Hugging Face's logo

physicsrob
/
torchwright-calculator-scratchpad-max-digits-3

Text Generation
Transformers
Safetensors
phi3
torchwright
compiled-transformer
calculator_scratchpad
text-generation-inference
Model card Files
xet
 Community
physicsrob commited on
Commit
3834179
·
verified ·
1 Parent(s): a324d0a

Add explicit <unk> token

Browse files

Append a zero-semantic unknown-token row without changing any existing token ids or transformer-layer weights.

Files changed (5) hide show
  1. config.json +1 -1
  2. model-00019-of-00019.safetensors +2 -2
  3. model.safetensors.index.json +117 -1
  4. tokenizer.json +11 -1
  5. tokenizer_config.json +1 -1
config.json CHANGED
@@ -29,5 +29,5 @@
29
  "tie_word_embeddings": true,
30
  "transformers_version": "5.12.1",
31
  "use_cache": true,
32
- "vocab_size": 33
33
  }
 
29
  "tie_word_embeddings": true,
30
  "transformers_version": "5.12.1",
31
  "use_cache": true,
32
+ "vocab_size": 34
33
  }
model-00019-of-00019.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00da4f5695aa0d54395ed4474a3a3b94fcf7bbcd71d120016321b5c3577ec56c
3
- size 577472
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7007bb14771230ab3129388319b7d18a4b544ec0900c064f72d0a9cba5d7c457
3
+ size 585664
model.safetensors.index.json CHANGED
@@ -1 +1,117 @@
1
- {"metadata": {"total_size": 2306048000}, "weight_map": {"model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00019.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00019.safetensors", "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00019.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00019.safetensors", "model.layers.1.self_attn.qkv_proj.weight": "model-00002-of-00019.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00019.safetensors", "model.layers.1.mlp.gate_up_proj.weight": "model-00002-of-00019.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00019.safetensors", "model.layers.2.self_attn.qkv_proj.weight": "model-00003-of-00019.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00019.safetensors", "model.layers.2.mlp.gate_up_proj.weight": "model-00003-of-00019.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00019.safetensors", "model.layers.3.self_attn.qkv_proj.weight": "model-00004-of-00019.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00019.safetensors", "model.layers.3.mlp.gate_up_proj.weight": "model-00004-of-00019.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00004-of-00019.safetensors", "model.layers.4.self_attn.qkv_proj.weight": "model-00005-of-00019.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00019.safetensors", "model.layers.4.mlp.gate_up_proj.weight": "model-00005-of-00019.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00005-of-00019.safetensors", "model.layers.5.self_attn.qkv_proj.weight": "model-00006-of-00019.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00019.safetensors", "model.layers.5.mlp.gate_up_proj.weight": "model-00006-of-00019.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00006-of-00019.safetensors", "model.layers.6.self_attn.qkv_proj.weight": "model-00007-of-00019.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00019.safetensors", "model.layers.6.mlp.gate_up_proj.weight": "model-00007-of-00019.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00007-of-00019.safetensors", "model.layers.7.self_attn.qkv_proj.weight": "model-00008-of-00019.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00019.safetensors", "model.layers.7.mlp.gate_up_proj.weight": "model-00008-of-00019.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00008-of-00019.safetensors", "model.layers.8.self_attn.qkv_proj.weight": "model-00009-of-00019.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00019.safetensors", "model.layers.8.mlp.gate_up_proj.weight": "model-00009-of-00019.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00009-of-00019.safetensors", "model.layers.9.self_attn.qkv_proj.weight": "model-00010-of-00019.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00010-of-00019.safetensors", "model.layers.9.mlp.gate_up_proj.weight": "model-00010-of-00019.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00010-of-00019.safetensors", "model.layers.10.self_attn.qkv_proj.weight": "model-00011-of-00019.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00011-of-00019.safetensors", "model.layers.10.mlp.gate_up_proj.weight": "model-00011-of-00019.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00011-of-00019.safetensors", "model.layers.11.self_attn.qkv_proj.weight": "model-00012-of-00019.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00012-of-00019.safetensors", "model.layers.11.mlp.gate_up_proj.weight": "model-00012-of-00019.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00012-of-00019.safetensors", "model.layers.12.self_attn.qkv_proj.weight": "model-00013-of-00019.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00013-of-00019.safetensors", "model.layers.12.mlp.gate_up_proj.weight": "model-00013-of-00019.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00013-of-00019.safetensors", "model.layers.13.self_attn.qkv_proj.weight": "model-00014-of-00019.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00014-of-00019.safetensors", "model.layers.13.mlp.gate_up_proj.weight": "model-00014-of-00019.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00014-of-00019.safetensors", "model.layers.14.self_attn.qkv_proj.weight": "model-00015-of-00019.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00015-of-00019.safetensors", "model.layers.14.mlp.gate_up_proj.weight": "model-00015-of-00019.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00015-of-00019.safetensors", "model.layers.15.self_attn.qkv_proj.weight": "model-00016-of-00019.