model.layers.21.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
154
+ "wrapped_model.module_shards.0.model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
155
+ "wrapped_model.module_shards.0.model.layers.21.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
156
+ "wrapped_model.module_shards.0.model.layers.21.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
157
+ "wrapped_model.module_shards.0.model.layers.21.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
158
+ "wrapped_model.module_shards.0.model.layers.21.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
159
+ "wrapped_model.module_shards.0.model.layers.21.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
160
+ "wrapped_model.module_shards.0.model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
161
+ "wrapped_model.module_shards.0.model.layers.22.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
162
+ "wrapped_model.module_shards.0.model.layers.22.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
163
+ "wrapped_model.module_shards.0.model.layers.22.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
164
+ "wrapped_model.module_shards.0.model.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
165
+ "wrapped_model.module_shards.0.model.layers.22.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
166
+ "wrapped_model.module_shards.0.model.layers.22.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
167
+ "wrapped_model.module_shards.0.model.layers.22.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
168
+ "wrapped_model.module_shards.0.model.layers.22.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
169
+ "wrapped_model.module_shards.0.model.layers.22.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
170
+ "wrapped_model.module_shards.0.model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
171
+ "wrapped_model.module_shards.0.model.layers.23.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
172
+ "wrapped_model.module_shards.0.model.layers.23.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
173
+ "wrapped_model.module_shards.0.model.layers.23.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
174
+ "wrapped_model.module_shards.0.model.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
175
+ "wrapped_model.module_shards.0.model.layers.23.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
176
+ "wrapped_model.module_shards.0.model.layers.23.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
177
+ "wrapped_model.module_shards.0.model.layers.23.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
178
+ "wrapped_model.module_shards.0.model.layers.23.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
179
+ "wrapped_model.module_shards.0.model.layers.23.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
180
+ "wrapped_model.module_shards.0.model.layers.24.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
181
+ "wrapped_model.module_shards.0.model.layers.24.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
182
+ "wrapped_model.module_shards.0.model.layers.24.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
183
+ "wrapped_model.module_shards.0.model.layers.24.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
184
+ "wrapped_model.module_shards.0.model.layers.24.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
185
+ "wrapped_model.module_shards.0.model.layers.24.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
186
+ "wrapped_model.module_shards.0.model.layers.24.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
187
+ "wrapped_model.module_shards.0.model.layers.24.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
188
+ "wrapped_model.module_shards.0.model.layers.24.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
189
+ "wrapped_model.module_shards.0.model.layers.24.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
190
+ "wrapped_model.module_shards.0.model.layers.25.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
191
+ "wrapped_model.module_shards.0.model.layers.25.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
192
+ "wrapped_model.module_shards.0.model.layers.25.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
193
+ "wrapped_model.module_shards.0.model.layers.25.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
194
+ "wrapped_model.module_shards.0.model.layers.25.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
195
+ "wrapped_model.module_shards.0.model.layers.25.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
196
+ "wrapped_model.module_shards.0.model.layers.25.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
197
+ "wrapped_model.module_shards.0.model.layers.25.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
198
+ "wrapped_model.module_shards.0.model.layers.25.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
199
+ "wrapped_model.module_shards.0.model.layers.25.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
200
+ "wrapped_model.module_shards.0.model.layers.26.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
201
+ "wrapped_model.module_shards.0.model.layers.26.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
202
+ "wrapped_model.module_shards.0.model.layers.26.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
203
+ "wrapped_model.module_shards.0.model.layers.26.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
204
+ "wrapped_model.module_shards.0.model.layers.26.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
205
+ "wrapped_model.module_shards.0.model.layers.26.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
206
+ "wrapped_model.module_shards.0.model.layers.26.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
207
+ "wrapped_model.module_shards.0.model.layers.26.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
208
+ "wrapped_model.module_shards.0.model.layers.26.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
209
+ "wrapped_model.module_shards.0.model.layers.26.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
210
+ "wrapped_model.module_shards.0.model.layers.27.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
211
+ "wrapped_model.module_shards.0.model.layers.27.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
212
+ "wrapped_model.module_shards.0.model.layers.27.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
213
+ "wrapped_model.module_shards.0.model.layers.27.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
214
+ "wrapped_model.module_shards.0.model.layers.27.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
215
+ "wrapped_model.module_shards.0.model.layers.27.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
216
+ "wrapped_model.module_shards.0.model.layers.27.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
217
+ "wrapped_model.module_shards.0.model.layers.27.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
