yangwang825 commited on
Commit
4cfc429
·
verified ·
1 Parent(s): ef80841

End of training

Browse files
.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
.gitignore ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ step_*
2
+ epoch_*
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
config.json ADDED
@@ -0,0 +1,203 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "UnmaskingQwen2ForTokenClassification"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151643,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 896,
10
+ "id2label": {
11
+ "0": "O",
12
+ "1": "B-medical_record_number",
13
+ "2": "I-medical_record_number",
14
+ "3": "B-date_of_birth",
15
+ "4": "I-date_of_birth",
16
+ "5": "B-ssn",
17
+ "6": "I-ssn",
18
+ "7": "B-date",
19
+ "8": "I-date",
20
+ "9": "B-first_name",
21
+ "10": "I-first_name",
22
+ "11": "B-email",
23
+ "12": "I-email",
24
+ "13": "B-last_name",
25
+ "14": "I-last_name",
26
+ "15": "B-customer_id",
27
+ "16": "I-customer_id",
28
+ "17": "B-employee_id",
29
+ "18": "I-employee_id",
30
+ "19": "B-name",
31
+ "20": "I-name",
32
+ "21": "B-street_address",
33
+ "22": "I-street_address",
34
+ "23": "B-phone_number",
35
+ "24": "I-phone_number",
36
+ "25": "B-ipv4",
37
+ "26": "I-ipv4",
38
+ "27": "B-credit_card_number",
39
+ "28": "I-credit_card_number",
40
+ "29": "B-license_plate",
41
+ "30": "I-license_plate",
42
+ "31": "B-address",
43
+ "32": "I-address",
44
+ "33": "B-user_name",
45
+ "34": "I-user_name",
46
+ "35": "B-device_identifier",
47
+ "36": "I-device_identifier",
48
+ "37": "B-bank_routing_number",
49
+ "38": "I-bank_routing_number",
50
+ "39": "B-date_time",
51
+ "40": "I-date_time",
52
+ "41": "B-company_name",
53
+ "42": "I-company_name",
54
+ "43": "B-unique_identifier",
55
+ "44": "I-unique_identifier",
56
+ "45": "B-biometric_identifier",
57
+ "46": "I-biometric_identifier",
58
+ "47": "B-account_number",
59
+ "48": "I-account_number",
60
+ "49": "B-city",
61
+ "50": "I-city",
62
+ "51": "B-certificate_license_number",
63
+ "52": "I-certificate_license_number",
64
+ "53": "B-time",
65
+ "54": "I-time",
66
+ "55": "B-postcode",
67
+ "56": "I-postcode",
68
+ "57": "B-vehicle_identifier",
69
+ "58": "I-vehicle_identifier",
70
+ "59": "B-coordinate",
71
+ "60": "I-coordinate",
72
+ "61": "B-country",
73
+ "62": "I-country",
74
+ "63": "B-api_key",
75
+ "64": "I-api_key",
76
+ "65": "B-ipv6",
77
+ "66": "I-ipv6",
78
+ "67": "B-password",
79
+ "68": "I-password",
80
+ "69": "B-health_plan_beneficiary_number",
81
+ "70": "I-health_plan_beneficiary_number",
82
+ "71": "B-national_id",
83
+ "72": "I-national_id",
84
+ "73": "B-tax_id",
85
+ "74": "I-tax_id",
86
+ "75": "B-url",
87
+ "76": "I-url",
88
+ "77": "B-state",
89
+ "78": "I-state",
90
+ "79": "B-swift_bic",
91
+ "80": "I-swift_bic",
92
+ "81": "B-cvv",
93
+ "82": "I-cvv",
94
+ "83": "B-pin",
95
+ "84": "I-pin"
96
+ },
97
+ "initializer_range": 0.02,
98
+ "intermediate_size": 4864,
99
+ "label2id": {
100
+ "B-account_number": 47,
101
+ "B-address": 31,
102
+ "B-api_key": 63,
103
+ "B-bank_routing_number": 37,
104
+ "B-biometric_identifier": 45,
105
+ "B-certificate_license_number": 51,
106
