Auditt commited on
Commit
e179fad
Β·
verified Β·
1 Parent(s): c62b4a2

Training in progress, epoch 0

Browse files
added_tokens.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "Ξ΅": 100315,
3
+ "Ο‡": 100297,
4
+ "β†’": 100312,
5
+ "↦": 100310,
6
+ "∧": 100286,
7
+ "β‰ ": 100304,
8
+ "≀": 100306,
9
+ "β‰₯": 100287,
10
+ "β‹€": 100292,
11
+ "⋁": 100282,
12
+ "βŸ‚": 100290,
13
+ "γ€ˆ": 100299,
14
+ "〉": 100280,
15
+ "𐔰": 100314,
16
+ "𐔱": 100308,
17
+ "𐔲": 100278,
18
+ "𐔳": 100303,
19
+ "𐔷": 100305,
20
+ "𐔸": 100285,
21
+ "𐔻": 100301,
22
+ "𐔾": 100279,
23
+ "𐕀": 100302,
24
+ "𐕂": 100309,
25
+ "𐕃": 100294,
26
+ "π•Š": 100298,
27
+ "π•Ž": 100311,
28
+ "𐕏": 100291,
29
+ "𐕐": 100300,
30
+ "𐕕": 100296,
31
+ "𐕖": 100289,
32
+ "𐕙": 100295,
33
+ "𐕛": 100313,
34
+ "π•œ": 100284,
35
+ "π•ž": 100307,
36
+ "π•Ÿ": 100288,
37
+ "𐕠": 100283,
38
+ "𐕣": 100293,
39
+ "𝜎": 100281
40
+ }
chat_template.jinja ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {% set has_system = messages|selectattr('role', 'equalto', 'system')|list|length > 0 %}{% if not has_system %}{{ '<|im_start|>system
2
+ You are OLMo, a helpful function-calling AI assistant built by Ai2. Your date cutoff is November 2024, and your model weights are available at https://huggingface.co/allenai. You do not currently have access to any functions. <functions></functions><|im_end|>
3
+ ' }}{% endif %}{% for message in messages %}{% if message['role'] == 'system' %}{{ '<|im_start|>system
4
+ ' + message['content'] }}{% if message.get('functions', none) is not none %}{{ ' <functions>' + message['functions'] + '</functions><|im_end|>
5
+ ' }}{% else %}{{ ' You do not currently have access to any functions. <functions></functions><|im_end|>
6
+ ' }}{% endif %}{% elif message['role'] == 'user' %}{% if message.get('functions', none) is not none %}{{ '<|im_start|>user
7
+ ' + message['content'] + '
8
+ ' + '<functions>' + message['functions'] + '</functions><|im_end|>
9
+ ' }}{% else %}{{ '<|im_start|>user
10
+ ' + message['content'] + '<|im_end|>
11
+ ' }}{% endif %}{% elif message['role'] == 'assistant' %}{{ '<|im_start|>assistant
12
+ ' }}{% if message.get('content', none) is not none %}{{ message['content'] }}{% endif %}{% if message.get('function_calls', none) is not none %}{{ '<function_calls>' + message['function_calls'] + '</function_calls>' }}{% endif %}{% if not loop.last %}{{ '<|im_end|>' + '
13
+ ' }}{% else %}{{ eos_token }}{% endif %}{% elif message['role'] == 'environment' %}{{ '<|im_start|>environment
14
+ ' + message['content'] + '<|im_end|>
15
+ ' }}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<|im_start|>assistant
16
+ <think>' }}{% endif %}{% endfor %}
config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Olmo3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": 100257,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 11008,
13
+ "layer_types": [
14
+ "sliding_attention",
15
+ "sliding_attention",
16
+ "sliding_attention",
17
+ "full_attention",
18
+ "sliding_attention",
19
+ "sliding_attention",
20
+ "sliding_attention",
21
+ "full_attention",
22
+ "sliding_attention",
23
+ "sliding_attention",
24
+ "sliding_attention",
25
+ "full_attention",
26
+ "sliding_attention",
27
+ "sliding_attention",
28
+ "sliding_attention",
29
+ "full_attention",
30
+ "sliding_attention",
31
+ "sliding_attention",
32
+ "sliding_attention",
33
+ "full_attention",
34
+ "sliding_attention",
35
+ "sliding_attention",
36
+ "sliding_attention",
37
+ "full_attention",
38
+ "sliding_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "full_attention",
42
+ "sliding_attention",
43
+ "sliding_attention",
44
+ "sliding_attention",
45
+ "full_attention"
46
+ ],
47
+ "max_position_embeddings": 65536,
48
+ "model_type": "olmo3",
49
+ "num_attention_heads": 32,
50
+ "num_hidden_layers": 32,
51
+ "num_key_value_heads": 32,
52
+ "pad_token_id": 100277,
53
+ "rms_norm_eps": 1e-06,
54
+ "rope_scaling": {
55
+ "attention_factor": 1.2079441541679836,
56
+ "beta_fast": 32,
57
+ "beta_slow": 1,
58
+ "factor": 8.0,
59
+ "original_max_position_embeddings": 8192,
60
+ "rope_type": "yarn"
61
+ },
62
+ "rope_theta": 500000,
63
+ "sliding_window": 4096,
64
+ "tie_word_embeddings": false,
65
+ "transformers_version": "4.57.0",
66
+ "use_cache": false,
67
+ "vocab_size": 100316
68
+ }
debug.log ADDED
The diff for this file is too large to render. See raw diff
 
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 100257
6
+ ],
7
+ "pad_token_id": 100277,
8
+ "transformers_version": "4.57.0"
9
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:388261a50fbf0eeb4bfe70a569864034136371be5e1eadf296c1c47a754a04ac
3
+ size 4970296272
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bd68cd0fe72c155079429d0dbebea051320beb1cca26dca7addffb189880c45
3
+ size 4981161496
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cd8746be0e467fc71540028f00a460140058054a59b338275cc02ce874c724a
3
+ size 4645228536
model.safetensors.index.json ADDED
@@ -0,0 +1,363 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 7298322432,
4
+ "total_size": 14596644864
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00003-of-00003.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
28
+ "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
30
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
31
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
32
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
33
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
34
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
35
+ "model.layers.10.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
36
+ "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
37
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
38
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
39
+ "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
40
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
41
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
42
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
43
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
44
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
45
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
46
+ "model.layers.11.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
47
+ "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
48
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
49
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
50
+ "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
51
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
52
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
53
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
54
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
55
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
56
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
57
+ "model.layers.12.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
58
+ "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
59
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
60
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
61
+ "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
62
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
63
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
64
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
65
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
66
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
67
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
68
+ "model.layers.13.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
69
+ "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
70
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
71
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
73
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
77
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
79
+ "model.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
83
+ "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
89
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.15.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
93
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.16.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.17.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
116
+ "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
117
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
118
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
119
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
120
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
121
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
122
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
123
+ "model.layers.18.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
124
+ "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
125
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
126
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
129
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
130
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
134
+ "model.layers.19.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
135
+ "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
136
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
137
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
138
+ "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
139
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
140
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
141
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
142
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
143
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
144
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
145
+ "model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
146
+ "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
147
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
