Hugging Face's logo

Motif-Technologies
/
Motif-2.6b-v1.1-LC

Text Generation
Safetensors
English
Korean
Motif
text-generation-inference
conversational
motif
custom_code
Model card Files
xet
Community
5
eunhwanpark-motiftech commited on
Commit
6908d73
·
verified ·
1 Parent(s): 54900e2

Upload 8 files

Browse files
Files changed (9) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +127 -0
  3. merges.txt +0 -0
  4. model-00003-of-00003.safetensors +3 -0
  5. model.safetensors.index.json +521 -0
  6. special_tokens_map.json +30 -0
  7. tokenizer.json +3 -0
  8. tokenizer_config.json +1027 -0
  9. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,127 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 219406,
3
+ "<think>": 219404,
4
+ "<|assistant|>": 219402,
5
+ "<|beginoftext|>": 219396,
6
+ "<|dummy_id_100|>": 219505,
7
+ "<|dummy_id_101|>": 219506,
8
+ "<|dummy_id_102|>": 219507,
9
+ "<|dummy_id_103|>": 219508,
10
+ "<|dummy_id_104|>": 219509,
11
+ "<|dummy_id_105|>": 219510,
12
+ "<|dummy_id_106|>": 219511,
13
+ "<|dummy_id_107|>": 219512,
14
+ "<|dummy_id_108|>": 219513,
15
+ "<|dummy_id_109|>": 219514,
16
+ "<|dummy_id_10|>": 219414,
17
+ "<|dummy_id_110|>": 219515,
18
+ "<|dummy_id_111|>": 219516,
19
+ "<|dummy_id_112|>": 219517,
20
+ "<|dummy_id_113|>": 219518,
21
+ "<|dummy_id_114|>": 219519,
22
+ "<|dummy_id_11|>": 219415,
23
+ "<|dummy_id_12|>": 219417,
24
+ "<|dummy_id_13|>": 219418,
25
+ "<|dummy_id_14|>": 219419,
26
+ "<|dummy_id_15|>": 219420,
27
+ "<|dummy_id_16|>": 219421,
28
+ "<|dummy_id_17|>": 219422,
29
+ "<|dummy_id_18|>": 219423,
30
+ "<|dummy_id_19|>": 219424,
31
+ "<|dummy_id_20|>": 219425,
32
+ "<|dummy_id_21|>": 219426,
33
+ "<|dummy_id_22|>": 219427,
34
+ "<|dummy_id_23|>": 219428,
35
+ "<|dummy_id_24|>": 219429,
36
+ "<|dummy_id_25|>": 219430,
37
+ "<|dummy_id_26|>": 219431,
38
+ "<|dummy_id_27|>": 219432,
39
+ "<|dummy_id_28|>": 219433,
40
+ "<|dummy_id_29|>": 219434,
41
+ "<|dummy_id_30|>": 219435,
42
+ "<|dummy_id_31|>": 219436,
43
+ "<|dummy_id_32|>": 219437,
44
+ "<|dummy_id_33|>": 219438,
45
+ "<|dummy_id_34|>": 219439,
46
+ "<|dummy_id_35|>": 219440,
47
+ "<|dummy_id_36|>": 219441,
48
+ "<|dummy_id_37|>": 219442,
49
+ "<|dummy_id_38|>": 219443,
50
+ "<|dummy_id_39|>": 219444,
51
+ "<|dummy_id_3|>": 219407,
52
+ "<|dummy_id_40|>": 219445,
53
+ "<|dummy_id_41|>": 219446,
54
+ "<|dummy_id_42|>": 219447,
55
+ "<|dummy_id_43|>": 219448,
56
+ "<|dummy_id_44|>": 219449,
57
+ "<|dummy_id_45|>": 219450,
58
+ "<|dummy_id_46|>": 219451,
59
+ "<|dummy_id_47|>": 219452,
60
+ "<|dummy_id_48|>": 219453,
61
+ "<|dummy_id_49|>": 219454,
62
+ "<|dummy_id_4|>": 219408,
63
+ "<|dummy_id_50|>": 219455,
64
+ "<|dummy_id_51|>": 219456,
65
+ "<|dummy_id_52|>": 219457,
66
+ "<|dummy_id_53|>": 219458,
67
+ "<|dummy_id_54|>": 219459,
68
+ "<|dummy_id_55|>": 219460,
69
+ "<|dummy_id_56|>": 219461,
70
+ "<|dummy_id_57|>": 219462,
71
+ "<|dummy_id_58|>": 219463,
72
+ "<|dummy_id_59|>": 219464,
73
+ "<|dummy_id_5|>": 219409,
74
+ "<|dummy_id_60|>": 219465,
75
+ "<|dummy_id_61|>": 219466,
76
+ "<|dummy_id_62|>": 219467,
77
+ "<|dummy_id_63|>": 219468,
78
+ "<|dummy_id_64|>": 219469,
79
+ "<|dummy_id_65|>": 219470,
80
+ "<|dummy_id_66|>": 219471,
81
+ "<|dummy_id_67|>": 219472,
82
+ "<|dummy_id_68|>": 219473,
83
+ "<|dummy_id_69|>": 219474,
84
+ "<|dummy_id_6|>": 219410,
85
+ "<|dummy_id_70|>": 219475,
86
+ "<|dummy_id_71|>": 219476,
87
+ "<|dummy_id_72|>": 219477,
88
+ "<|dummy_id_73|>": 219478,
89
+ "<|dummy_id_74|>": 219479,
90
+ "<|dummy_id_75|>": 219480,
91
+ "<|dummy_id_76|>": 219481,
92
+ "<|dummy_id_77|>": 219482,
93
+ "<|dummy_id_78|>": 219483,
94
+ "<|dummy_id_79|>": 219484,
95
+ "<|dummy_id_7|>": 219411,
96
+ "<|dummy_id_80|>": 219485,
97
+ "<|dummy_id_81|>": 219486,
98
+ "<|dummy_id_82|>": 219487,
99
+ "<|dummy_id_83|>": 219488,
100
+ "<|dummy_id_84|>": 219489,
101
+ "<|dummy_id_85|>": 219490,
102
+ "<|dummy_id_86|>": 219491,
103
+ "<|dummy_id_87|>": 219492,
104
+ "<|dummy_id_88|>": 219493,
105
+ "<|dummy_id_89|>": 219494,
106
+ "<|dummy_id_8|>": 219412,
107
+ "<|dummy_id_90|>": 219495,
108
+ "<|dummy_id_91|>": 219496,
109
+ "<|dummy_id_92|>": 219497,
110
+ "<|dummy_id_93|>": 219498,
111
+ "<|dummy_id_94|>": 219499,
112
+ "<|dummy_id_95|>": 219500,
113
+ "<|dummy_id_96|>": 219501,
114
+ "<|dummy_id_97|>": 219502,
115
+ "<|dummy_id_98|>": 219503,
116
+ "<|dummy_id_99|>": 219504,
117
+ "<|dummy_id_9|>": 219413,
118
+ "<|endofprompt|>": 219416,
119
+ "<|endoftext|>": 219395,
120
+ "<|endofturn|>": 219405,
121
+ "<|fim_middle|>": 219398,
122
+ "<|fim_prefix|>": 219397,
123
+ "<|fim_suffix|>": 219399,
124
+ "<|startofturn|>": 219403,
125
+ "<|system|>": 219400,
126
+ "<|user|>": 219401
127
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f2ac83eb3c0304aca1c639fdf4c27c71e1835833c31f919259c104e8b944a12
3
+ size 469808712
model.safetensors.index.json ADDED
@@ -0,0 +1,521 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 10388873728
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.mlp.act_fn.bias": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.act_fn.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.self_attn.lambda_k1": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.self_attn.lambda_k2": "model-00001-of-00003.safetensors",
17
+ "model.layers.0.self_attn.lambda_q1": "model-00001-of-00003.safetensors",
18
+ "model.layers.0.self_attn.lambda_q2": "model-00001-of-00003.safetensors",
19
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.0.self_attn.subln.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.mlp.act_fn.bias": "model-00001-of-00003.safetensors",
25
+ "model.layers.1.mlp.act_fn.weight": "model-00001-of-00003.safetensors",
26
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
27
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
28
+ "model.layers.1.mlp.up_proj.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.lambda_k1": "model-00001-of-00003.safetensors",
32
+ "model.layers.1.self_attn.lambda_k2": "model-00001-of-00003.safetensors",
33
+ "model.layers.1.self_attn.lambda_q1": "model-00001-of-00003.safetensors",
34
+ "model.layers.1.self_attn.lambda_q2": "model-00001-of-00003.safetensors",
35
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
36
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
37
+ "model.layers.1.self_attn.subln.weight": "model-00001-of-00003.safetensors",
38
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
39
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
40
+ "model.layers.10.mlp.act_fn.bias": "model-00001-of-00003.safetensors",
41
+ "model.layers.10.mlp.act_fn.weight": "model-00001-of-00003.safetensors",
42
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