218
+ "wrapped_model.module_shards.0.model.layers.27.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
219
+ "wrapped_model.module_shards.0.model.layers.27.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
220
+ "wrapped_model.module_shards.0.model.layers.28.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
221
+ "wrapped_model.module_shards.0.model.layers.28.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
222
+ "wrapped_model.module_shards.0.model.layers.28.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
223
+ "wrapped_model.module_shards.0.model.layers.28.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
224
+ "wrapped_model.module_shards.0.model.layers.28.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
225
+ "wrapped_model.module_shards.0.model.layers.28.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
226
+ "wrapped_model.module_shards.0.model.layers.28.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
227
+ "wrapped_model.module_shards.0.model.layers.28.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
228
+ "wrapped_model.module_shards.0.model.layers.28.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
229
+ "wrapped_model.module_shards.0.model.layers.28.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
230
+ "wrapped_model.module_shards.0.model.layers.29.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
231
+ "wrapped_model.module_shards.0.model.layers.29.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
232
+ "wrapped_model.module_shards.0.model.layers.29.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
233
+ "wrapped_model.module_shards.0.model.layers.29.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
234
+ "wrapped_model.module_shards.0.model.layers.29.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
235
+ "wrapped_model.module_shards.0.model.layers.29.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
236
+ "wrapped_model.module_shards.0.model.layers.29.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
237
+ "wrapped_model.module_shards.0.model.layers.29.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
238
+ "wrapped_model.module_shards.0.model.layers.29.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
239
+ "wrapped_model.module_shards.0.model.layers.29.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
240
+ "wrapped_model.module_shards.0.model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
241
+ "wrapped_model.module_shards.0.model.layers.3.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
242
+ "wrapped_model.module_shards.0.model.layers.3.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
243
+ "wrapped_model.module_shards.0.model.layers.3.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
244
+ "wrapped_model.module_shards.0.model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
245
+ "wrapped_model.module_shards.0.model.layers.3.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
246
+ "wrapped_model.module_shards.0.model.layers.3.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
247
+ "wrapped_model.module_shards.0.model.layers.3.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
248
+ "wrapped_model.module_shards.0.model.layers.3.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
249
+ "wrapped_model.module_shards.0.model.layers.3.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
250
+ "wrapped_model.module_shards.0.model.layers.30.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
251
+ "wrapped_model.module_shards.0.model.layers.30.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
252
+ "wrapped_model.module_shards.0.model.layers.30.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
253
+ "wrapped_model.module_shards.0.model.layers.30.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
254
+ "wrapped_model.module_shards.0.model.layers.30.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
255
+ "wrapped_model.module_shards.0.model.layers.30.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
256
+ "wrapped_model.module_shards.0.model.layers.30.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
257
+ "wrapped_model.module_shards.0.model.layers.30.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
258
+ "wrapped_model.module_shards.0.model.layers.30.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
259
+ "wrapped_model.module_shards.0.model.layers.30.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
260
+ "wrapped_model.module_shards.0.model.layers.31.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
261
+ "wrapped_model.module_shards.0.model.layers.31.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
262
+ "wrapped_model.module_shards.0.model.layers.31.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
263
+ "wrapped_model.module_shards.0.model.layers.31.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
264
+ "wrapped_model.module_shards.0.model.layers.31.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
265
+ "wrapped_model.module_shards.0.model.layers.31.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
266
+ "wrapped_model.module_shards.0.model.layers.31.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
267
+ "wrapped_model.module_shards.0.model.layers.31.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
268
+ "wrapped_model.module_shards.0.model.layers.31.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
269
+ "wrapped_model.module_shards.0.model.layers.31.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
270
+ "wrapped_model.module_shards.0.model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
271
+ "wrapped_model.module_shards.0.model.layers.4.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
272
+ "wrapped_model.module_shards.0.model.layers.4.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
273
+ "wrapped_model.module_shards.0.model.layers.4.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
274
+ "wrapped_model.module_shards.0.model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
275
+ "wrapped_model.module_shards.0.model.layers.4.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
276
+ "wrapped_model.module_shards.0.model.layers.4.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
277
+ "wrapped_model.module_shards.0.model.layers.4.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
278
+ "wrapped_model.module_shards.0.model.layers.4.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
279
+ "wrapped_model.module_shards.0.model.layers.4.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
280
+ "wrapped_model.module_shards.0.model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
281
+ "wrapped_model.module_shards.0.model.layers.5.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
282
