Hugging Face's logo

TroyDoesAI
/
DoesPython

Safetensors
mixtral
Model card Files
xet
Community
TroyDoesAI commited on
Commit
bee839b
·
verified ·
1 Parent(s): 45a7732

Base Model of my 2 Grokked Models - AgentFlow for mermaid and AgentRAG for context obedience

Browse files
Files changed (11) hide show
  1. added_tokens.json +40 -0
  2. config.json +35 -0
  3. generation_config.json +6 -0
  4. model-00001-of-00003.safetensors +3 -0
  5. model-00002-of-00003.safetensors +3 -0
  6. model-00003-of-00003.safetensors +3 -0
  7. model.safetensors.index.json +400 -0
  8. special_tokens_map.json +33 -0
  9. tokenizer.json +0 -0
  10. tokenizer.model +3 -0
  11. tokenizer_config.json +353 -0
added_tokens.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|/code|>": 32014,
3
+ "<|/data|>": 32033,
4
+ "<|/inst|>": 32037,
5
+ "<|/query|>": 32031,
6
+ "<|/sys|>": 32035,
7
+ "<|assistant_mask|>": 32017,
8
+ "<|assistant|>": 32001,
9
+ "<|calc|>": 32012,
10
+ "<|code|>": 32013,
11
+ "<|continue|>": 32009,
12
+ "<|data|>": 32032,
13
+ "<|diff_marker|>": 32025,
14
+ "<|disc_sep|>": 32029,
15
+ "<|disc_start|>": 32028,
16
+ "<|disc_thread|><|query|>": 32030,
17
+ "<|endoftext|>": 32000,
18
+ "<|end|>": 32007,
19
+ "<|fim_middle|>": 32021,
20
+ "<|fim_prefix|>": 32020,
21
+ "<|fim_suffix|>": 32022,
22
+ "<|function_call|>": 32005,
23
+ "<|function_list|>": 32011,
24
+ "<|function_output|>": 32003,
25
+ "<|ghissue|>": 32026,
26
+ "<|ghreview|>": 32027,
27
+ "<|inst|>": 32036,
28
+ "<|ipynb_marker|>": 32024,
29
+ "<|message|>": 32019,
30
+ "<|meta_start|>": 32023,
31
+ "<|raw|>": 32008,
32
+ "<|resource|>": 32016,
33
+ "<|start|>": 32018,
34
+ "<|step|>": 32002,
35
+ "<|summary|>": 32015,
36
+ "<|system|>": 32006,
37
+ "<|sys|>": 32034,
38
+ "<|tag|>": 32004,
39
+ "<|user|>": 32010
40
+ }
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": ".\\AgentRAG",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_bias": true,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 32000,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 3072,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 8192,
14
+ "max_position_embeddings": 32768,
15
+ "mlp_bias": false,
16
+ "model_type": "mixtral",
17
+ "num_attention_heads": 32,
18
+ "num_experts_per_tok": 2,
19
+ "num_hidden_layers": 30,
20
+ "num_key_value_heads": 32,
21
+ "num_local_experts": 2,
22
+ "output_router_logits": false,
23
+ "pretraining_tp": 1,
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_scaling": null,
26
+ "rope_theta": 10000.0,
27
+ "router_aux_loss_coef": 0.001,
28
+ "router_jitter_noise": 0.0,
29
+ "sliding_window": 16384,
30
+ "tie_word_embeddings": false,
31
+ "torch_dtype": "bfloat16",
32
+ "transformers_version": "4.44.0",
33
+ "use_cache": true,
34
+ "vocab_size": 32064
35
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 32000,
5
+ "transformers_version": "4.44.0"
6
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96d553a8365f780137bd02fa4c46d434d05bb06416bcc32fbe8f2f1234f9bf9f
3
+ size 4953669424
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:076bc0fadd38e2004f934381c5e7d69b1eefe7f4167bf198e34b61cf4e2d9a39
3
+ size 4958007856
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16d7ccbf2f68a1000ac2bd46119a1815ea379eceb697e642e15a38bc75304f39
3
+ size 1807737792
model.safetensors.index.json ADDED
@@ -0,0 +1,400 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 11719366656
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00003-of-00003.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors",
26
+ "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors",
27
+ "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00003.safetensors",
28
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
29
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
30
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
31
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
32
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
33
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
34
+ "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors",
35
+ "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors",
36
+ "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors",
37
+ "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors",
38
+ "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors",
39
+ "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors",
40
+ "model.layers.10.block_sparse_moe.gate.weight": "model-00001-of-00003.safetensors",
41
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
42
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
43
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
44
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
45
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
46
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
47
+ "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors",
48
+ "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors",
49
+ "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors",
50
+ "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors",
51
+ "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors",
52
+ "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors",
53
+ "model.layers.11.block_sparse_moe.gate.weight": "model-00001-of-00003.safetensors",
54
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
55
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
56
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
57
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
58
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
59
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
60
+ "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors",
61
+ "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors",
62
+ "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors",
63
+ "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors",
64
+ "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors",
65
+ "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors",
66
+ "model.layers.12.block_sparse_moe.gate.weight": "model-00001-of-00003.safetensors",
67
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
68
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
69
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
70
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
71
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
72
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
73
+ "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors",
77
+ "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors",
79
+ "model.layers.13.block_sparse_moe.gate.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
83
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors",
89
+ "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.14.block_sparse_moe.gate.weight": "model-00002-of-00003.safetensors",
93
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.15.block_sparse_moe.gate.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors",
116
+ "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors",
117
+ "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors",
118
+ "model.layers.16.block_sparse_moe.gate.weight": "model-00002-of-00003.safetensors",
119
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
120
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
121
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
122
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
123
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
124
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
125
+ "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors",
126
+ "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors",
129
+ "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors",
130
+ "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.17.block_sparse_moe.gate.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
134
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
135
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
136
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
137
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