43
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
44
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
45
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
46
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
47
+ "model.layers.10.self_attn.lambda_k1": "model-00001-of-00003.safetensors",
48
+ "model.layers.10.self_attn.lambda_k2": "model-00001-of-00003.safetensors",
49
+ "model.layers.10.self_attn.lambda_q1": "model-00001-of-00003.safetensors",
50
+ "model.layers.10.self_attn.lambda_q2": "model-00001-of-00003.safetensors",
51
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
52
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
53
+ "model.layers.10.self_attn.subln.weight": "model-00001-of-00003.safetensors",
54
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
55
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
56
+ "model.layers.11.mlp.act_fn.bias": "model-00002-of-00003.safetensors",
57
+ "model.layers.11.mlp.act_fn.weight": "model-00002-of-00003.safetensors",
58
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
59
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
60
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
61
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
62
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
63
+ "model.layers.11.self_attn.lambda_k1": "model-00001-of-00003.safetensors",
64
+ "model.layers.11.self_attn.lambda_k2": "model-00001-of-00003.safetensors",
65
+ "model.layers.11.self_attn.lambda_q1": "model-00001-of-00003.safetensors",
66
+ "model.layers.11.self_attn.lambda_q2": "model-00001-of-00003.safetensors",
67
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
68
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
69
+ "model.layers.11.self_attn.subln.weight": "model-00001-of-00003.safetensors",
70
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
71
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.12.mlp.act_fn.bias": "model-00002-of-00003.safetensors",
73
+ "model.layers.12.mlp.act_fn.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
77
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
79
+ "model.layers.12.self_attn.lambda_k1": "model-00002-of-00003.safetensors",
80
+ "model.layers.12.self_attn.lambda_k2": "model-00002-of-00003.safetensors",
81
+ "model.layers.12.self_attn.lambda_q1": "model-00002-of-00003.safetensors",
82
+ "model.layers.12.self_attn.lambda_q2": "model-00002-of-00003.safetensors",
83
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.12.self_attn.subln.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.13.mlp.act_fn.bias": "model-00002-of-00003.safetensors",
89
+ "model.layers.13.mlp.act_fn.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
93
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.13.self_attn.lambda_k1": "model-00002-of-00003.safetensors",
96
+ "model.layers.13.self_attn.lambda_k2": "model-00002-of-00003.safetensors",
97
+ "model.layers.13.self_attn.lambda_q1": "model-00002-of-00003.safetensors",
98
+ "model.layers.13.self_attn.lambda_q2": "model-00002-of-00003.safetensors",
99
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.13.self_attn.subln.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.14.mlp.act_fn.bias": "model-00002-of-00003.safetensors",
105
+ "model.layers.14.mlp.act_fn.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.14.self_attn.lambda_k1": "model-00002-of-00003.safetensors",
112
+ "model.layers.14.self_attn.lambda_k2": "model-00002-of-00003.safetensors",
113
+ "model.layers.14.self_attn.lambda_q1": "model-00002-of-00003.safetensors",
114
+ "model.layers.14.self_attn.lambda_q2": "model-00002-of-00003.safetensors",
115
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
116
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
117
+ "model.layers.14.self_attn.subln.weight": "model-00002-of-00003.safetensors",
118
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
119
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
120
+ "model.layers.15.mlp.act_fn.bias": "model-00002-of-00003.safetensors",
121
+ "model.layers.15.mlp.act_fn.weight": "model-00002-of-00003.safetensors",
122
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
123
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
124
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
125
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
126
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.15.self_attn.lambda_k1": "model-00002-of-00003.safetensors",
128
+ "model.layers.15.self_attn.lambda_k2": "model-00002-of-00003.safetensors",
129
+ "model.layers.15.self_attn.lambda_q1": "model-00002-of-00003.safetensors",
130
+ "model.layers.15.self_attn.lambda_q2": "model-00002-of-00003.safetensors",
131
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.15.self_attn.subln.weight": "model-00002-of-00003.safetensors",
134
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
135
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
136
+ "model.layers.16.mlp.act_fn.bias": "model-00002-of-00003.safetensors",
137
+ "model.layers.16.mlp.act_fn.weight": "model-00002-of-00003.safetensors",
138
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
139
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
140
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
141
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
142
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
143
+ "model.layers.16.self_attn.lambda_k1": "model-00002-of-00003.safetensors",
144
+ "model.layers.16.self_attn.lambda_k2": "model-00002-of-00003.safetensors",
145
+ "model.layers.16.self_attn.lambda_q1": "model-00002-of-00003.safetensors",
146
+ "model.layers.16.self_attn.lambda_q2": "model-00002-of-00003.safetensors",
147
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
148
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
149
+ "model.layers.16.self_attn.subln.weight": "model-00002-of-00003.safetensors",
150
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
151
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
152
+ "model.layers.17.mlp.act_fn.bias": "model-00002-of-00003.safetensors",
153
+ "model.layers.17.mlp.act_fn.weight": "model-00002-of-00003.safetensors",
154
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
155
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
156
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
157
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
158
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
159
+ "model.layers.17.self_attn.lambda_k1": "model-00002-of-00003.safetensors",
160
+ "model.layers.17.self_attn.lambda_k2": "model-00002-of-00003.safetensors",
161