+ "wrapped_model.module_shards.0.model.layers.5.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
283
+ "wrapped_model.module_shards.0.model.layers.5.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
284
+ "wrapped_model.module_shards.0.model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
285
+ "wrapped_model.module_shards.0.model.layers.5.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
286
+ "wrapped_model.module_shards.0.model.layers.5.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
287
+ "wrapped_model.module_shards.0.model.layers.5.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
288
+ "wrapped_model.module_shards.0.model.layers.5.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
289
+ "wrapped_model.module_shards.0.model.layers.5.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
290
+ "wrapped_model.module_shards.0.model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
291
+ "wrapped_model.module_shards.0.model.layers.6.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
292
+ "wrapped_model.module_shards.0.model.layers.6.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
293
+ "wrapped_model.module_shards.0.model.layers.6.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
294
+ "wrapped_model.module_shards.0.model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
295
+ "wrapped_model.module_shards.0.model.layers.6.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
296
+ "wrapped_model.module_shards.0.model.layers.6.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
297
+ "wrapped_model.module_shards.0.model.layers.6.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
298
+ "wrapped_model.module_shards.0.model.layers.6.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
299
+ "wrapped_model.module_shards.0.model.layers.6.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
300
+ "wrapped_model.module_shards.0.model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
301
+ "wrapped_model.module_shards.0.model.layers.7.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
302
+ "wrapped_model.module_shards.0.model.layers.7.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
303
+ "wrapped_model.module_shards.0.model.layers.7.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
304
+ "wrapped_model.module_shards.0.model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
305
+ "wrapped_model.module_shards.0.model.layers.7.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
306
+ "wrapped_model.module_shards.0.model.layers.7.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
307
+ "wrapped_model.module_shards.0.model.layers.7.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
308
+ "wrapped_model.module_shards.0.model.layers.7.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
309
+ "wrapped_model.module_shards.0.model.layers.7.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
310
+ "wrapped_model.module_shards.0.model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
311
+ "wrapped_model.module_shards.0.model.layers.8.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
312
+ "wrapped_model.module_shards.0.model.layers.8.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
313
+ "wrapped_model.module_shards.0.model.layers.8.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
314
+ "wrapped_model.module_shards.0.model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
315
+ "wrapped_model.module_shards.0.model.layers.8.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
316
+ "wrapped_model.module_shards.0.model.layers.8.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
317
+ "wrapped_model.module_shards.0.model.layers.8.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
318
+ "wrapped_model.module_shards.0.model.layers.8.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
319
+ "wrapped_model.module_shards.0.model.layers.8.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
320
+ "wrapped_model.module_shards.0.model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
321
+ "wrapped_model.module_shards.0.model.layers.9.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
322
+ "wrapped_model.module_shards.0.model.layers.9.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
323
+ "wrapped_model.module_shards.0.model.layers.9.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
324
+ "wrapped_model.module_shards.0.model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
325
+ "wrapped_model.module_shards.0.model.layers.9.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
326
+ "wrapped_model.module_shards.0.model.layers.9.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
327
+ "wrapped_model.module_shards.0.model.layers.9.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
328
+ "wrapped_model.module_shards.0.model.layers.9.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
329
+ "wrapped_model.module_shards.0.model.layers.9.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
330
+ "wrapped_model.module_shards.0.model.norm.weight": "pytorch_model-00001-of-00002.bin",
331
+ "wrapped_model.module_shards.1.lm_head.tp_wrapped_module.weight": "pytorch_model-00002-of-00002.bin",
332
+ "wrapped_model.module_shards.1.model.embed_tokens.tp_wrapped_module.weight": "pytorch_model-00001-of-00002.bin",
333
+ "wrapped_model.module_shards.1.model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
334
+ "wrapped_model.module_shards.1.model.layers.0.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
335
+ "wrapped_model.module_shards.1.model.layers.0.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
336
+ "wrapped_model.module_shards.1.model.layers.0.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
337
+ "wrapped_model.module_shards.1.model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
338
+ "wrapped_model.module_shards.1.model.layers.0.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
339
+ "wrapped_model.module_shards.1.model.layers.0.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
340
+ "wrapped_model.module_shards.1.model.layers.0.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
341
+ "wrapped_model.module_shards.1.model.layers.0.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
342
+ "wrapped_model.module_shards.1.model.layers.0.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
343
+ "wrapped_model.module_shards.1.model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
344
+ "wrapped_model.module_shards.1.model.layers.1.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
345
+ "wrapped_model.module_shards.1.model.layers.1.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
346
+ "wrapped_model.module_shards.1.model.layers.1.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
347
+ "wrapped_model.module_shards.1.model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