138
+ "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors",
139
+ "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors",
140
+ "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors",
141
+ "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors",
142
+ "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors",
143
+ "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors",
144
+ "model.layers.18.block_sparse_moe.gate.weight": "model-00002-of-00003.safetensors",
145
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
146
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
147
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
148
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
149
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
150
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
151
+ "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors",
152
+ "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors",
153
+ "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors",
154
+ "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors",
155
+ "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors",
156
+ "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors",
157
+ "model.layers.19.block_sparse_moe.gate.weight": "model-00002-of-00003.safetensors",
158
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
159
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
160
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
161
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
162
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
163
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
164
+ "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors",
165
+ "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors",
166
+ "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors",
167
+ "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors",
168
+ "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors",
169
+ "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors",
170
+ "model.layers.2.block_sparse_moe.gate.weight": "model-00001-of-00003.safetensors",
171
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
172
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
173
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
174
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
175
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
176
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
177
+ "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors",
178
+ "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors",
179
+ "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors",
180
+ "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors",
181
+ "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors",
182
+ "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors",
183
+ "model.layers.20.block_sparse_moe.gate.weight": "model-00002-of-00003.safetensors",
184
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
185
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
186
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
187
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
188
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
189
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
190
+ "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors",
191
+ "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors",
192
+ "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors",
193
+ "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors",
194
+ "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors",
195
+ "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors",
196
+ "model.layers.21.block_sparse_moe.gate.weight": "model-00002-of-00003.safetensors",
197
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
198
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
199
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
200
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
201
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
202
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
203
+ "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors",
204
+ "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors",
205
+ "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors",
206
+ "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors",
207
+ "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors",
208
+ "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors",
209
+ "model.layers.22.block_sparse_moe.gate.weight": "model-00002-of-00003.safetensors",
210
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
211
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
212
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
213
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
214
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
215
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
216
+ "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors",
217
+ "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors",
218
+ "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors",
219
+ "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors",
220
+ "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors",
221
+ "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors",
222
+ "model.layers.23.block_sparse_moe.gate.weight": "model-00002-of-00003.safetensors",
223
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
224
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
225
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
226
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
227
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
228
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
229
+ "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors",
230
+ "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors",
231
+ "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors",
232
+ "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors",
233
+ "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors",
234
+ "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00003.safetensors",
235
+ "model.layers.24.block_sparse_moe.gate.weight": "model-00002-of-00003.safetensors",
236
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
237
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
238
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
239
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
240
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
241
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
242
+ "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors",
243
+ "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors",
244
+ "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00003.safetensors",
245
+ "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors",
246
+ "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00003.safetensors",
247
+ "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00003.safetensors",
248
+ "model.layers.25.block_sparse_moe.gate.weight": "model-00002-of-00003.safetensors",
249
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
250
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
251
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
252
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
253
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
254
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
255
+ "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors",
256
+ "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00003.safetensors",
257
+ "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00003.safetensors",
258
+ "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors",
259
+ "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00003.safetensors",
260
+ "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00003.safetensors",
261
+ "model.layers.26.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors",
262
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
263