+ "model.layers.17.self_attn.lambda_q1": "model-00002-of-00003.safetensors",
162
+ "model.layers.17.self_attn.lambda_q2": "model-00002-of-00003.safetensors",
163
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
164
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
165
+ "model.layers.17.self_attn.subln.weight": "model-00002-of-00003.safetensors",
166
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
167
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
168
+ "model.layers.18.mlp.act_fn.bias": "model-00002-of-00003.safetensors",
169
+ "model.layers.18.mlp.act_fn.weight": "model-00002-of-00003.safetensors",
170
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
171
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
172
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
173
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
174
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
175
+ "model.layers.18.self_attn.lambda_k1": "model-00002-of-00003.safetensors",
176
+ "model.layers.18.self_attn.lambda_k2": "model-00002-of-00003.safetensors",
177
+ "model.layers.18.self_attn.lambda_q1": "model-00002-of-00003.safetensors",
178
+ "model.layers.18.self_attn.lambda_q2": "model-00002-of-00003.safetensors",
179
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
180
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
181
+ "model.layers.18.self_attn.subln.weight": "model-00002-of-00003.safetensors",
182
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
183
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
184
+ "model.layers.19.mlp.act_fn.bias": "model-00002-of-00003.safetensors",
185
+ "model.layers.19.mlp.act_fn.weight": "model-00002-of-00003.safetensors",
186
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
187
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
188
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
189
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
190
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
191
+ "model.layers.19.self_attn.lambda_k1": "model-00002-of-00003.safetensors",
192
+ "model.layers.19.self_attn.lambda_k2": "model-00002-of-00003.safetensors",
193
+ "model.layers.19.self_attn.lambda_q1": "model-00002-of-00003.safetensors",
194
+ "model.layers.19.self_attn.lambda_q2": "model-00002-of-00003.safetensors",
195
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
196
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
197
+ "model.layers.19.self_attn.subln.weight": "model-00002-of-00003.safetensors",
198
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
199
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
200
+ "model.layers.2.mlp.act_fn.bias": "model-00001-of-00003.safetensors",
201
+ "model.layers.2.mlp.act_fn.weight": "model-00001-of-00003.safetensors",
202
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
203
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
204
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
205
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
206
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
207
+ "model.layers.2.self_attn.lambda_k1": "model-00001-of-00003.safetensors",
208
+ "model.layers.2.self_attn.lambda_k2": "model-00001-of-00003.safetensors",
209
+ "model.layers.2.self_attn.lambda_q1": "model-00001-of-00003.safetensors",
210
+ "model.layers.2.self_attn.lambda_q2": "model-00001-of-00003.safetensors",
211
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
212
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
213
+ "model.layers.2.self_attn.subln.weight": "model-00001-of-00003.safetensors",
214
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
215
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
216
+ "model.layers.20.mlp.act_fn.bias": "model-00002-of-00003.safetensors",
217
+ "model.layers.20.mlp.act_fn.weight": "model-00002-of-00003.safetensors",
218
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
219
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
220
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
221
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
222
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
223
+ "model.layers.20.self_attn.lambda_k1": "model-00002-of-00003.safetensors",
224
+ "model.layers.20.self_attn.lambda_k2": "model-00002-of-00003.safetensors",
225
+ "model.layers.20.self_attn.lambda_q1": "model-00002-of-00003.safetensors",
226
+ "model.layers.20.self_attn.lambda_q2": "model-00002-of-00003.safetensors",
227
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
228
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
229
+ "model.layers.20.self_attn.subln.weight": "model-00002-of-00003.safetensors",
230
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
231
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
232
+ "model.layers.21.mlp.act_fn.bias": "model-00002-of-00003.safetensors",
233
+ "model.layers.21.mlp.act_fn.weight": "model-00002-of-00003.safetensors",
234
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
235
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
236
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
237
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
238
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
239
+ "model.layers.21.self_attn.lambda_k1": "model-00002-of-00003.safetensors",
240
+ "model.layers.21.self_attn.lambda_k2": "model-00002-of-00003.safetensors",
241
+ "model.layers.21.self_attn.lambda_q1": "model-00002-of-00003.safetensors",
242
+ "model.layers.21.self_attn.lambda_q2": "model-00002-of-00003.safetensors",
243
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
244
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
245
+ "model.layers.21.self_attn.subln.weight": "model-00002-of-00003.safetensors",
246
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
247
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
248
+ "model.layers.22.mlp.act_fn.bias": "model-00002-of-00003.safetensors",
249
+ "model.layers.22.mlp.act_fn.weight": "model-00002-of-00003.safetensors",
250
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
251
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
252
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
253
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
254
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
255
+ "model.layers.22.self_attn.lambda_k1": "model-00002-of-00003.safetensors",
256
+ "model.layers.22.self_attn.lambda_k2": "model-00002-of-00003.safetensors",
257
+ "model.layers.22.self_attn.lambda_q1": "model-00002-of-00003.safetensors",
258
+ "model.layers.22.self_attn.lambda_q2": "model-00002-of-00003.safetensors",
259