+ "B-city": 49,
107
+ "B-company_name": 41,
108
+ "B-coordinate": 59,
109
+ "B-country": 61,
110
+ "B-credit_card_number": 27,
111
+ "B-customer_id": 15,
112
+ "B-cvv": 81,
113
+ "B-date": 7,
114
+ "B-date_of_birth": 3,
115
+ "B-date_time": 39,
116
+ "B-device_identifier": 35,
117
+ "B-email": 11,
118
+ "B-employee_id": 17,
119
+ "B-first_name": 9,
120
+ "B-health_plan_beneficiary_number": 69,
121
+ "B-ipv4": 25,
122
+ "B-ipv6": 65,
123
+ "B-last_name": 13,
124
+ "B-license_plate": 29,
125
+ "B-medical_record_number": 1,
126
+ "B-name": 19,
127
+ "B-national_id": 71,
128
+ "B-password": 67,
129
+ "B-phone_number": 23,
130
+ "B-pin": 83,
131
+ "B-postcode": 55,
132
+ "B-ssn": 5,
133
+ "B-state": 77,
134
+ "B-street_address": 21,
135
+ "B-swift_bic": 79,
136
+ "B-tax_id": 73,
137
+ "B-time": 53,
138
+ "B-unique_identifier": 43,
139
+ "B-url": 75,
140
+ "B-user_name": 33,
141
+ "B-vehicle_identifier": 57,
142
+ "I-account_number": 48,
143
+ "I-address": 32,
144
+ "I-api_key": 64,
145
+ "I-bank_routing_number": 38,
146
+ "I-biometric_identifier": 46,
147
+ "I-certificate_license_number": 52,
148
+ "I-city": 50,
149
+ "I-company_name": 42,
150
+ "I-coordinate": 60,
151
+ "I-country": 62,
152
+ "I-credit_card_number": 28,
153
+ "I-customer_id": 16,
154
+ "I-cvv": 82,
155
+ "I-date": 8,
156
+ "I-date_of_birth": 4,
157
+ "I-date_time": 40,
158
+ "I-device_identifier": 36,
159
+ "I-email": 12,
160
+ "I-employee_id": 18,
161
+ "I-first_name": 10,
162
+ "I-health_plan_beneficiary_number": 70,
163
+ "I-ipv4": 26,
164
+ "I-ipv6": 66,
165
+ "I-last_name": 14,
166
+ "I-license_plate": 30,
167
+ "I-medical_record_number": 2,
168
+ "I-name": 20,
169
+ "I-national_id": 72,
170
+ "I-password": 68,
171
+ "I-phone_number": 24,
172
+ "I-pin": 84,
173
+ "I-postcode": 56,
174
+ "I-ssn": 6,
175
+ "I-state": 78,
176
+ "I-street_address": 22,
177
+ "I-swift_bic": 80,
178
+ "I-tax_id": 74,
179
+ "I-time": 54,
180
+ "I-unique_identifier": 44,
181
+ "I-url": 76,
182
+ "I-user_name": 34,
183
+ "I-vehicle_identifier": 58,
184
+ "O": 0
185
+ },
186
+ "max_position_embeddings": 32768,
187
+ "max_window_layers": 24,
188
+ "model_type": "qwen2",
189
+ "num_attention_heads": 14,
190
+ "num_hidden_layers": 24,
191
+ "num_key_value_heads": 2,
192
+ "rms_norm_eps": 1e-06,
193
+ "rope_scaling": null,
194
+ "rope_theta": 1000000.0,
195
+ "sliding_window": 32768,
196
+ "tie_word_embeddings": true,
197
+ "torch_dtype": "float32",
198
+ "transformers_version": "4.51.3",
199
+ "use_cache": true,
200
+ "use_mrope": false,
201
+ "use_sliding_window": false,
202
+ "vocab_size": 151936
203
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56e11d0f530579881ede646ebb4914bd05c7dba2083680d09c6c8e02c0772066
3
+ size 1976468620
modeling_unmasking_qwen3.py ADDED
File without changes
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e72410ddfe59d4ec8aeea923685710c76492112d74f5d127b86e2d08d65a3a4
3
+ size 11422174
tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|endoftext|>",
201
+ "errors": "replace",
202
+ "extra_special_tokens": {},
203
+ "model_max_length": 131072,
204
+ "pad_token": "<|endoftext|>",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff