Hugging Face's logo

weblab-GENIAC
/
team_hatakeyama_phase1

Text Generation
Transformers
Safetensors
mixtral
text-generation-inference
Inference Endpoints
Model card Files Community
kanhatakeyama commited on
Commit
8b5ed4f
•
1 Parent(s): 8761dd2

Upload MixtralForCausalLM

Browse files
Files changed (9) hide show
  1. config.json +38 -0
  2. generation_config.json +8 -0
  3. model-00001-of-00006.safetensors +3 -0
  4. model-00002-of-00006.safetensors +3 -0
  5. model-00003-of-00006.safetensors +3 -0
  6. model-00004-of-00006.safetensors +3 -0
  7. model-00005-of-00006.safetensors +3 -0
  8. model-00006-of-00006.safetensors +3 -0
  9. model.safetensors.index.json +426 -0
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "../X_merge/merged_models/0526_2x8b_w_and_wo_halci_epoch3/",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 8192,
15
+ "max_sequence_length": 8192,
16
+ "mlp_bias": false,
17
+ "model_type": "mixtral",
18
+ "num_attention_heads": 32,
19
+ "num_experts_per_tok": 2,
20
+ "num_hidden_layers": 32,
21
+ "num_key_value_heads": 8,
22
+ "num_local_experts": 2,
23
+ "output_router_logits": false,
24
+ "pad_token_id": 0,
25
+ "pretraining_tp": 1,
26
+ "repetition_penalty": 1.15,
27
+ "rms_norm_eps": 1e-05,
28
+ "rope_scaling": null,
29
+ "rope_theta": 500000.0,
30
+ "router_aux_loss_coef": 0.001,
31
+ "router_jitter_noise": 0.0,
32
+ "sliding_window": null,
33
+ "tie_word_embeddings": false,
34
+ "torch_dtype": "bfloat16",
35
+ "transformers_version": "4.41.0",
36
+ "use_cache": true,
37
+ "vocab_size": 65024
38
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "repetition_penalty": 1.15,
7
+ "transformers_version": "4.41.0"
8
+ }
model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1d36c2b89e68e0d326803bf1a4a4244d422a3bdae708b3f1f06ac9afb5f9ee3
3
+ size 4911719336
model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:894131c9e96f13e00e765d26024e44ecb57662b9cf000ceff07807017ae2993f
3
+ size 4966262456
model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75e4e92991fd8a68e68627fcfbf8d4ed59c1003a3050d564c7ee2e021f7bb4c5
3
+ size 4932741544
model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb71f83855057dae00b503083f0f464a769f3c30aec2404503df2af8bbbd1da7
3
+ size 4966262528
model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9943d913794d119617ac4ea97f482723103be1bfba3195e2d2a59979d78dc18
3
+ size 4966262528
model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8999037e45dfba0b5ec276bc2cc7b6a4f55ac2ac89bb9f4f460a0e4958062a0
3
+ size 1556146448
model.safetensors.index.json ADDED
@@ -0,0 +1,426 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 26299342848
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00006-of-00006.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
8
+ "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors",
9
+ "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors",
10
+ "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors",
11
+ "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors",
12
+ "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors",
13
+ "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors",
14
+ "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00006.safetensors",
15
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
16
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
17
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
18
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
19
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
20
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
21
+ "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors",
22
+ "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors",
23
+ "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors",
24
+ "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors",
25
+ "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors",
26
+ "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors",
27
+ "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00006.safetensors",
28
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
29
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
30
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
31
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
32
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
33
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
34
+ "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
35
+ "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors",
36
+ "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
37
+ "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
38
+ "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
39
+ "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors",
40
+ "model.layers.10.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
41
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
42
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
43
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
44
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
45
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
46
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
47
+ "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
48
+ "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors",
49
+ "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
50
+ "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
51
+ "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
52
+ "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors",
53
+ "model.layers.11.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
54
+ "model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
55
+ "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
56
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
57
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
58
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
59
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
60
+ "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors",
61
+ "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors",
62
+ "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors",
63
+ "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors",
64
+ "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors",
65
+ "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors",
66
+ "model.layers.12.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
67
+ "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
68
+ "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
69
+ "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
70
+ "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
71
+ "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
72
+ "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
73
+ "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors",
74
+ "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors",
75
+ "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors",
76
+ "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors",
77
+ "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors",
78
+ "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors",
79
+ "model.layers.13.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
80
+ "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
81
+ "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
82
+ "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
83
+ "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
84
+ "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
85
+ "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
86
+ "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors",
87
+ "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors",
88
+ "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors",
89
+ "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors",
90
+ "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors",
91
+ "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors",
92
+ "model.layers.14.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
93
+ "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
94
+ "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
95
+ "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
96
+ "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
97
+ "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
98
+ "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
99
+ "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors",
100
+ "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors",
101
+ "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors",
102
+ "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors",
103
+ "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors",
104
+ "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors",
105
+ "model.layers.15.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
106
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
107
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
108
+ "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
109
+ "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
110
+ "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
111
+ "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
112
+ "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors",
113
+ "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors",
114
+ "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors",
115
+ "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors",
116
+ "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors",
117
+ "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors",
118
+ "model.layers.16.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
119
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
120
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
121
+ "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
122
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
123
+ "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
124
+ "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
125
+ "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors",
126
+ "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors",
127
+ "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors",
128
+ "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors",
129
+ "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors",
130
+ "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors",
131
+ "model.layers.17.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
132
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
133
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
134
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
135
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
136
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
137
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
138
+ "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors",
139
+ "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors",
140
+ "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors",
141
+ "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors",
142
+ "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors",
143
+ "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors",
144
+ "model.layers.18.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
145
+ "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
146
+ "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
147
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
148
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
149
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
150
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
151
+ "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors",
152
+ "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors",
153
+ "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors",
154
+ "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors",
155
+ "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors",
156
+ "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors",
157
+ "model.layers.19.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors",
158
+ "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
159
+ "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
160
+ "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
161
+ "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
162
+ "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
163
+ "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
164
+ "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors",
165
+ "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors",
166
+ "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors",
167
+ "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors",
168
+ "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors",
169
+ "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors",
170
+ "model.layers.2.block_sparse_moe.gate.weight": "model-00001-of-00006.safetensors",
171
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
172
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
173
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
174
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
175
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
176
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
177
+ "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors",
178
+ "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors",
179
+ "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors",
180
+ "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors",
181
+ "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors",
182
+ "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors",
183
+ "model.layers.20.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors",
184
+ "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
185
+ "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
186
+ "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
187
+ "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
188
+ "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
189
+ "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
190
+ "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors",
191
+ "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors",
192
+ "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors",
193
+ "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors",
194
+ "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors",
195
+ "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors",