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
260
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
261
+ "model.layers.22.self_attn.subln.weight": "model-00002-of-00003.safetensors",
262
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
263
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
264
+ "model.layers.23.mlp.act_fn.bias": "model-00002-of-00003.safetensors",
265
+ "model.layers.23.mlp.act_fn.weight": "model-00002-of-00003.safetensors",
266
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
267
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
268
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
269
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
270
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
271
+ "model.layers.23.self_attn.lambda_k1": "model-00002-of-00003.safetensors",
272
+ "model.layers.23.self_attn.lambda_k2": "model-00002-of-00003.safetensors",
273
+ "model.layers.23.self_attn.lambda_q1": "model-00002-of-00003.safetensors",
274
+ "model.layers.23.self_attn.lambda_q2": "model-00002-of-00003.safetensors",
275
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
276
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
277
+ "model.layers.23.self_attn.subln.weight": "model-00002-of-00003.safetensors",
278
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
279
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
280
+ "model.layers.24.mlp.act_fn.bias": "model-00002-of-00003.safetensors",
281
+ "model.layers.24.mlp.act_fn.weight": "model-00002-of-00003.safetensors",
282
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
283
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
284
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
285
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
286
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
287
+ "model.layers.24.self_attn.lambda_k1": "model-00002-of-00003.safetensors",
288
+ "model.layers.24.self_attn.lambda_k2": "model-00002-of-00003.safetensors",
289
+ "model.layers.24.self_attn.lambda_q1": "model-00002-of-00003.safetensors",
290
+ "model.layers.24.self_attn.lambda_q2": "model-00002-of-00003.safetensors",
291
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
292
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
293
+ "model.layers.24.self_attn.subln.weight": "model-00002-of-00003.safetensors",
294
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
295
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
296
+ "model.layers.25.mlp.act_fn.bias": "model-00002-of-00003.safetensors",
297
+ "model.layers.25.mlp.act_fn.weight": "model-00002-of-00003.safetensors",
298
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
299
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
300
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
301
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
302
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
303
+ "model.layers.25.self_attn.lambda_k1": "model-00002-of-00003.safetensors",
304
+ "model.layers.25.self_attn.lambda_k2": "model-00002-of-00003.safetensors",
305
+ "model.layers.25.self_attn.lambda_q1": "model-00002-of-00003.safetensors",
306
+ "model.layers.25.self_attn.lambda_q2": "model-00002-of-00003.safetensors",
307
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
308
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
309
+ "model.layers.25.self_attn.subln.weight": "model-00002-of-00003.safetensors",
310
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
311
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
312
+ "model.layers.26.mlp.act_fn.bias": "model-00002-of-00003.safetensors",
313
+ "model.layers.26.mlp.act_fn.weight": "model-00002-of-00003.safetensors",
314
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
315
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
316
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
317
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
318
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
319
+ "model.layers.26.self_attn.lambda_k1": "model-00002-of-00003.safetensors",
320
+ "model.layers.26.self_attn.lambda_k2": "model-00002-of-00003.safetensors",
321
+ "model.layers.26.self_attn.lambda_q1": "model-00002-of-00003.safetensors",
322
+ "model.layers.26.self_attn.lambda_q2": "model-00002-of-00003.safetensors",
323
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
324
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
325
+ "model.layers.26.self_attn.subln.weight": "model-00002-of-00003.safetensors",
326
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
327
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
328
+ "model.layers.27.mlp.act_fn.bias": "model-00002-of-00003.safetensors",
329
+ "model.layers.27.mlp.act_fn.weight": "model-00002-of-00003.safetensors",
330
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
331
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
332
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
333
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
334
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
335
+ "model.layers.27.self_attn.lambda_k1": "model-00002-of-00003.safetensors",
336
+ "model.layers.27.self_attn.lambda_k2": "model-00002-of-00003.safetensors",
337
+ "model.layers.27.self_attn.lambda_q1": "model-00002-of-00003.safetensors",
338
+ "model.layers.27.self_attn.lambda_q2": "model-00002-of-00003.safetensors",
339
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
340
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
341
+ "model.layers.27.self_attn.subln.weight": "model-00002-of-00003.safetensors",
342
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
343
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
344
+ "model.layers.28.mlp.act_fn.bias": "model-00002-of-00003.safetensors",
345
+ "model.layers.28.mlp.act_fn.weight": "model-00002-of-00003.safetensors",
346
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
347
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
348
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
349
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
350
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
351
+ "model.layers.28.self_attn.lambda_k1": "model-00002-of-00003.safetensors",
352
+ "model.layers.28.self_attn.lambda_k2": "model-00002-of-00003.safetensors",
353
+ "model.layers.28.self_attn.lambda_q1": "model-00002-of-00003.safetensors",
354
+ "model.layers.28.self_attn.lambda_q2": "model-00002-of-00003.safetensors",
355
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
356
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
357
+ "model.layers.28.self_attn.subln.weight": "model-00002-of-00003.safetensors",
