bogdankostic
commited on
Upload 8 files
Browse files- .gitattributes +1 -0
- config.json +237 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +3 -0
- tokenizer_config.json +54 -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
|
config.json
ADDED
@@ -0,0 +1,237 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "FacebookAI/xlm-roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "labor_shortage",
|
15 |
+
"1": "supply_shortage",
|
16 |
+
"2": "environmental_damage",
|
17 |
+
"3": "supplying",
|
18 |
+
"4": "fundraise",
|
19 |
+
"5": "penalty_payment",
|
20 |
+
"6": "site_closure",
|
21 |
+
"7": "Co2_emission",
|
22 |
+
"8": "partnership",
|
23 |
+
"9": "discrimination",
|
24 |
+
"10": "rebranding",
|
25 |
+
"11": "RnD_opening",
|
26 |
+
"12": "IT_incidents",
|
27 |
+
"13": "bankruptcy",
|
28 |
+
"14": "logistics_disruption",
|
29 |
+
"15": "harassment",
|
30 |
+
"16": "financial_warnings",
|
31 |
+
"17": "ipo",
|
32 |
+
"18": "legal_embroilment",
|
33 |
+
"19": "extend_contract",
|
34 |
+
"20": "profit_decrease",
|
35 |
+
"21": "revenue_decrease",
|
36 |
+
"22": "trade_fair",
|
37 |
+
"23": "corruption",
|
38 |
+
"24": "work_standards",
|
39 |
+
"25": "sign_agreement",
|
40 |
+
"26": "protest",
|
41 |
+
"27": "strike",
|
42 |
+
"28": "joint_venture",
|
43 |
+
"29": "power_outage",
|
44 |
+
"30": "contract_breach",
|
45 |
+
"31": "win_bid",
|
46 |
+
"32": "industrial_fire",
|
47 |
+
"33": "end_partnership",
|
48 |
+
"34": "record_success",
|
49 |
+
"35": "enter_market",
|
50 |
+
"36": "political_unrest",
|
51 |
+
"37": "win_contract",
|
52 |
+
"38": "investigation",
|
53 |
+
"39": "company_merger",
|
54 |
+
"40": "child_labor",
|
55 |
+
"41": "investment",
|
56 |
+
"42": "chemical_accident",
|
57 |
+
"43": "get_certification",
|
58 |
+
"44": "water_consumption",
|
59 |
+
"45": "launch_tender",
|
60 |
+
"46": "recall_product",
|
61 |
+
"47": "strategy_change",
|
62 |
+
"48": "open_fund",
|
63 |
+
"49": "start_project",
|
64 |
+
"50": "withdraw",
|
65 |
+
"51": "partial_acquisition",
|
66 |
+
"52": "acquisition_sales",
|
67 |
+
"53": "patent_application",
|
68 |
+
"54": "management_change",
|
69 |
+
"55": "product_sales",
|
70 |
+
"56": "technology_innovation",
|
71 |
+
"57": "forced_labor",
|
72 |
+
"58": "demand",
|
73 |
+
"59": "industrial_explosion",
|
74 |
+
"60": "extend_partnership",
|
75 |
+
"61": "product_failure",
|
76 |
+
"62": "win_tender",
|
77 |
+
"63": "labor_union",
|
78 |
+
"64": "get_approval",
|
79 |
+
"65": "antitrust",
|
80 |
+
"66": "profit_increase",
|
81 |
+
"67": "sponsorship",
|
82 |
+
"68": "support",
|
83 |
+
"69": "sanctions",
|
84 |
+
"70": "select_provider",
|
85 |
+
"71": "production_halt",
|
86 |
+
"72": "job_increase",
|
87 |
+
"73": "acquisition",
|
88 |
+
"74": "water_pollution",
|
89 |
+
"75": "person_leave",
|
90 |
+
"76": "industrial_accident",
|
91 |
+
"77": "data_privacy",
|
92 |
+
"78": "receive_order",
|