196
+ "model.layers.21.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors",
197
+ "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
198
+ "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
199
+ "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
200
+ "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
201
+ "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
202
+ "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
203
+ "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors",
204
+ "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors",
205
+ "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors",
206
+ "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors",
207
+ "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors",
208
+ "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors",
209
+ "model.layers.22.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors",
210
+ "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
211
+ "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
212
+ "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
213
+ "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
214
+ "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
215
+ "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
216
+ "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors",
217
+ "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors",
218
+ "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors",
219
+ "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors",
220
+ "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors",
221
+ "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors",
222
+ "model.layers.23.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors",
223
+ "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
224
+ "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
225
+ "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
226
+ "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
227
+ "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
228
+ "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
229
+ "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors",
230
+ "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors",
231
+ "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
232
+ "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
233
+ "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
234
+ "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
235
+ "model.layers.24.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors",
236
+ "model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
237
+ "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
238
+ "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
239
+ "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
240
+ "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
241
+ "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
242
+ "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors",
243
+ "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors",
244
+ "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
245
+ "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
246
+ "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
247
+ "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
248
+ "model.layers.25.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
249
+ "model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
250
+ "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
251
+ "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
252
+ "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
253
+ "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
254
+ "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
255
+ "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors",
256
+ "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors",
257
+ "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
258
+ "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
259
+ "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
260
+ "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
261
+ "model.layers.26.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
262
+ "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
263
+ "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
264
+ "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
265
+ "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
266
+ "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
267
+ "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
268
+ "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors",
269
+ "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors",
270
+ "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
271
+ "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
272
+ "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
273
+ "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
274
+ "model.layers.27.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
275
+ "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
276
+ "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
277
+ "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
278
+ "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
279
+ "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
280
+ "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
281
+ "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors",
282
+ "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors",
283
+ "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
284
+ "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
285
+ "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
286
+ "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
287
+ "model.layers.28.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
288
+ "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
289
+ "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
290
+ "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
291
+ "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
292
+ "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
293
+ "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
294
+ "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors",
295
+ "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors",
296
+ "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
297
+ "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
298
+ "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
299
+ "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
300
+ "model.layers.29.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
301
+ "model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors",
302
+ "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
303
+ "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
304
+ "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
305
+ "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
306
+ "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
307
+ "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors",
308
+ "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors",
309
+ "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors",
310
+ "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors",
311
+ "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors",
312
+ "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors",
313
+ "model.layers.3.block_sparse_moe.gate.weight": "model-00001-of-00006.safetensors",
314
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
315
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
316
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
317
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
318
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
319
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
320
+ "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors",
321
+ "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors",
322
+ "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
323
+ "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
324
+ "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00006.safetensors",
325
+ "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00006.safetensors",
326
+ "model.layers.30.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
327
+ "model.layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
328
+ "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
329
+ "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
330
+ "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
331
+ "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
332
+ "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
333
+ "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00006.safetensors",
334
+ "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00006.safetensors",
335
+ "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00006.safetensors",
336
+ "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00006.safetensors",
337
+ "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00006.safetensors",
338
+ "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00006.safetensors",
339
+ "model.layers.31.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors",
340
+ "model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
341
+ "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
342
+ "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
343
+ "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
344
+ "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
345
+ "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
346
+ "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors",
347
+ "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors",
348
+ "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors",
349
+ "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors",
350
+ "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors",
351
+ "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors",
352
+ "model.layers.4.block_sparse_moe.gate.weight": "model-00001-of-00006.safetensors",
353
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
354
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
355
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
356
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
357
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
358
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
359
+ "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors",
360
+ "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors",
361
+ "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors",
362
+ "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
363
+ "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
364
+ "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors",
365
+ "model.layers.5.block_sparse_moe.gate.weight": "model-00001-of-00006.safetensors",
366
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
367
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
368
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
369
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
370
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
371
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
372
+ "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
373
+ "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors",
374
+ "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
375
+ "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
376
+ "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
377
+ "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors",
378
+ "model.layers.6.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
379
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
380
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
381
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
382
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
383
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
384
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
385
+ "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
386
+ "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors",
387
+ "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
388
+ "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
389
+ "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
390
+ "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors",
391
+ "model.layers.7.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
392
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
393
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
394
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
395
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
396
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
397
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
398
+ "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
399
+ "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors",
400
+ "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
401
+ "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
402
+ "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
403
+ "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors",
404
+ "model.layers.8.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
405
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
406
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
407
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
408
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
409
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
410
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
411
+ "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
412
+ "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors",
413
+ "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
414
+ "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
415
+ "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
416
+ "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors",
417
+ "model.layers.9.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
418
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
419
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
420
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
421
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
422
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
423
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
424
+ "model.norm.weight": "model-00006-of-00006.safetensors"
425
+ }
426
+ }