Upload RobertaForSequenceClassification
Browse files- README.md +199 -0
- config.json +74 -34
- model.safetensors +3 -0
README.md
ADDED
@@ -0,0 +1,199 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
tags: []
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "model/
|
3 |
"architectures": [
|
4 |
"RobertaForSequenceClassification"
|
5 |
],
|
@@ -11,42 +11,82 @@
|
|
11 |
"hidden_dropout_prob": 0.1,
|
12 |
"hidden_size": 768,
|
13 |
"id2label": {
|
14 |
-
"0": "
|
15 |
-
"1": "
|
16 |
-
"2": "
|
17 |
-
"3": "
|
18 |
-
"4": "
|
19 |
-
"5": "
|
20 |
-
"6": "
|
21 |
-
"7": "
|
22 |
-
"8": "
|
23 |
-
"9": "
|
24 |
-
"10": "
|
25 |
-
"11": "
|
26 |
-
"12": "
|
27 |
-
"13": "
|
28 |
-
"14": "
|
29 |
-
"15": "
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
30 |
},
|
31 |
"initializer_range": 0.02,
|
32 |
"intermediate_size": 3072,
|
33 |
"label2id": {
|
34 |
-
"
|
35 |
-
"
|
36 |
-
"
|
37 |
-
"
|
38 |
-
"
|
39 |
-
"
|
40 |
-
"
|
41 |
-
"
|
42 |
-
"
|
43 |
-
"
|
44 |
-
"
|
45 |
-
"
|
46 |
-
"
|
47 |
-
"
|
48 |
-
"
|
49 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
50 |
},
|
51 |
"layer_norm_eps": 1e-05,
|
52 |
"max_position_embeddings": 514,
|
@@ -57,7 +97,7 @@
|
|
57 |
"position_embedding_type": "absolute",
|
58 |
"problem_type": "single_label_classification",
|
59 |
"torch_dtype": "float32",
|
60 |
-
"transformers_version": "4.
|
61 |
"type_vocab_size": 1,
|
62 |
"use_cache": true,
|
63 |
"vocab_size": 50265
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "model/bea_classifier_v2.1_36",
|
3 |
"architectures": [
|
4 |
"RobertaForSequenceClassification"
|
5 |
],
|
|
|
11 |
"hidden_dropout_prob": 0.1,
|
12 |
"hidden_size": 768,
|
13 |
"id2label": {
|
14 |
+
"0": "Academic_Activity",
|
15 |
+
"1": "Acquisition",
|
16 |
+
"2": "Art_Culture",
|
17 |
+
"3": "Company_Company_Partnership",
|
18 |
+
"4": "Company_Compliance_Issues",
|
19 |
+
"5": "Company_Contract",
|
20 |
+
"6": "Company_Event",
|
21 |
+
"7": "Company_Finance",
|
22 |
+
"8": "Company_Governance",
|
23 |
+
"9": "Company_Insight",
|
24 |
+
"10": "Company_Invest",
|
25 |
+
"11": "Company_Government_Partnership",
|
26 |
+
"12": "Company_Patent",
|
27 |
+
"13": "Company_Product_Stop",
|
28 |
+
"14": "Company_Sale",
|
29 |
+
"15": "Company_Startup",
|
30 |
+
"16": "Company_Supply_Disruption",
|
31 |
+
"17": "Company_Workforce_Dynamic",
|
32 |
+
"18": "Competitive_Landscape",
|
33 |
+
"19": "Crypto",
|
34 |
+
"20": "Disaster_ManMade",
|
35 |
+
"21": "Disaster_Natural",
|
36 |
+
"22": "Economic_Indicator_Lagging",
|
37 |
+
"23": "Economic_Indicator_Leading",
|
38 |
+
"24": "Government_Invest",
|
39 |
+
"25": "Government_Policy",
|
40 |
+
"26": "Government_Politic",
|
41 |
+
"27": "Market_Outlook",
|
42 |
+
"28": "Other",
|
43 |
+
"29": "Product_Issues",
|
44 |
+
"30": "Product_Release",
|
45 |
+
"31": "Product_Rumor",
|
46 |
+
"32": "Product_Upgrade",
|
47 |
+
"33": "Sport",
|
48 |
+
"34": "Supply_Environment",
|
49 |
+
"35": "Technology_Usecase"
|
50 |
},
|
51 |
"initializer_range": 0.02,
|
52 |
"intermediate_size": 3072,
|
53 |
"label2id": {
|
54 |
+
"Academic_Activity": 0,
|
55 |
+
"Acquisition": 1,
|
56 |
+
"Art_Culture": 2,
|
57 |
+
"Company_Company_Partnership": 3,
|
58 |
+
"Company_Compliance_Issues": 4,
|
59 |
+
"Company_Contract": 5,
|
60 |
+
"Company_Event": 6,
|
61 |
+
"Company_Finance": 7,
|
62 |
+
"Company_Governance": 8,
|
63 |
+
"Company_Government_Partnership": 11,
|
64 |
+
"Company_Insight": 9,
|
65 |
+
"Company_Invest": 10,
|
66 |
+
"Company_Patent": 12,
|
67 |
+
"Company_Product_Stop": 13,
|
68 |
+
"Company_Sale": 14,
|
69 |
+
"Company_Startup": 15,
|
70 |
+
"Company_Supply_Disruption": 16,
|
71 |
+
"Company_Workforce_Dynamic": 17,
|
72 |
+
"Competitive_Landscape": 18,
|
73 |
+
"Crypto": 19,
|
74 |
+
"Disaster_ManMade": 20,
|
75 |
+
"Disaster_Natural": 21,
|
76 |
+
"Economic_Indicator_Lagging": 22,
|
77 |
+
"Economic_Indicator_Leading": 23,
|
78 |
+
"Government_Invest": 24,
|
79 |
+
"Government_Policy": 25,
|
80 |
+
"Government_Politic": 26,
|
81 |
+
"Market_Outlook": 27,
|
82 |
+
"Other": 28,
|
83 |
+
"Product_Issues": 29,
|
84 |
+
"Product_Release": 30,
|
85 |
+
"Product_Rumor": 31,
|
86 |
+
"Product_Upgrade": 32,
|
87 |
+
"Sport": 33,
|
88 |
+
"Supply_Environment": 34,
|
89 |
+
"Technology_Usecase": 35
|
90 |
},
|
91 |
"layer_norm_eps": 1e-05,
|
92 |
"max_position_embeddings": 514,
|
|
|
97 |
"position_embedding_type": "absolute",
|
98 |
"problem_type": "single_label_classification",
|
99 |
"torch_dtype": "float32",
|
100 |
+
"transformers_version": "4.38.2",
|
101 |
"type_vocab_size": 1,
|
102 |
"use_cache": true,
|
103 |
"vocab_size": 50265
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f6acd2f47bdc47ea9a8004f23050ecd85ecfc608047f3c684b331dc256aefe0
|
3 |
+
size 498717408
|