348
+ "wrapped_model.module_shards.1.model.layers.1.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
349
+ "wrapped_model.module_shards.1.model.layers.1.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
350
+ "wrapped_model.module_shards.1.model.layers.1.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
351
+ "wrapped_model.module_shards.1.model.layers.1.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
352
+ "wrapped_model.module_shards.1.model.layers.1.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
353
+ "wrapped_model.module_shards.1.model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
354
+ "wrapped_model.module_shards.1.model.layers.10.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
355
+ "wrapped_model.module_shards.1.model.layers.10.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
356
+ "wrapped_model.module_shards.1.model.layers.10.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
357
+ "wrapped_model.module_shards.1.model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
358
+ "wrapped_model.module_shards.1.model.layers.10.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
359
+ "wrapped_model.module_shards.1.model.layers.10.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
360
+ "wrapped_model.module_shards.1.model.layers.10.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
361
+ "wrapped_model.module_shards.1.model.layers.10.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
362
+ "wrapped_model.module_shards.1.model.layers.10.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
363
+ "wrapped_model.module_shards.1.model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
364
+ "wrapped_model.module_shards.1.model.layers.11.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
365
+ "wrapped_model.module_shards.1.model.layers.11.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
366
+ "wrapped_model.module_shards.1.model.layers.11.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
367
+ "wrapped_model.module_shards.1.model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
368
+ "wrapped_model.module_shards.1.model.layers.11.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
369
+ "wrapped_model.module_shards.1.model.layers.11.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
370
+ "wrapped_model.module_shards.1.model.layers.11.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
371
+ "wrapped_model.module_shards.1.model.layers.11.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
372
+ "wrapped_model.module_shards.1.model.layers.11.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
373
+ "wrapped_model.module_shards.1.model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
374
+ "wrapped_model.module_shards.1.model.layers.12.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
375
+ "wrapped_model.module_shards.1.model.layers.12.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
376
+ "wrapped_model.module_shards.1.model.layers.12.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
377
+ "wrapped_model.module_shards.1.model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
378
+ "wrapped_model.module_shards.1.model.layers.12.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
379
+ "wrapped_model.module_shards.1.model.layers.12.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
380
+ "wrapped_model.module_shards.1.model.layers.12.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
381
+ "wrapped_model.module_shards.1.model.layers.12.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
382
+ "wrapped_model.module_shards.1.model.layers.12.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
383
+ "wrapped_model.module_shards.1.model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
384
+ "wrapped_model.module_shards.1.model.layers.13.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
385
+ "wrapped_model.module_shards.1.model.layers.13.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
386
+ "wrapped_model.module_shards.1.model.layers.13.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
387
+ "wrapped_model.module_shards.1.model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
388
+ "wrapped_model.module_shards.1.model.layers.13.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
389
+ "wrapped_model.module_shards.1.model.layers.13.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
390
+ "wrapped_model.module_shards.1.model.layers.13.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
391
+ "wrapped_model.module_shards.1.model.layers.13.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
392
+ "wrapped_model.module_shards.1.model.layers.13.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
393
+ "wrapped_model.module_shards.1.model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
394
+ "wrapped_model.module_shards.1.model.layers.14.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
395
+ "wrapped_model.module_shards.1.model.layers.14.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
396
+ "wrapped_model.module_shards.1.model.layers.14.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
397
+ "wrapped_model.module_shards.1.model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
398
+ "wrapped_model.module_shards.1.model.layers.14.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
399
+ "wrapped_model.module_shards.1.model.layers.14.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
400
+ "wrapped_model.module_shards.1.model.layers.14.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
401
+ "wrapped_model.module_shards.1.model.layers.14.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
402
+ "wrapped_model.module_shards.1.model.layers.14.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
403
+ "wrapped_model.module_shards.1.model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
404
+ "wrapped_model.module_shards.1.model.layers.15.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00002-of-00002.bin",
405
+ "wrapped_model.module_shards.1.model.layers.15.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
406
+ "wrapped_model.module_shards.1.model.layers.15.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00002-of-00002.bin",
407
+ "wrapped_model.module_shards.1.model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
408
+ "wrapped_model.module_shards.1.model.layers.15.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
409
+ "wrapped_model.module_shards.1.model.layers.15.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
410
+ "wrapped_model.module_shards.1.model.layers.15.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
411
+ "wrapped_model.module_shards.1.model.layers.15.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
412
+ "wrapped_model.module_shards.1.model.layers.15.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