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00016-of-00019.safetensors", "model.layers.15.mlp.gate_up_proj.weight": "model-00016-of-00019.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00016-of-00019.safetensors", "model.layers.16.self_attn.qkv_proj.weight": "model-00017-of-00019.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00017-of-00019.safetensors", "model.layers.16.mlp.gate_up_proj.weight": "model-00017-of-00019.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00017-of-00019.safetensors", "model.layers.17.self_attn.qkv_proj.weight": "model-00018-of-00019.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00018-of-00019.safetensors", "model.layers.17.mlp.gate_up_proj.weight": "model-00018-of-00019.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00018-of-00019.safetensors", "model.embed_tokens.weight": "model-00019-of-00019.safetensors", "model.norm.weight": "model-00019-of-00019.safetensors", "model.layers.0.input_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.1.input_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.2.input_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.3.input_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.4.input_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.5.input_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.6.input_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.7.input_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.8.input_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.9.input_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.10.input_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.11.input_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.12.input_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.13.input_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.14.input_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.15.input_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.16.input_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.17.input_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00019-of-00019.safetensors"}}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 2306056192
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00019-of-00019.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00019-of-00019.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00019.safetensors",
9
+ "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00019.safetensors",
10
+ "model.layers.0.post_attention_layernorm.weight": "model-00019-of-00019.safetensors",
11
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00019.safetensors",
12
+ "model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00019.safetensors",
13
+ "model.layers.1.input_layernorm.weight": "model-00019-of-00019.safetensors",
14
+ "model.layers.1.mlp.down_proj.weight": "model-00002-of-00019.safetensors",
15
+ "model.layers.1.mlp.gate_up_proj.weight": "model-00002-of-00019.safetensors",
16
+ "model.layers.1.post_attention_layernorm.weight": "model-00019-of-00019.safetensors",
17
+ "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00019.safetensors",
18
+ "model.layers.1.self_attn.qkv_proj.weight": "model-00002-of-00019.safetensors",
19
+ "model.layers.10.input_layernorm.weight": "model-00019-of-00019.safetensors",
20
+ "model.layers.10.mlp.down_proj.weight": "model-00011-of-00019.safetensors",
21
+ "model.layers.10.mlp.gate_up_proj.weight": "model-00011-of-00019.safetensors",
22
+ "model.layers.10.post_attention_layernorm.weight": "model-00019-of-00019.safetensors",
23
+ "model.layers.10.self_attn.o_proj.weight": "model-00011-of-00019.safetensors",
24
+ "model.layers.10.self_attn.qkv_proj.weight": "model-00011-of-00019.safetensors",
25
+ "model.layers.11.input_layernorm.weight": "model-00019-of-00019.safetensors",
26
+ "model.layers.11.mlp.down_proj.weight": "model-00012-of-00019.safetensors",
27
+ "model.layers.11.mlp.gate_up_proj.weight": "model-00012-of-00019.safetensors",
28
+ "model.layers.11.post_attention_layernorm.weight": "model-00019-of-00019.safetensors",
29
+ "model.layers.11.self_attn.o_proj.weight": "model-00012-of-00019.safetensors",
30
+ "model.layers.11.self_attn.qkv_proj.weight": "model-00012-of-00019.safetensors",
31
+ "model.layers.12.input_layernorm.weight": "model-00019-of-00019.safetensors",
32
+ "model.layers.12.mlp.down_proj.weight": "model-00013-of-00019.safetensors",
33
+ "model.layers.12.mlp.gate_up_proj.weight": "model-00013-of-00019.safetensors",
34
+ "model.layers.12.post_attention_layernorm.weight": "model-00019-of-00019.safetensors",
35
+ "model.layers.12.self_attn.o_proj.weight": "model-00013-of-00019.safetensors",
36
+ "model.layers.12.self_attn.qkv_proj.weight": "model-00013-of-00019.safetensors",
37
+ "model.layers.13.input_layernorm.weight": "model-00019-of-00019.safetensors",
38
+ "model.layers.13.mlp.down_proj.weight": "model-00014-of-00019.safetensors",
39
+ "model.layers.13.mlp.gate_up_proj.weight": "model-00014-of-00019.safetensors",
40
+ "model.layers.13.post_attention_layernorm.weight": "model-00019-of-00019.safetensors",
41
+ "model.layers.13.self_attn.o_proj.weight": "model-00014-of-00019.safetensors",
42
+ "model.layers.13.self_attn.qkv_proj.weight": "model-00014-of-00019.safetensors",
43
+ "model.layers.14.input_layernorm.weight": "model-00019-of-00019.safetensors",
44
+ "model.layers.14.mlp.down_proj.weight": "model-00015-of-00019.safetensors",
45
+ "model.layers.14.mlp.gate_up_proj.weight": "model-00015-of-00019.safetensors",
46
+ "model.layers.14.post_attention_layernorm.weight": "model-00019-of-00019.safetensors",
47
+ "model.layers.14.self_attn.o_proj.weight": "model-00015-of-00019.safetensors",
48
+ "model.layers.14.self_attn.qkv_proj.weight": "model-00015-of-00019.safetensors",