148
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
149
+ "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
150
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
151
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
152
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
153
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
154
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
155
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
156
+ "model.layers.20.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
157
+ "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
158
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
159
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
160
+ "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
161
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
162
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
163
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
164
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
165
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
166
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
167
+ "model.layers.21.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
168
+ "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
169
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
170
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
171
+ "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
172
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
173
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
174
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
175
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
176
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
177
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
178
+ "model.layers.22.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
179
+ "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
180
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
181
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
182
+ "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
183
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
184
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
185
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
186
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
187
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
188
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
189
+ "model.layers.23.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
190
+ "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
191
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
192
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
193
+ "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
194
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
195
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
196
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
197
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
198
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
199
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
200
+ "model.layers.24.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
201
+ "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
202
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
203
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
204
+ "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
205
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
206
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
207
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
208
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
209
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
210
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
211
+ "model.layers.25.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
212
+ "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
213
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
214
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
215
+ "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
216
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
217
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
218
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
219
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
220
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
221
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
222
+ "model.layers.26.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
223
+ "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
224
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
225
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
226
+ "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
227
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
228
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
229
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
230
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
231
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
232
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
233
+ "model.layers.27.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
234
+ "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
235
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
236
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
237
+ "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
238
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
239
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
240
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
241
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
242
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
243
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
244
+ "model.layers.28.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
245
+ "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
246
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
247
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
248
+ "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
249
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
250
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
251
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
252
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
253
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
254
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
255
+ "model.layers.29.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
256
+ "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
257
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
258
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
259
+ "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
260
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
261
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
262
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
263
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
264
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
265
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
266
+ "model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
267
+ "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
268
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
269
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
270
+ "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
271
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
272
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
273
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
274
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
275
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
276
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
277
+ "model.layers.30.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
278
+ "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
279
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
280
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
281
+ "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
282
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
283
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
284
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
285
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
286
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
287
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
288
+ "model.layers.31.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
289
+ "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
290
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
291
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
292
+ "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
293
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
294
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
295
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
296
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
297
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
298
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
299
+ "model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
300
+ "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
301
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
302
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
303
+ "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
304
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
305
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
306
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
307
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
308
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
309
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
310
+ "model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
311
+ "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
312
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