358
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
359
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
360
+ "model.layers.29.mlp.act_fn.bias": "model-00002-of-00003.safetensors",
361
+ "model.layers.29.mlp.act_fn.weight": "model-00002-of-00003.safetensors",
362
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
363
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
364
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
365
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
366
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
367
+ "model.layers.29.self_attn.lambda_k1": "model-00002-of-00003.safetensors",
368
+ "model.layers.29.self_attn.lambda_k2": "model-00002-of-00003.safetensors",
369
+ "model.layers.29.self_attn.lambda_q1": "model-00002-of-00003.safetensors",
370
+ "model.layers.29.self_attn.lambda_q2": "model-00002-of-00003.safetensors",
371
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
372
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
373
+ "model.layers.29.self_attn.subln.weight": "model-00002-of-00003.safetensors",
374
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
375
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
376
+ "model.layers.3.mlp.act_fn.bias": "model-00001-of-00003.safetensors",
377
+ "model.layers.3.mlp.act_fn.weight": "model-00001-of-00003.safetensors",
378
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
379
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
380
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
381
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
382
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
383
+ "model.layers.3.self_attn.lambda_k1": "model-00001-of-00003.safetensors",
384
+ "model.layers.3.self_attn.lambda_k2": "model-00001-of-00003.safetensors",
385
+ "model.layers.3.self_attn.lambda_q1": "model-00001-of-00003.safetensors",
386
+ "model.layers.3.self_attn.lambda_q2": "model-00001-of-00003.safetensors",
387
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
388
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
389
+ "model.layers.3.self_attn.subln.weight": "model-00001-of-00003.safetensors",
390
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
391
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
392
+ "model.layers.30.mlp.act_fn.bias": "model-00003-of-00003.safetensors",
393
+ "model.layers.30.mlp.act_fn.weight": "model-00003-of-00003.safetensors",
394
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
395
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
396
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
397
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
398
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
399
+ "model.layers.30.self_attn.lambda_k1": "model-00002-of-00003.safetensors",
400
+ "model.layers.30.self_attn.lambda_k2": "model-00002-of-00003.safetensors",
401
+ "model.layers.30.self_attn.lambda_q1": "model-00002-of-00003.safetensors",
402
+ "model.layers.30.self_attn.lambda_q2": "model-00002-of-00003.safetensors",
403
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
404
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
405
+ "model.layers.30.self_attn.subln.weight": "model-00002-of-00003.safetensors",
406
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
407
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
408
+ "model.layers.31.mlp.act_fn.bias": "model-00003-of-00003.safetensors",
409
+ "model.layers.31.mlp.act_fn.weight": "model-00003-of-00003.safetensors",
410
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
411
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
412
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
413
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
414
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
415
+ "model.layers.31.self_attn.lambda_k1": "model-00003-of-00003.safetensors",
416
+ "model.layers.31.self_attn.lambda_k2": "model-00003-of-00003.safetensors",
417
+ "model.layers.31.self_attn.lambda_q1": "model-00003-of-00003.safetensors",
418
+ "model.layers.31.self_attn.lambda_q2": "model-00003-of-00003.safetensors",
419
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
420
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
421
+ "model.layers.31.self_attn.subln.weight": "model-00003-of-00003.safetensors",
422
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
423
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
424
+ "model.layers.4.mlp.act_fn.bias": "model-00001-of-00003.safetensors",
425
+ "model.layers.4.mlp.act_fn.weight": "model-00001-of-00003.safetensors",
426
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
427
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
428
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
429
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
430
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
431
+ "model.layers.4.self_attn.lambda_k1": "model-00001-of-00003.safetensors",
432
+ "model.layers.4.self_attn.lambda_k2": "model-00001-of-00003.safetensors",
433
+ "model.layers.4.self_attn.lambda_q1": "model-00001-of-00003.safetensors",
434
+ "model.layers.4.self_attn.lambda_q2": "model-00001-of-00003.safetensors",
435
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
436
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
437
+ "model.layers.4.self_attn.subln.weight": "model-00001-of-00003.safetensors",
438
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
439
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
440
+ "model.layers.5.mlp.act_fn.bias": "model-00001-of-00003.safetensors",
441
+ "model.layers.5.mlp.act_fn.weight": "model-00001-of-00003.safetensors",
442
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
443
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
444
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
445
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
446
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
447
+ "model.layers.5.self_attn.lambda_k1": "model-00001-of-00003.safetensors",
448
+ "model.layers.5.self_attn.lambda_k2": "model-00001-of-00003.safetensors",
449
+ "model.layers.5.self_attn.lambda_q1": "model-00001-of-00003.safetensors",
450
+ "model.layers.5.self_attn.lambda_q2": "model-00001-of-00003.safetensors",
451
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
452
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
453
+ "model.layers.5.self_attn.subln.weight": "model-00001-of-00003.safetensors",
454
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
455
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
456