413
+ "wrapped_model.module_shards.1.model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
414
+ "wrapped_model.module_shards.1.model.layers.16.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00002-of-00002.bin",
415
+ "wrapped_model.module_shards.1.model.layers.16.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
416
+ "wrapped_model.module_shards.1.model.layers.16.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00002-of-00002.bin",
417
+ "wrapped_model.module_shards.1.model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
418
+ "wrapped_model.module_shards.1.model.layers.16.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00002-of-00002.bin",
419
+ "wrapped_model.module_shards.1.model.layers.16.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00002-of-00002.bin",
420
+ "wrapped_model.module_shards.1.model.layers.16.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00002-of-00002.bin",
421
+ "wrapped_model.module_shards.1.model.layers.16.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
422
+ "wrapped_model.module_shards.1.model.layers.16.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00002-of-00002.bin",
423
+ "wrapped_model.module_shards.1.model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
424
+ "wrapped_model.module_shards.1.model.layers.17.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00002-of-00002.bin",
425
+ "wrapped_model.module_shards.1.model.layers.17.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
426
+ "wrapped_model.module_shards.1.model.layers.17.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00002-of-00002.bin",
427
+ "wrapped_model.module_shards.1.model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
428
+ "wrapped_model.module_shards.1.model.layers.17.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00002-of-00002.bin",
429
+ "wrapped_model.module_shards.1.model.layers.17.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00002-of-00002.bin",
430
+ "wrapped_model.module_shards.1.model.layers.17.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00002-of-00002.bin",
431
+ "wrapped_model.module_shards.1.model.layers.17.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
432
+ "wrapped_model.module_shards.1.model.layers.17.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00002-of-00002.bin",
433
+ "wrapped_model.module_shards.1.model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
434
+ "wrapped_model.module_shards.1.model.layers.18.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00002-of-00002.bin",
435
+ "wrapped_model.module_shards.1.model.layers.18.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
436
+ "wrapped_model.module_shards.1.model.layers.18.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00002-of-00002.bin",
437
+ "wrapped_model.module_shards.1.model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
438
+ "wrapped_model.module_shards.1.model.layers.18.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00002-of-00002.bin",
439
+ "wrapped_model.module_shards.1.model.layers.18.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00002-of-00002.bin",
440
+ "wrapped_model.module_shards.1.model.layers.18.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00002-of-00002.bin",
441
+ "wrapped_model.module_shards.1.model.layers.18.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
442
+ "wrapped_model.module_shards.1.model.layers.18.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00002-of-00002.bin",
443
+ "wrapped_model.module_shards.1.model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
444
+ "wrapped_model.module_shards.1.model.layers.19.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00002-of-00002.bin",
445
+ "wrapped_model.module_shards.1.model.layers.19.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
446
+ "wrapped_model.module_shards.1.model.layers.19.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00002-of-00002.bin",
447
+ "wrapped_model.module_shards.1.model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
448
+ "wrapped_model.module_shards.1.model.layers.19.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00002-of-00002.bin",
449
+ "wrapped_model.module_shards.1.model.layers.19.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00002-of-00002.bin",
450
+ "wrapped_model.module_shards.1.model.layers.19.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00002-of-00002.bin",
451
+ "wrapped_model.module_shards.1.model.layers.19.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
452
+ "wrapped_model.module_shards.1.model.layers.19.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00002-of-00002.bin",
453
+ "wrapped_model.module_shards.1.model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
454
+ "wrapped_model.module_shards.1.model.layers.2.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
455
+ "wrapped_model.module_shards.1.model.layers.2.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
456
+ "wrapped_model.module_shards.1.model.layers.2.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
457
+ "wrapped_model.module_shards.1.model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
458
+ "wrapped_model.module_shards.1.model.layers.2.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
459
+ "wrapped_model.module_shards.1.model.layers.2.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
460
+ "wrapped_model.module_shards.1.model.layers.2.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
461
+ "wrapped_model.module_shards.1.model.layers.2.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
462
+ "wrapped_model.module_shards.1.model.layers.2.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
463
+ "wrapped_model.module_shards.1.model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
464
+ "wrapped_model.module_shards.1.model.layers.20.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00002-of-00002.bin",
465
+ "wrapped_model.module_shards.1.model.layers.20.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
466
+ "wrapped_model.module_shards.1.model.layers.20.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00002-of-00002.bin",
467
+ "wrapped_model.module_shards.1.model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
468
+ "wrapped_model.module_shards.1.model.layers.20.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00002-of-00002.bin",
469
+ "wrapped_model.module_shards.1.model.layers.20.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00002-of-00002.bin",
470
+ "wrapped_model.module_shards.1.model.layers.20.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00002-of-00002.bin",
471
+ "wrapped_model.module_shards.1.model.layers.20.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
472