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
264
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
265
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
266
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
267
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
268
+ "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors",
269
+ "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00003.safetensors",
270
+ "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00003.safetensors",
271
+ "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors",
272
+ "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00003.safetensors",
273
+ "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00003.safetensors",
274
+ "model.layers.27.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors",
275
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
276
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
277
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
278
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
279
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
280
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
281
+ "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors",
282
+ "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00003.safetensors",
283
+ "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00003.safetensors",
284
+ "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors",
285
+ "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00003.safetensors",
286
+ "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00003.safetensors",
287
+ "model.layers.28.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors",
288
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
289
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
290
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
291
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
292
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
293
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
294
+ "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors",
295
+ "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00003.safetensors",
296
+ "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00003.safetensors",
297
+ "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors",
298
+ "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00003.safetensors",
299
+ "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00003.safetensors",
300
+ "model.layers.29.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors",
301
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
302
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
303
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
304
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
305
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
306
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
307
+ "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors",
308
+ "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors",
309
+ "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors",
310
+ "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors",
311
+ "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors",
312
+ "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors",
313
+ "model.layers.3.block_sparse_moe.gate.weight": "model-00001-of-00003.safetensors",
314
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
315
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
316
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
317
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
318
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
319
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
320
+ "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors",
321
+ "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors",
322
+ "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors",
323
+ "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors",
324
+ "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors",
325
+ "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors",
326
+ "model.layers.4.block_sparse_moe.gate.weight": "model-00001-of-00003.safetensors",
327
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
328
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
329
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
330
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
331
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
332
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
333
+ "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors",
334
+ "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors",
335
+ "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors",
336
+ "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors",
337
+ "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors",
338
+ "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors",
339
+ "model.layers.5.block_sparse_moe.gate.weight": "model-00001-of-00003.safetensors",
340
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
341
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
342
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
343
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
344
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
345
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
346
+ "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors",
347
+ "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors",
348
+ "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors",
349
+ "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors",
350
+ "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors",
351
+ "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors",
352
+ "model.layers.6.block_sparse_moe.gate.weight": "model-00001-of-00003.safetensors",
353
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
354
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
355
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
356
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
357
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
358
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
359
+ "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors",
360
+ "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors",
361
+ "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors",
362
+ "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors",
363
+ "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors",
364
+ "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors",
365
+ "model.layers.7.block_sparse_moe.gate.weight": "model-00001-of-00003.safetensors",
366
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
367
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
368
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
369
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
370
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
371
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
372
+ "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors",
373
+ "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors",
374
+ "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors",
375
+ "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors",
376
+ "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors",
377
+ "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors",
378
+ "model.layers.8.block_sparse_moe.gate.weight": "model-00001-of-00003.safetensors",
379
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
380
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
381
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
382
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
383
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
384
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
385
+ "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00003.safetensors",
386
+ "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors",
387
+ "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors",
388
+ "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00003.safetensors",