313
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
314
+ "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
315
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
316
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
317
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
318
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
319
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
320
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
321
+ "model.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
322
+ "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
323
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
324
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
325
+ "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
326
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
327
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
328
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
329
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
330
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
331
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
332
+ "model.layers.7.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
333
+ "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
334
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
335
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
336
+ "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
337
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
338
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
339
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
340
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
341
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
342
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
343
+ "model.layers.8.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
344
+ "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
345
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
346
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
347
+ "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
348
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
349
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
350
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
351
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
352
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
353
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
354
+ "model.layers.9.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
355
+ "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
356
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
357
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
358
+ "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
359
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
360
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
361
+ "model.norm.weight": "model-00003-of-00003.safetensors"
362
+ }
363
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "<|pad|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,493 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "100256": {
5
+ "content": "<|extra_id_0|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": false
11
+ },
12
+ "100257": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "100258": {
21
+ "content": "<|fim_prefix|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "100259": {
29
+ "content": "<|fim_middle|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "100260": {
37
+ "content": "<|fim_suffix|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "100261": {
45
+ "content": "|||PHONE_NUMBER|||",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "100262": {
53
+ "content": "|||EMAIL_ADDRESS|||",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "100263": {
61
+ "content": "|||IP_ADDRESS|||",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "100264": {
69
+ "content": "<|im_start|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "100265": {
77
+ "content": "<|im_end|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "100266": {
85
+ "content": "<|extra_id_1|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "100267": {
93
+ "content": "<|extra_id_2|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "100268": {
101
+ "content": "<|extra_id_3|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "100269": {
109
+ "content": "<|extra_id_4|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": false
115
+ },
116
+ "100270": {
117
+ "content": "<|extra_id_5|>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "100271": {
125
+ "content": "<|extra_id_6|>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "100272": {
133
+ "content": "<|extra_id_7|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "100273": {
141
+ "content": "<|extra_id_8|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "100274": {
149
+ "content": "<|extra_id_9|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "100275": {
157
+ "content": "<|extra_id_10|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "100276": {
165
+ "content": "<|endofprompt|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "100277": {
173
+ "content": "<|pad|>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "100278": {
181
+ "content": "𐔲",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "100279": {
189
+ "content": "𐔾",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "100280": {
197
+ "content": "〉",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ },
204
+ "100281": {
205
+ "content": "𝜎",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": false
211
+ },
212
+ "100282": {
213
+ "content": "⋁",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": false
219
+ },
220
+ "100283": {
221
+ "content": "𐕠",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": false
227
+ },
228
+ "100284": {
229
+ "content": "π•œ",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": false
235
+ },
236
+ "100285": {
237
+ "content": "𐔸",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": false
243
+ },
244
+ "100286": {
245
+ "content": "∧",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": false
251
+ },
252
+ "100287": {
253
+ "content": "β‰₯",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": false
259
+ },
260
+ "100288": {
261
+ "content": "π•Ÿ",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": false
267
+ },
268
+ "100289": {
269
+ "content": "𐕖",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": false
275
+ },
276
+ "100290": {
277
+ "content": "βŸ‚",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": false
283
+ },
284
+ "100291": {
285
+ "content": "𐕏",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": false
291
+ },
292
+ "100292": {
293
+ "content": "β‹€",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": false
299
+ },
300
+ "100293": {
301
+ "content": "𐕣",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": false
307
+ },
308
+ "100294": {
309
+ "content": "𐕃",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": false
315
+ },
316
+ "100295": {
317
+ "content": "𐕙",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": false
323
+ },
324
+ "100296": {
325
+ "content": "𐕕",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": false
331
+ },
332
+ "100297": {
333
+ "content": "Ο‡",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": false
339
+ },
340
+ "100298": {
341
+ "content": "π•Š",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": false
347
+ },
348
+ "100299": {
349
+ "content": "γ€ˆ",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": false
355
+ },
356
+ "100300": {
357
+ "content": "𐕐",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": false
363
+ },
364
+ "100301": {
365
+ "content": "𐔻",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": false
371
+ },
372
+ "100302": {
373
+ "content": "𐕀",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": false
379
+ },
380
+ "100303": {
381
+ "content": "𐔳",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": false
387
+ },
388
+ "100304": {
389
+ "content": "β‰ ",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": false
395
+ },
396
+ "100305": {
397
+ "content": "𐔷",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": false
403
+ },
404
+ "100306": {
405
+ "content": "≀",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": false
411
+ },
412
+ "100307": {
413
+ "content": "π•ž",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": false
419
+ },
420
+ "100308": {
421
+ "content": "𐔱",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": false
427
+ },
428
+ "100309": {
429
+ "content": "𐕂",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": false
435
+ },
436
+ "100310": {
437
+ "content": "↦",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": false
443
+ },
444
+ "100311": {
445
+ "content": "π•Ž",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": false
451
+ },
452
+ "100312": {
453
+ "content": "β†’",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": false
459
+ },
460
+ "100313": {
461
+ "content": "𐕛",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": false
467
+ },
468
+ "100314": {
469
+ "content": "𐔰",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": false
475
+ },
476
+ "100315": {
477
+ "content": "Ξ΅",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": false
483
+ }
484
+ },
485
+ "bos_token": null,
486
+ "clean_up_tokenization_spaces": false,
487
+ "eos_token": "<|endoftext|>",
488
+ "extra_special_tokens": {},
489
+ "model_max_length": 65536,
490
+ "pad_token": "<|pad|>",
491
+ "tokenizer_class": "GPT2Tokenizer",
492
+ "unk_token": "<|endoftext|>"
493
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6962bf53823a69d4d2b73a07a651e443af5d51fc98c9e793c9abdaba6c7c69f1
3
+ size 8977
vocab.json ADDED
The diff for this file is too large to render. See raw diff