49
+ "model.layers.15.input_layernorm.weight": "model-00019-of-00019.safetensors",
50
+ "model.layers.15.mlp.down_proj.weight": "model-00016-of-00019.safetensors",
51
+ "model.layers.15.mlp.gate_up_proj.weight": "model-00016-of-00019.safetensors",
52
+ "model.layers.15.post_attention_layernorm.weight": "model-00019-of-00019.safetensors",
53
+ "model.layers.15.self_attn.o_proj.weight": "model-00016-of-00019.safetensors",
54
+ "model.layers.15.self_attn.qkv_proj.weight": "model-00016-of-00019.safetensors",
55
+ "model.layers.16.input_layernorm.weight": "model-00019-of-00019.safetensors",
56
+ "model.layers.16.mlp.down_proj.weight": "model-00017-of-00019.safetensors",
57
+ "model.layers.16.mlp.gate_up_proj.weight": "model-00017-of-00019.safetensors",
58
+ "model.layers.16.post_attention_layernorm.weight": "model-00019-of-00019.safetensors",
59
+ "model.layers.16.self_attn.o_proj.weight": "model-00017-of-00019.safetensors",
60
+ "model.layers.16.self_attn.qkv_proj.weight": "model-00017-of-00019.safetensors",
61
+ "model.layers.17.input_layernorm.weight": "model-00019-of-00019.safetensors",
62
+ "model.layers.17.mlp.down_proj.weight": "model-00018-of-00019.safetensors",
63
+ "model.layers.17.mlp.gate_up_proj.weight": "model-00018-of-00019.safetensors",
64
+ "model.layers.17.post_attention_layernorm.weight": "model-00019-of-00019.safetensors",
65
+ "model.layers.17.self_attn.o_proj.weight": "model-00018-of-00019.safetensors",
66
+ "model.layers.17.self_attn.qkv_proj.weight": "model-00018-of-00019.safetensors",
67
+ "model.layers.2.input_layernorm.weight": "model-00019-of-00019.safetensors",
68
+ "model.layers.2.mlp.down_proj.weight": "model-00003-of-00019.safetensors",
69
+ "model.layers.2.mlp.gate_up_proj.weight": "model-00003-of-00019.safetensors",
70
+ "model.layers.2.post_attention_layernorm.weight": "model-00019-of-00019.safetensors",
71
+ "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00019.safetensors",
72
+ "model.layers.2.self_attn.qkv_proj.weight": "model-00003-of-00019.safetensors",
73
+ "model.layers.3.input_layernorm.weight": "model-00019-of-00019.safetensors",
74
+ "model.layers.3.mlp.down_proj.weight": "model-00004-of-00019.safetensors",
75
+ "model.layers.3.mlp.gate_up_proj.weight": "model-00004-of-00019.safetensors",
76
+ "model.layers.3.post_attention_layernorm.weight": "model-00019-of-00019.safetensors",
77
+ "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00019.safetensors",
78
+ "model.layers.3.self_attn.qkv_proj.weight": "model-00004-of-00019.safetensors",
79
+ "model.layers.4.input_layernorm.weight": "model-00019-of-00019.safetensors",
80
+ "model.layers.4.mlp.down_proj.weight": "model-00005-of-00019.safetensors",
81
+ "model.layers.4.mlp.gate_up_proj.weight": "model-00005-of-00019.safetensors",
82
+ "model.layers.4.post_attention_layernorm.weight": "model-00019-of-00019.safetensors",
83
+ "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00019.safetensors",
84
+ "model.layers.4.self_attn.qkv_proj.weight": "model-00005-of-00019.safetensors",
85
+ "model.layers.5.input_layernorm.weight": "model-00019-of-00019.safetensors",
86
+ "model.layers.5.mlp.down_proj.weight": "model-00006-of-00019.safetensors",
87
+ "model.layers.5.mlp.gate_up_proj.weight": "model-00006-of-00019.safetensors",
88
+ "model.layers.5.post_attention_layernorm.weight": "model-00019-of-00019.safetensors",
89
+ "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00019.safetensors",
90
+ "model.layers.5.self_attn.qkv_proj.weight": "model-00006-of-00019.safetensors",
91
+ "model.layers.6.input_layernorm.weight": "model-00019-of-00019.safetensors",
92
+ "model.layers.6.mlp.down_proj.weight": "model-00007-of-00019.safetensors",
93
+ "model.layers.6.mlp.gate_up_proj.weight": "model-00007-of-00019.safetensors",
94
+ "model.layers.6.post_attention_layernorm.weight": "model-00019-of-00019.safetensors",
95
+ "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00019.safetensors",
96
+ "model.layers.6.self_attn.qkv_proj.weight": "model-00007-of-00019.safetensors",
97
+ "model.layers.7.input_layernorm.weight": "model-00019-of-00019.safetensors",
98
+ "model.layers.7.mlp.down_proj.weight": "model-00008-of-00019.safetensors",
99
+ "model.layers.7.mlp.gate_up_proj.weight": "model-00008-of-00019.safetensors",
100
+ "model.layers.7.post_attention_layernorm.weight": "model-00019-of-00019.safetensors",
101
+ "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00019.safetensors",
102
+ "model.layers.7.self_attn.qkv_proj.weight": "model-00008-of-00019.safetensors",
103
+ "model.layers.8.input_layernorm.weight": "model-00019-of-00019.safetensors",
104
+ "model.layers.8.mlp.down_proj.weight": "model-00009-of-00019.safetensors",
105
+ "model.layers.8.mlp.gate_up_proj.weight": "model-00009-of-00019.safetensors",
106
+ "model.layers.8.post_attention_layernorm.weight": "model-00019-of-00019.safetensors",
107
+ "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00019.safetensors",
108
+ "model.layers.8.self_attn.qkv_proj.weight": "model-00009-of-00019.safetensors",
109
+ "model.layers.9.input_layernorm.weight": "model-00019-of-00019.safetensors",
110
+ "model.layers.9.mlp.down_proj.weight": "model-00010-of-00019.safetensors",
111
+ "model.layers.9.mlp.gate_up_proj.weight": "model-00010-of-00019.safetensors",
112
+ "model.layers.9.post_attention_layernorm.weight": "model-00019-of-00019.safetensors",
113
+ "model.layers.9.self_attn.o_proj.weight": "model-00010-of-00019.safetensors",
114
+ "model.layers.9.self_attn.qkv_proj.weight": "model-00010-of-00019.safetensors",
115
+ "model.norm.weight": "model-00019-of-00019.safetensors"
116
+ }
117
+ }
tokenizer.json CHANGED
@@ -20,6 +20,15 @@
20
  "rstrip": false,
21
  "normalized": false,
22
  "special": true
 