93 |
+
"79": "lawsuit",
|
94 |
+
"80": "layoff",
|
95 |
+
"81": "natural_disaster",
|
96 |
+
"82": "market_exit",
|
97 |
+
"83": "revenue_increase",
|
98 |
+
"84": "bidding",
|
99 |
+
"85": "price_hike",
|
100 |
+
"86": "industrial_delay",
|
101 |
+
"87": "person_hired",
|
102 |
+
"88": "air_pollution",
|
103 |
+
"89": "site_expansion",
|
104 |
+
"90": "award_winning",
|
105 |
+
"91": "company_dispute",
|
106 |
+
"92": "mine_accident",
|
107 |
+
"93": "memorandum_of_understanding",
|
108 |
+
"94": "accusation",
|
109 |
+
"95": "salary_conditions",
|
110 |
+
"96": "negotiations",
|
111 |
+
"97": "occupational_safety",
|
112 |
+
"98": "resume_operations",
|
113 |
+
"99": "production_expansion",
|
114 |
+
"100": "gas_leaks",
|
115 |
+
"101": "shareholder_activities"
|
116 |
+
},
|
117 |
+
"initializer_range": 0.02,
|
118 |
+
"intermediate_size": 3072,
|
119 |
+
"label2id": {
|
120 |
+
"Co2_emission": 7,
|
121 |
+
"IT_incidents": 12,
|
122 |
+
"RnD_opening": 11,
|
123 |
+
"accusation": 94,
|
124 |
+
"acquisition": 73,
|
125 |
+
"acquisition_sales": 52,
|
126 |
+
"air_pollution": 88,
|
127 |
+
"antitrust": 65,
|
128 |
+
"award_winning": 90,
|
129 |
+
"bankruptcy": 13,
|
130 |
+
"bidding": 84,
|
131 |
+
"chemical_accident": 42,
|
132 |
+
"child_labor": 40,
|
133 |
+
"company_dispute": 91,
|
134 |
+
"company_merger": 39,
|
135 |
+
"contract_breach": 30,
|
136 |
+
"corruption": 23,
|
137 |
+
"data_privacy": 77,
|
138 |
+
"demand": 58,
|
139 |
+
"discrimination": 9,
|
140 |
+
"end_partnership": 33,
|
141 |
+
"enter_market": 35,
|
142 |
+
"environmental_damage": 2,
|
143 |
+
"extend_contract": 19,
|
144 |
+
"extend_partnership": 60,
|
145 |
+
"financial_warnings": 16,
|
146 |
+
"forced_labor": 57,
|
147 |
+
"fundraise": 4,
|
148 |
+
"gas_leaks": 100,
|
149 |
+
"get_approval": 64,
|
150 |
+
"get_certification": 43,
|
151 |
+
"harassment": 15,
|
152 |
+
"industrial_accident": 76,
|
153 |
+
"industrial_delay": 86,
|
154 |
+
"industrial_explosion": 59,
|
155 |
+
"industrial_fire": 32,
|
156 |
+
"investigation": 38,
|
157 |
+
"investment": 41,
|
158 |
+
"ipo": 17,
|
159 |
+
"job_increase": 72,
|
160 |
+
"joint_venture": 28,
|
161 |
+
"labor_shortage": 0,
|
162 |
+
"labor_union": 63,
|
163 |
+
"launch_tender": 45,
|
164 |
+
"lawsuit": 79,
|
165 |
+
"layoff": 80,
|
166 |
+
"legal_embroilment": 18,
|
167 |
+
"logistics_disruption": 14,
|
168 |
+
"management_change": 54,
|
169 |
+
"market_exit": 82,
|
170 |
+
"memorandum_of_understanding": 93,
|
171 |
+
"mine_accident": 92,
|
172 |
+
"natural_disaster": 81,
|
173 |
+
"negotiations": 96,
|
174 |
+
"occupational_safety": 97,
|
175 |
+
"open_fund": 48,
|
176 |
+
"partial_acquisition": 51,
|
177 |
+
"partnership": 8,
|
178 |
+
"patent_application": 53,
|
179 |
+
"penalty_payment": 5,
|
180 |
+
"person_hired": 87,
|
181 |
+
"person_leave": 75,
|
182 |
+
"political_unrest": 36,
|
183 |
+
"power_outage": 29,
|
184 |
+
"price_hike": 85,