+ "wrapped_model.module_shards.1.model.layers.20.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00002-of-00002.bin",
473
+ "wrapped_model.module_shards.1.model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
474
+ "wrapped_model.module_shards.1.model.layers.21.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00002-of-00002.bin",
475
+ "wrapped_model.module_shards.1.model.layers.21.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
476
+ "wrapped_model.module_shards.1.model.layers.21.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00002-of-00002.bin",
477
+ "wrapped_model.module_shards.1.model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
478
+ "wrapped_model.module_shards.1.model.layers.21.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00002-of-00002.bin",
479
+ "wrapped_model.module_shards.1.model.layers.21.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00002-of-00002.bin",
480
+ "wrapped_model.module_shards.1.model.layers.21.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00002-of-00002.bin",
481
+ "wrapped_model.module_shards.1.model.layers.21.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
482
+ "wrapped_model.module_shards.1.model.layers.21.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00002-of-00002.bin",
483
+ "wrapped_model.module_shards.1.model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
484
+ "wrapped_model.module_shards.1.model.layers.22.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00002-of-00002.bin",
485
+ "wrapped_model.module_shards.1.model.layers.22.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
486
+ "wrapped_model.module_shards.1.model.layers.22.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00002-of-00002.bin",
487
+ "wrapped_model.module_shards.1.model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
488
+ "wrapped_model.module_shards.1.model.layers.22.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00002-of-00002.bin",
489
+ "wrapped_model.module_shards.1.model.layers.22.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00002-of-00002.bin",
490
+ "wrapped_model.module_shards.1.model.layers.22.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00002-of-00002.bin",
491
+ "wrapped_model.module_shards.1.model.layers.22.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
492
+ "wrapped_model.module_shards.1.model.layers.22.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00002-of-00002.bin",
493
+ "wrapped_model.module_shards.1.model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
494
+ "wrapped_model.module_shards.1.model.layers.23.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00002-of-00002.bin",
495
+ "wrapped_model.module_shards.1.model.layers.23.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
496
+ "wrapped_model.module_shards.1.model.layers.23.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00002-of-00002.bin",
497
+ "wrapped_model.module_shards.1.model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
498
+ "wrapped_model.module_shards.1.model.layers.23.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00002-of-00002.bin",
499
+ "wrapped_model.module_shards.1.model.layers.23.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00002-of-00002.bin",
500
+ "wrapped_model.module_shards.1.model.layers.23.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00002-of-00002.bin",
501
+ "wrapped_model.module_shards.1.model.layers.23.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
502
+ "wrapped_model.module_shards.1.model.layers.23.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00002-of-00002.bin",
503
+ "wrapped_model.module_shards.1.model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
504
+ "wrapped_model.module_shards.1.model.layers.24.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00002-of-00002.bin",
505
+ "wrapped_model.module_shards.1.model.layers.24.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
506
+ "wrapped_model.module_shards.1.model.layers.24.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00002-of-00002.bin",
507
+ "wrapped_model.module_shards.1.model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
508
+ "wrapped_model.module_shards.1.model.layers.24.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00002-of-00002.bin",
509
+ "wrapped_model.module_shards.1.model.layers.24.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00002-of-00002.bin",
510
+ "wrapped_model.module_shards.1.model.layers.24.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00002-of-00002.bin",
511
+ "wrapped_model.module_shards.1.model.layers.24.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
512
+ "wrapped_model.module_shards.1.model.layers.24.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00002-of-00002.bin",
513
+ "wrapped_model.module_shards.1.model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
514
+ "wrapped_model.module_shards.1.model.layers.25.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00002-of-00002.bin",
515
+ "wrapped_model.module_shards.1.model.layers.25.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
516
+ "wrapped_model.module_shards.1.model.layers.25.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00002-of-00002.bin",
517
+ "wrapped_model.module_shards.1.model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
518
+ "wrapped_model.module_shards.1.model.layers.25.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00002-of-00002.bin",
519
+ "wrapped_model.module_shards.1.model.layers.25.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00002-of-00002.bin",
520
+ "wrapped_model.module_shards.1.model.layers.25.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00002-of-00002.bin",
521
+ "wrapped_model.module_shards.1.model.layers.25.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
522
+ "wrapped_model.module_shards.1.model.layers.25.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00002-of-00002.bin",
523
+ "wrapped_model.module_shards.1.model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
524
+ "wrapped_model.module_shards.1.model.layers.26.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00002-of-00002.bin",
525
+ "wrapped_model.module_shards.1.model.layers.26.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
526
+ "wrapped_model.module_shards.1.model.layers.26.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00002-of-00002.bin",
527
+ "wrapped_model.module_shards.1.model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
528
+ "wrapped_model.module_shards.1.model.layers.26.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00002-of-00002.bin",
529
+ "wrapped_model.module_shards.1.model.layers.26.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00002-of-00002.bin",
530
+ "wrapped_model.module_shards.1.model.layers.26.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00002-of-00002.bin",