 
 
 
 
 
 
 
 
23
  }
24
  ],
25
  "normalizer": null,
@@ -123,7 +132,8 @@
123
  "₄ ": 29,
124
  "₅ ": 30,
125
  "₆ ": 31,
126
- "</THINKING>": 32
 
127
  },
128
  "unk_token": "<unk>"
129
  }
 
20
  "rstrip": false,
21
  "normalized": false,
22
  "special": true
23
+ },
24
+ {
25
+ "id": 33,
26
+ "content": "<unk>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
  }
33
  ],
34
  "normalizer": null,
 
132
  "₄ ": 29,
133
  "₅ ": 30,
134
  "₆ ": 31,
135
+ "</THINKING>": 32,
136
+ "<unk>": 33
137
  },
138
  "unk_token": "<unk>"
139
  }
tokenizer_config.json CHANGED
@@ -4,5 +4,5 @@
4
  "eos_token": "<eos>",
5
  "model_max_length": 1000000000000000019884624838656,
6
  "tokenizer_class": "TokenizersBackend",
7
- "unk_token": null
8
  }
 
4
  "eos_token": "<eos>",
5
  "model_max_length": 1000000000000000019884624838656,
6
  "tokenizer_class": "TokenizersBackend",
7
+ "unk_token": "<unk>"
8
  }