|
185 |
+
"product_failure": 61,
|
186 |
+
"product_sales": 55,
|
187 |
+
"production_expansion": 99,
|
188 |
+
"production_halt": 71,
|
189 |
+
"profit_decrease": 20,
|
190 |
+
"profit_increase": 66,
|
191 |
+
"protest": 26,
|
192 |
+
"rebranding": 10,
|
193 |
+
"recall_product": 46,
|
194 |
+
"receive_order": 78,
|
195 |
+
"record_success": 34,
|
196 |
+
"resume_operations": 98,
|
197 |
+
"revenue_decrease": 21,
|
198 |
+
"revenue_increase": 83,
|
199 |
+
"salary_conditions": 95,
|
200 |
+
"sanctions": 69,
|
201 |
+
"select_provider": 70,
|
202 |
+
"shareholder_activities": 101,
|
203 |
+
"sign_agreement": 25,
|
204 |
+
"site_closure": 6,
|
205 |
+
"site_expansion": 89,
|
206 |
+
"sponsorship": 67,
|
207 |
+
"start_project": 49,
|
208 |
+
"strategy_change": 47,
|
209 |
+
"strike": 27,
|
210 |
+
"supply_shortage": 1,
|
211 |
+
"supplying": 3,
|
212 |
+
"support": 68,
|
213 |
+
"technology_innovation": 56,
|
214 |
+
"trade_fair": 22,
|
215 |
+
"water_consumption": 44,
|
216 |
+
"water_pollution": 74,
|
217 |
+
"win_bid": 31,
|
218 |
+
"win_contract": 37,
|
219 |
+
"win_tender": 62,
|
220 |
+
"withdraw": 50,
|
221 |
+
"work_standards": 24
|
222 |
+
},
|
223 |
+
"layer_norm_eps": 1e-05,
|
224 |
+
"max_position_embeddings": 514,
|
225 |
+
"model_type": "xlm-roberta",
|
226 |
+
"num_attention_heads": 12,
|
227 |
+
"num_hidden_layers": 12,
|
228 |
+
"output_past": true,
|
229 |
+
"pad_token_id": 1,
|
230 |
+
"position_embedding_type": "absolute",
|
231 |
+
"problem_type": "single_label_classification",
|
232 |
+
"torch_dtype": "float32",
|
233 |
+
"transformers_version": "4.41.2",
|
234 |
+
"type_vocab_size": 1,
|
235 |
+
"use_cache": true,
|
236 |
+
"vocab_size": 250002
|
237 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:203491a9601b2569ff79ba6a3fc75a3fceba4abc4f1e0ccd1f947a2e6d6004de
|
3 |
+
size 1112512616
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e7df6da80196b9b46582da87ec976eb845732596d3cc1d68e394ce18467adca
|
3 |
+
size 2225144826
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:508eb622d4a7c35b406349092b6f045d9af0f9e3bf1c553dd173144324e481d4
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a68a362e3b1ab798069e45e18c38472aca7082a5c1002880d6b9bea168696d16
|
3 |
+
size 1064
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ffb37461c391f096759f4a9bbbc329da0f36952f88bab061fcf84940c022e98
|
3 |
+
size 17082999
|
tokenizer_config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"250001": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": true,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"bos_token": "<s>",
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "<s>",
|
47 |
+
"eos_token": "</s>",
|
48 |
+
"mask_token": "<mask>",
|
49 |
+
"model_max_length": 512,
|
50 |
+
"pad_token": "<pad>",
|
51 |
+
"sep_token": "</s>",
|
52 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
53 |
+
"unk_token": "<unk>"
|
54 |
+
}
|