531
+ "wrapped_model.module_shards.1.model.layers.26.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
532
+ "wrapped_model.module_shards.1.model.layers.26.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00002-of-00002.bin",
533
+ "wrapped_model.module_shards.1.model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
534
+ "wrapped_model.module_shards.1.model.layers.27.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00002-of-00002.bin",
535
+ "wrapped_model.module_shards.1.model.layers.27.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
536
+ "wrapped_model.module_shards.1.model.layers.27.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00002-of-00002.bin",
537
+ "wrapped_model.module_shards.1.model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
538
+ "wrapped_model.module_shards.1.model.layers.27.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00002-of-00002.bin",
539
+ "wrapped_model.module_shards.1.model.layers.27.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00002-of-00002.bin",
540
+ "wrapped_model.module_shards.1.model.layers.27.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00002-of-00002.bin",
541
+ "wrapped_model.module_shards.1.model.layers.27.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
542
+ "wrapped_model.module_shards.1.model.layers.27.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00002-of-00002.bin",
543
+ "wrapped_model.module_shards.1.model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
544
+ "wrapped_model.module_shards.1.model.layers.28.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00002-of-00002.bin",
545
+ "wrapped_model.module_shards.1.model.layers.28.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
546
+ "wrapped_model.module_shards.1.model.layers.28.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00002-of-00002.bin",
547
+ "wrapped_model.module_shards.1.model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
548
+ "wrapped_model.module_shards.1.model.layers.28.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00002-of-00002.bin",
549
+ "wrapped_model.module_shards.1.model.layers.28.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00002-of-00002.bin",
550
+ "wrapped_model.module_shards.1.model.layers.28.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00002-of-00002.bin",
551
+ "wrapped_model.module_shards.1.model.layers.28.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
552
+ "wrapped_model.module_shards.1.model.layers.28.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00002-of-00002.bin",
553
+ "wrapped_model.module_shards.1.model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
554
+ "wrapped_model.module_shards.1.model.layers.29.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00002-of-00002.bin",
555
+ "wrapped_model.module_shards.1.model.layers.29.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
556
+ "wrapped_model.module_shards.1.model.layers.29.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00002-of-00002.bin",
557
+ "wrapped_model.module_shards.1.model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
558
+ "wrapped_model.module_shards.1.model.layers.29.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00002-of-00002.bin",
559
+ "wrapped_model.module_shards.1.model.layers.29.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00002-of-00002.bin",
560
+ "wrapped_model.module_shards.1.model.layers.29.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00002-of-00002.bin",
561
+ "wrapped_model.module_shards.1.model.layers.29.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
562
+ "wrapped_model.module_shards.1.model.layers.29.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00002-of-00002.bin",
563
+ "wrapped_model.module_shards.1.model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
564
+ "wrapped_model.module_shards.1.model.layers.3.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
565
+ "wrapped_model.module_shards.1.model.layers.3.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
566
+ "wrapped_model.module_shards.1.model.layers.3.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
567
+ "wrapped_model.module_shards.1.model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
568
+ "wrapped_model.module_shards.1.model.layers.3.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
569
+ "wrapped_model.module_shards.1.model.layers.3.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
570
+ "wrapped_model.module_shards.1.model.layers.3.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
571
+ "wrapped_model.module_shards.1.model.layers.3.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
572
+ "wrapped_model.module_shards.1.model.layers.3.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
573
+ "wrapped_model.module_shards.1.model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
574
+ "wrapped_model.module_shards.1.model.layers.30.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00002-of-00002.bin",
575
+ "wrapped_model.module_shards.1.model.layers.30.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
576
+ "wrapped_model.module_shards.1.model.layers.30.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00002-of-00002.bin",
577
+ "wrapped_model.module_shards.1.model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
578
+ "wrapped_model.module_shards.1.model.layers.30.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00002-of-00002.bin",
579
+ "wrapped_model.module_shards.1.model.layers.30.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00002-of-00002.bin",
580
+ "wrapped_model.module_shards.1.model.layers.30.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00002-of-00002.bin",
581
+ "wrapped_model.module_shards.1.model.layers.30.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
582
+ "wrapped_model.module_shards.1.model.layers.30.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00002-of-00002.bin",
583
+ "wrapped_model.module_shards.1.model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
584
+ "wrapped_model.module_shards.1.model.layers.31.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00002-of-00002.bin",
585
+ "wrapped_model.module_shards.1.model.layers.31.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
586
+ "wrapped_model.module_shards.1.model.layers.31.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00002-of-00002.bin",
587
+ "wrapped_model.module_shards.1.model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
588
+ "wrapped_model.module_shards.1.model.layers.31.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00002-of-00002.bin",
589
+ "wrapped_model.module_shards.1.model.layers.31.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00002-of-00002.bin",
590
+ "wrapped_model.module_shards.1.model.layers.31.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00002-of-00002.bin",