+ "model.layers.6.mlp.act_fn.bias": "model-00001-of-00003.safetensors",
457
+ "model.layers.6.mlp.act_fn.weight": "model-00001-of-00003.safetensors",
458
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
459
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
460
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
461
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
462
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
463
+ "model.layers.6.self_attn.lambda_k1": "model-00001-of-00003.safetensors",
464
+ "model.layers.6.self_attn.lambda_k2": "model-00001-of-00003.safetensors",
465
+ "model.layers.6.self_attn.lambda_q1": "model-00001-of-00003.safetensors",
466
+ "model.layers.6.self_attn.lambda_q2": "model-00001-of-00003.safetensors",
467
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
468
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
469
+ "model.layers.6.self_attn.subln.weight": "model-00001-of-00003.safetensors",
470
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
471
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
472
+ "model.layers.7.mlp.act_fn.bias": "model-00001-of-00003.safetensors",
473
+ "model.layers.7.mlp.act_fn.weight": "model-00001-of-00003.safetensors",
474
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
475
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
476
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
477
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
478
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
479
+ "model.layers.7.self_attn.lambda_k1": "model-00001-of-00003.safetensors",
480
+ "model.layers.7.self_attn.lambda_k2": "model-00001-of-00003.safetensors",
481
+ "model.layers.7.self_attn.lambda_q1": "model-00001-of-00003.safetensors",
482
+ "model.layers.7.self_attn.lambda_q2": "model-00001-of-00003.safetensors",
483
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
484
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
485
+ "model.layers.7.self_attn.subln.weight": "model-00001-of-00003.safetensors",
486
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
487
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
488
+ "model.layers.8.mlp.act_fn.bias": "model-00001-of-00003.safetensors",
489
+ "model.layers.8.mlp.act_fn.weight": "model-00001-of-00003.safetensors",
490
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
491
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
492
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
493
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
494
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
495
+ "model.layers.8.self_attn.lambda_k1": "model-00001-of-00003.safetensors",
496
+ "model.layers.8.self_attn.lambda_k2": "model-00001-of-00003.safetensors",
497
+ "model.layers.8.self_attn.lambda_q1": "model-00001-of-00003.safetensors",
498
+ "model.layers.8.self_attn.lambda_q2": "model-00001-of-00003.safetensors",
499
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
500
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
501
+ "model.layers.8.self_attn.subln.weight": "model-00001-of-00003.safetensors",
502
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
503
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
504
+ "model.layers.9.mlp.act_fn.bias": "model-00001-of-00003.safetensors",
505
+ "model.layers.9.mlp.act_fn.weight": "model-00001-of-00003.safetensors",
506
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
507
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
508
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
509
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
510
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
511
+ "model.layers.9.self_attn.lambda_k1": "model-00001-of-00003.safetensors",
512
+ "model.layers.9.self_attn.lambda_k2": "model-00001-of-00003.safetensors",
513
+ "model.layers.9.self_attn.lambda_q1": "model-00001-of-00003.safetensors",
514
+ "model.layers.9.self_attn.lambda_q2": "model-00001-of-00003.safetensors",
515
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
516
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
517
+ "model.layers.9.self_attn.subln.weight": "model-00001-of-00003.safetensors",
518
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
519
+ "model.norm.weight": "model-00003-of-00003.safetensors"
520
+ }
521
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|beginoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:275139d476909028da05d4ee035aba88f0ca0dbfd0d395f72b7fc80fd7782e19
3
+ size 17264873
tokenizer_config.json ADDED
@@ -0,0 +1,1027 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "219395": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "219396": {
13
+ "content": "<|beginoftext|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "219397": {
21
+ "content": "<|fim_prefix|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "219398": {
29
+ "content": "<|fim_middle|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "219399": {
37
+ "content": "<|fim_suffix|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "219400": {
45
+ "content": "<|system|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "219401": {
53
+ "content": "<|user|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "219402": {
61
+ "content": "<|assistant|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "219403": {
69
+ "content": "<|startofturn|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "219404": {
77
+ "content": "<think>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "219405": {
85
+ "content": "<|endofturn|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "219406": {
93
+ "content": "</think>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "219407": {
101
+ "content": "<|dummy_id_3|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "219408": {
109
+ "content": "<|dummy_id_4|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "219409": {
117
+ "content": "<|dummy_id_5|>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "219410": {
125
+ "content": "<|dummy_id_6|>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "219411": {
133
+ "content": "<|dummy_id_7|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "219412": {
141
+ "content": "<|dummy_id_8|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "219413": {
149
+ "content": "<|dummy_id_9|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "219414": {
157
+ "content": "<|dummy_id_10|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "219415": {
165
+ "content": "<|dummy_id_11|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "219416": {
173
+ "content": "<|endofprompt|>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "219417": {
181