389
+ "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors",
390
+ "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors",
391
+ "model.layers.9.block_sparse_moe.gate.weight": "model-00001-of-00003.safetensors",
392
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
393
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
394
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
395
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
396
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
397
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
398
+ "model.norm.weight": "model-00003-of-00003.safetensors"
399
+ }
400
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|/inst|>"
4
+ ],
5
+ "bos_token": {
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "eos_token": {
13
+ "content": "<|end|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": true,
17
+ "single_word": false
18
+ },
19
+ "pad_token": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "unk_token": {
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,353 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": true,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "32000": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|assistant|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": true,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "<|step|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": true,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "32003": {
55
+ "content": "<|function_output|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": true,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "32004": {
63
+ "content": "<|tag|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": true,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "32005": {
71
+ "content": "<|function_call|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": true,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "32006": {
79
+ "content": "<|system|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": true,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "32007": {
87
+ "content": "<|end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": true,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "32008": {
95
+ "content": "<|raw|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": true,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "32009": {
103
+ "content": "<|continue|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": true,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "32010": {
111
+ "content": "<|user|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": true,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "32011": {
119
+ "content": "<|function_list|>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": true,
123
+ "single_word": false,
124
+ "special": true
125
+ },
126
+ "32012": {
127
+ "content": "<|calc|>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": true,
131
+ "single_word": false,
132
+ "special": true
133
+ },
134
+ "32013": {
135
+ "content": "<|code|>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": true,
139
+ "single_word": false,
140
+ "special": true
141
+ },
142
+ "32014": {
143
+ "content": "<|/code|>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": true,
147
+ "single_word": false,
148
+ "special": true
149
+ },
150
+ "32015": {
151
+ "content": "<|summary|>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": true,
155
+ "single_word": false,
156
+ "special": true
157
+ },
158
+ "32016": {
159
+ "content": "<|resource|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": true,
163
+ "single_word": false,
164
+ "special": true
165
+ },
166
+ "32017": {
167
+ "content": "<|assistant_mask|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": true,
171
+ "single_word": false,
172
+ "special": true
173
+ },
174
+ "32018": {
175
+ "content": "<|start|>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": true,
179
+ "single_word": false,
180
+ "special": true
181
+ },
182
+ "32019": {
183
+ "content": "<|message|>",
184
+ "lstrip": false,
185
+ "normalized": false,
186
+ "rstrip": true,
187
+ "single_word": false,
188
+ "special": true
189
+ },
190
+ "32020": {
191
+ "content": "<|fim_prefix|>",
192
+ "lstrip": false,
193
+ "normalized": false,
194
+ "rstrip": true,
195
+ "single_word": false,
196
+ "special": true
197
+ },
198
+ "32021": {
199
+ "content": "<|fim_middle|>",
200
+ "lstrip": false,
201
+ "normalized": false,
202
+ "rstrip": true,
203
+ "single_word": false,
204
+ "special": true
205
+ },
206
+ "32022": {
207
+ "content": "<|fim_suffix|>",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": true,
211
+ "single_word": false,
212
+ "special": true
213
+ },
214
+ "32023": {
215
+ "content": "<|meta_start|>",
216
+ "lstrip": false,
217
+ "normalized": false,
218
+ "rstrip": true,
219
+ "single_word": false,
220
+ "special": true
221
+ },
222
+ "32024": {
223
+ "content": "<|ipynb_marker|>",
224
+ "lstrip": false,
225
+ "normalized": false,
226
+ "rstrip": true,
227
+ "single_word": false,
228
+ "special": true
229
+ },
230
+ "32025": {
231
+ "content": "<|diff_marker|>",
232
+ "lstrip": false,
233
+ "normalized": false,
234
+ "rstrip": true,
235
+ "single_word": false,
236
+ "special": true
237
+ },
238
+ "32026": {
239
+ "content": "<|ghissue|>",
240
+ "lstrip": false,
241
+ "normalized": false,
242
+ "rstrip": true,
243
+ "single_word": false,
244
+ "special": true
245
+ },
246
+ "32027": {
247
+ "content": "<|ghreview|>",
248
+ "lstrip": false,
249
+ "normalized": false,
250
+ "rstrip": true,
251
+ "single_word": false,
252
+ "special": true
253
+ },
254
+ "32028": {
255
+ "content": "<|disc_start|>",
256
+ "lstrip": false,
257
+ "normalized": false,
258
+ "rstrip": true,
259
+ "single_word": false,
260
+ "special": true
261
+ },
262
+ "32029": {
263
+ "content": "<|disc_sep|>",
264
+ "lstrip": false,
265
+ "normalized": false,
266
+ "rstrip": true,
267
+ "single_word": false,
268
+ "special": true
269
+ },
270
+ "32030": {
271
+ "content": "<|disc_thread|><|query|>",
272
+ "lstrip": false,
273
+ "normalized": false,
274
+ "rstrip": true,
275
+ "single_word": false,
276
+ "special": true
277
+ },
278
+ "32031": {
279
+ "content": "<|/query|>",
280
+ "lstrip": false,
281
+ "normalized": false,
282
+ "rstrip": true,
283
+ "single_word": false,
284
+ "special": true
285
+ },
286
+ "32032": {
287
+ "content": "<|data|>",
288
+ "lstrip": false,
289
+ "normalized": false,
290
+ "rstrip": true,
291
+ "single_word": false,
292
+ "special": true
293
+ },
294
+ "32033": {
295
+ "content": "<|/data|>",
296
+ "lstrip": false,
297
+ "normalized": false,
298
+ "rstrip": true,
299
+ "single_word": false,
300
+ "special": true
301
+ },
302
+ "32034": {
303
+ "content": "<|sys|>",
304
+ "lstrip": false,
305
+ "normalized": false,
306
+ "rstrip": true,
307
+ "single_word": false,
308
+ "special": true
309
+ },
310
+ "32035": {
311
+ "content": "<|/sys|>",
312
+ "lstrip": false,
313
+ "normalized": false,
314
+ "rstrip": true,
315
+ "single_word": false,
316
+ "special": true
317
+ },
318
+ "32036": {
319
+ "content": "<|inst|>",
320
+ "lstrip": false,
321
+ "normalized": false,
322
+ "rstrip": true,
323
+ "single_word": false,
324
+ "special": true
325
+ },
326
+ "32037": {
327
+ "content": "<|/inst|>",
328
+ "lstrip": false,
329
+ "normalized": false,
330
+ "rstrip": true,
331
+ "single_word": false,
332
+ "special": true
333
+ }
334
+ },
335
+ "additional_special_tokens": [
336
+ "<|/inst|>"
337
+ ],
338
+ "bos_token": "<s>",
339
+ "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|' + message['role'] + '|>' + '\n' + message['content'] + '<|end|>\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
340
+ "clean_up_tokenization_spaces": false,
341
+ "eos_token": "<|end|>",
342
+ "legacy": false,
343
+ "max_length": null,
344
+ "model_max_length": 4096,
345
+ "pad_to_multiple_of": null,
346
+ "pad_token": "<s>",
347
+ "pad_token_type_id": 0,
348
+ "padding_side": "left",
349
+ "sp_model_kwargs": {},
350
+ "tokenizer_class": "LlamaTokenizer",
351
+ "unk_token": "<unk>",
352
+ "use_default_system_prompt": false
353
+ }