591
+ "wrapped_model.module_shards.1.model.layers.31.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
592
+ "wrapped_model.module_shards.1.model.layers.31.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00002-of-00002.bin",
593
+ "wrapped_model.module_shards.1.model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
594
+ "wrapped_model.module_shards.1.model.layers.4.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
595
+ "wrapped_model.module_shards.1.model.layers.4.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
596
+ "wrapped_model.module_shards.1.model.layers.4.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
597
+ "wrapped_model.module_shards.1.model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
598
+ "wrapped_model.module_shards.1.model.layers.4.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
599
+ "wrapped_model.module_shards.1.model.layers.4.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
600
+ "wrapped_model.module_shards.1.model.layers.4.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
601
+ "wrapped_model.module_shards.1.model.layers.4.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
602
+ "wrapped_model.module_shards.1.model.layers.4.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
603
+ "wrapped_model.module_shards.1.model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
604
+ "wrapped_model.module_shards.1.model.layers.5.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
605
+ "wrapped_model.module_shards.1.model.layers.5.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
606
+ "wrapped_model.module_shards.1.model.layers.5.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
607
+ "wrapped_model.module_shards.1.model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
608
+ "wrapped_model.module_shards.1.model.layers.5.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
609
+ "wrapped_model.module_shards.1.model.layers.5.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
610
+ "wrapped_model.module_shards.1.model.layers.5.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
611
+ "wrapped_model.module_shards.1.model.layers.5.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
612
+ "wrapped_model.module_shards.1.model.layers.5.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
613
+ "wrapped_model.module_shards.1.model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
614
+ "wrapped_model.module_shards.1.model.layers.6.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
615
+ "wrapped_model.module_shards.1.model.layers.6.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
616
+ "wrapped_model.module_shards.1.model.layers.6.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
617
+ "wrapped_model.module_shards.1.model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
618
+ "wrapped_model.module_shards.1.model.layers.6.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
619
+ "wrapped_model.module_shards.1.model.layers.6.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
620
+ "wrapped_model.module_shards.1.model.layers.6.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
621
+ "wrapped_model.module_shards.1.model.layers.6.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
622
+ "wrapped_model.module_shards.1.model.layers.6.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
623
+ "wrapped_model.module_shards.1.model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
624
+ "wrapped_model.module_shards.1.model.layers.7.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
625
+ "wrapped_model.module_shards.1.model.layers.7.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
626
+ "wrapped_model.module_shards.1.model.layers.7.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
627
+ "wrapped_model.module_shards.1.model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
628
+ "wrapped_model.module_shards.1.model.layers.7.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
629
+ "wrapped_model.module_shards.1.model.layers.7.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
630
+ "wrapped_model.module_shards.1.model.layers.7.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
631
+ "wrapped_model.module_shards.1.model.layers.7.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
632
+ "wrapped_model.module_shards.1.model.layers.7.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
633
+ "wrapped_model.module_shards.1.model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
634
+ "wrapped_model.module_shards.1.model.layers.8.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
635
+ "wrapped_model.module_shards.1.model.layers.8.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
636
+ "wrapped_model.module_shards.1.model.layers.8.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
637
+ "wrapped_model.module_shards.1.model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
638
+ "wrapped_model.module_shards.1.model.layers.8.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
639
+ "wrapped_model.module_shards.1.model.layers.8.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
640
+ "wrapped_model.module_shards.1.model.layers.8.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
641
+ "wrapped_model.module_shards.1.model.layers.8.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
642
+ "wrapped_model.module_shards.1.model.layers.8.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
643
+ "wrapped_model.module_shards.1.model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
644
+ "wrapped_model.module_shards.1.model.layers.9.mlp.tp_wrapped_module.down_proj.weight": "pytorch_model-00001-of-00002.bin",
645
+ "wrapped_model.module_shards.1.model.layers.9.mlp.tp_wrapped_module.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
646
+ "wrapped_model.module_shards.1.model.layers.9.mlp.tp_wrapped_module.up_proj.weight": "pytorch_model-00001-of-00002.bin",
647
+ "wrapped_model.module_shards.1.model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
648
+ "wrapped_model.module_shards.1.model.layers.9.self_attn.tp_wrapped_module.k_proj.weight": "pytorch_model-00001-of-00002.bin",
649
+ "wrapped_model.module_shards.1.model.layers.9.self_attn.tp_wrapped_module.o_proj.weight": "pytorch_model-00001-of-00002.bin",
650
+ "wrapped_model.module_shards.1.model.layers.9.self_attn.tp_wrapped_module.q_proj.weight": "pytorch_model-00001-of-00002.bin",
651
+ "wrapped_model.module_shards.1.model.layers.9.self_attn.tp_wrapped_module.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
652
+ "wrapped_model.module_shards.1.model.layers.9.self_attn.tp_wrapped_module.v_proj.weight": "pytorch_model-00001-of-00002.bin",
653
+ "wrapped_model.module_shards.1.model.norm.weight": "pytorch_model-00002-of-00002.bin"
654
+ }
655
+ }