+ "content": "<|dummy_id_12|>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "219418": {
189
+ "content": "<|dummy_id_13|>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "219419": {
197
+ "content": "<|dummy_id_14|>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "219420": {
205
+ "content": "<|dummy_id_15|>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "219421": {
213
+ "content": "<|dummy_id_16|>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "219422": {
221
+ "content": "<|dummy_id_17|>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "219423": {
229
+ "content": "<|dummy_id_18|>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "219424": {
237
+ "content": "<|dummy_id_19|>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "219425": {
245
+ "content": "<|dummy_id_20|>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "219426": {
253
+ "content": "<|dummy_id_21|>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "219427": {
261
+ "content": "<|dummy_id_22|>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "219428": {
269
+ "content": "<|dummy_id_23|>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "219429": {
277
+ "content": "<|dummy_id_24|>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "219430": {
285
+ "content": "<|dummy_id_25|>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "219431": {
293
+ "content": "<|dummy_id_26|>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "219432": {
301
+ "content": "<|dummy_id_27|>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "219433": {
309
+ "content": "<|dummy_id_28|>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "219434": {
317
+ "content": "<|dummy_id_29|>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "219435": {
325
+ "content": "<|dummy_id_30|>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "219436": {
333
+ "content": "<|dummy_id_31|>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "219437": {
341
+ "content": "<|dummy_id_32|>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "219438": {
349
+ "content": "<|dummy_id_33|>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "219439": {
357
+ "content": "<|dummy_id_34|>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "219440": {
365
+ "content": "<|dummy_id_35|>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "219441": {
373
+ "content": "<|dummy_id_36|>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "219442": {
381
+ "content": "<|dummy_id_37|>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "219443": {
389
+ "content": "<|dummy_id_38|>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "219444": {
397
+ "content": "<|dummy_id_39|>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "219445": {
405
+ "content": "<|dummy_id_40|>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "219446": {
413
+ "content": "<|dummy_id_41|>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "219447": {
421
+ "content": "<|dummy_id_42|>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "219448": {
429
+ "content": "<|dummy_id_43|>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "219449": {
437
+ "content": "<|dummy_id_44|>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "219450": {
445
+ "content": "<|dummy_id_45|>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "219451": {
453
+ "content": "<|dummy_id_46|>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "219452": {
461
+ "content": "<|dummy_id_47|>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "219453": {
469
+ "content": "<|dummy_id_48|>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "219454": {
477
+ "content": "<|dummy_id_49|>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "219455": {
485
+ "content": "<|dummy_id_50|>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "219456": {
493
+ "content": "<|dummy_id_51|>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "219457": {
501
+ "content": "<|dummy_id_52|>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "219458": {
509
+ "content": "<|dummy_id_53|>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "219459": {
517
+ "content": "<|dummy_id_54|>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "219460": {
525
+ "content": "<|dummy_id_55|>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "219461": {
533
+ "content": "<|dummy_id_56|>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "219462": {
541
+ "content": "<|dummy_id_57|>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "219463": {
549
+ "content": "<|dummy_id_58|>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "219464": {
557
+ "content": "<|dummy_id_59|>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "219465": {
565
+ "content": "<|dummy_id_60|>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "219466": {
573
+ "content": "<|dummy_id_61|>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "219467": {
581
+ "content": "<|dummy_id_62|>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "219468": {
589
+ "content": "<|dummy_id_63|>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "219469": {
597
+ "content": "<|dummy_id_64|>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "219470": {
605
+ "content": "<|dummy_id_65|>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "219471": {
613
+ "content": "<|dummy_id_66|>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "219472": {
621
+ "content": "<|dummy_id_67|>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "219473": {
629
+ "content": "<|dummy_id_68|>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "219474": {
637
+ "content": "<|dummy_id_69|>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "219475": {
645
+ "content": "<|dummy_id_70|>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "219476": {
653
+ "content": "<|dummy_id_71|>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "219477": {
661
+ "content": "<|dummy_id_72|>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "219478": {
669
+ "content": "<|dummy_id_73|>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "219479": {
677
+ "content": "<|dummy_id_74|>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "219480": {
685
+ "content": "<|dummy_id_75|>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "219481": {
693
+ "content": "<|dummy_id_76|>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "219482": {
701
+ "content": "<|dummy_id_77|>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "219483": {
709
+ "content": "<|dummy_id_78|>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "219484": {
717
+ "content": "<|dummy_id_79|>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "219485": {
725
+ "content": "<|dummy_id_80|>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "219486": {
733
+ "content": "<|dummy_id_81|>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "219487": {
741
+ "content": "<|dummy_id_82|>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "219488": {
749
+ "content": "<|dummy_id_83|>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "219489": {
757
+ "content": "<|dummy_id_84|>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "219490": {
765
+ "content": "<|dummy_id_85|>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "219491": {
773
+ "content": "<|dummy_id_86|>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "219492": {
781
+ "content": "<|dummy_id_87|>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "219493": {
789
+ "content": "<|dummy_id_88|>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "219494": {
797
+ "content": "<|dummy_id_89|>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "219495": {
805
+ "content": "<|dummy_id_90|>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "219496": {
813
+ "content": "<|dummy_id_91|>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "219497": {
821
+ "content": "<|dummy_id_92|>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "219498": {
829
+ "content": "<|dummy_id_93|>",
830
+ "lstrip": false,
831
+ "normalized": false,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": true
835
+ },
836
+ "219499": {
837
+ "content": "<|dummy_id_94|>",
838
+ "lstrip": false,
839
+ "normalized": false,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": true
843
+ },
844
+ "219500": {
845
+ "content": "<|dummy_id_95|>",
846
+ "lstrip": false,
847
+ "normalized": false,
848
+ "rstrip": false,
849
+ "single_word": false,
850
+ "special": true
851
+ },
852
+ "219501": {
853
+ "content": "<|dummy_id_96|>",
854
+ "lstrip": false,
855
+ "normalized": false,
856
+ "rstrip": false,
857
+ "single_word": false,
858
+ "special": true
859
+ },
860
+ "219502": {
861
+ "content": "<|dummy_id_97|>",
862
+ "lstrip": false,
863
+ "normalized": false,
864
+ "rstrip": false,
865
+ "single_word": false,
866
+ "special": true
867
+ },
868
+ "219503": {
869
+ "content": "<|dummy_id_98|>",
870
+ "lstrip": false,
871
+ "normalized": false,
872
+ "rstrip": false,
873
+ "single_word": false,
874
+ "special": true
875
+ },
876
+ "219504": {
877
+ "content": "<|dummy_id_99|>",
878
+ "lstrip": false,
879
+ "normalized": false,
880
+ "rstrip": false,
881
+ "single_word": false,
882
+ "special": true
883
+ },
884
+ "219505": {
885
+ "content": "<|dummy_id_100|>",
886
+ "lstrip": false,
887
+ "normalized": false,
888
+ "rstrip": false,
889
+ "single_word": false,
890
+ "special": true
891
+ },
892
+ "219506": {
893
+ "content": "<|dummy_id_101|>",
894
+ "lstrip": false,
895
+ "normalized": false,
896
+ "rstrip": false,
897
+ "single_word": false,
898
+ "special": true
899
+ },
900
+ "219507": {
901
+ "content": "<|dummy_id_102|>",
902
+ "lstrip": false,
903
+ "normalized": false,
904
+ "rstrip": false,
905
+ "single_word": false,
906
+ "special": true
907
+ },
908
+ "219508": {
909
+ "content": "<|dummy_id_103|>",
910
+ "lstrip": false,
911
+ "normalized": false,
912
+ "rstrip": false,
913
+ "single_word": false,
914
+ "special": true
915
+ },
916
+ "219509": {
917
+ "content": "<|dummy_id_104|>",
918
+ "lstrip": false,
919
+ "normalized": false,
920
+ "rstrip": false,
921
+ "single_word": false,
922
+ "special": true
923
+ },
924
+ "219510": {
925
+ "content": "<|dummy_id_105|>",
926
+ "lstrip": false,
927
+ "normalized": false,
928
+ "rstrip": false,
929
+ "single_word": false,
930
+ "special": true
931
+ },
932
+ "219511": {
933
+ "content": "<|dummy_id_106|>",
934
+ "lstrip": false,
935
+ "normalized": false,
936
+ "rstrip": false,
937
+ "single_word": false,
938
+ "special": true
939
+ },
940
+ "219512": {
941
+ "content": "<|dummy_id_107|>",
942
+ "lstrip": false,
943
+ "normalized": false,
944
+ "rstrip": false,
945
+ "single_word": false,
946
+ "special": true
947
+ },
948
+ "219513": {
949
+ "content": "<|dummy_id_108|>",
950
+ "lstrip": false,
951
+ "normalized": false,
952
+ "rstrip": false,
953
+ "single_word": false,
954
+ "special": true
955
+ },
956
+ "219514": {
957
+ "content": "<|dummy_id_109|>",
958
+ "lstrip": false,
959
+ "normalized": false,
960
+ "rstrip": false,
961
+ "single_word": false,
962
+ "special": true
963
+ },
964
+ "219515": {
965
+ "content": "<|dummy_id_110|>",
966
+ "lstrip": false,
967
+ "normalized": false,
968
+ "rstrip": false,
969
+ "single_word": false,
970
+ "special": true
971
+ },
972
+ "219516": {
973
+ "content": "<|dummy_id_111|>",
974
+ "lstrip": false,
975
+ "normalized": false,
976
+ "rstrip": false,
977
+ "single_word": false,
978
+ "special": true
979
+ },
980
+ "219517": {
981
+ "content": "<|dummy_id_112|>",
982
+ "lstrip": false,
983
+ "normalized": false,
984
+ "rstrip": false,
985
+ "single_word": false,
986
+ "special": true
987
+ },
988
+ "219518": {
989
+ "content": "<|dummy_id_113|>",
990
+ "lstrip": false,
991
+ "normalized": false,
992
+ "rstrip": false,
993
+ "single_word": false,
994
+ "special": true
995
+ },
996
+ "219519": {
997
+ "content": "<|dummy_id_114|>",
998
+ "lstrip": false,
999
+ "normalized": false,
1000
+ "rstrip": false,
1001
+ "single_word": false,
1002
+ "special": true
1003
+ }
1004
+ },
1005
+ "block_size": 2048,
1006
+ "bos_token": "<|beginoftext|>",
1007
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'assistant' and '</think>' in content %}{% set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}{% set content = content.split('</think>')[-1].lstrip('\n') %}{{ '<|startofturn|><|assistant|>\n\n<think>\n' + reasoning_content + '\n</think>\n\n' + content + '<|endofturn|>' }}{% else %}{{ '<|startofturn|><|' + message['role'] + '|>\n\n' + content + '<|endofturn|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|startofturn|><|assistant|>\n\n' }}{% endif %}",
1008
+ "clean_up_tokenization_spaces": false,
1009
+ "corruption_rate": 0.15,
1010
+ "eos_token": "<|endoftext|>",
1011
+ "extra_ids": 0,
1012
+ "extra_special_tokens": {},
1013
+ "fixed_vocab": true,
1014
+ "merges_file_path": "./data/merges.txt",
1015
+ "model_max_length": 1000000000000000019884624838656,
1016
+ "pad_token": "<|endoftext|>",
1017
+ "padding_side": "left",
1018
+ "seq_length": 2048,
1019
+ "tokenizer_class": "GPT2Tokenizer",
1020
+ "tokenizer_name": "/nfs-ssd/motif_1/tokenizers/ver5",
1021
+ "tokens": -1,
1022
+ "unk_token": "<|endoftext|>",
1023
+ "update_tokenizer": false,
1024
+ "use_moreh_tokenizer": false,
1025
+ "vocab_file_path": "./data/vocab.json",
1026
+ "vocab_size": 219395
1027
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff