Upload CrossEncoder
Browse files- README.md +200 -0
- config.json +33 -0
- model.safetensors +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +54 -0
README.md
ADDED
@@ -0,0 +1,200 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
tags:
|
4 |
+
- cross-encoder
|
5 |
+
---
|
6 |
+
|
7 |
+
# Model Card for Model ID
|
8 |
+
|
9 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
10 |
+
|
11 |
+
|
12 |
+
|
13 |
+
## Model Details
|
14 |
+
|
15 |
+
### Model Description
|
16 |
+
|
17 |
+
<!-- Provide a longer summary of what this model is. -->
|
18 |
+
|
19 |
+
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
|
20 |
+
|
21 |
+
- **Developed by:** [More Information Needed]
|
22 |
+
- **Funded by [optional]:** [More Information Needed]
|
23 |
+
- **Shared by [optional]:** [More Information Needed]
|
24 |
+
- **Model type:** [More Information Needed]
|
25 |
+
- **Language(s) (NLP):** [More Information Needed]
|
26 |
+
- **License:** [More Information Needed]
|
27 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
28 |
+
|
29 |
+
### Model Sources [optional]
|
30 |
+
|
31 |
+
<!-- Provide the basic links for the model. -->
|
32 |
+
|
33 |
+
- **Repository:** [More Information Needed]
|
34 |
+
- **Paper [optional]:** [More Information Needed]
|
35 |
+
- **Demo [optional]:** [More Information Needed]
|
36 |
+
|
37 |
+
## Uses
|
38 |
+
|
39 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
40 |
+
|
41 |
+
### Direct Use
|
42 |
+
|
43 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
44 |
+
|
45 |
+
[More Information Needed]
|
46 |
+
|
47 |
+
### Downstream Use [optional]
|
48 |
+
|
49 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
50 |
+
|
51 |
+
[More Information Needed]
|
52 |
+
|
53 |
+
### Out-of-Scope Use
|
54 |
+
|
55 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
56 |
+
|
57 |
+
[More Information Needed]
|
58 |
+
|
59 |
+
## Bias, Risks, and Limitations
|
60 |
+
|
61 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
62 |
+
|
63 |
+
[More Information Needed]
|
64 |
+
|
65 |
+
### Recommendations
|
66 |
+
|
67 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
68 |
+
|
69 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
70 |
+
|
71 |
+
## How to Get Started with the Model
|
72 |
+
|
73 |
+
Use the code below to get started with the model.
|
74 |
+
|
75 |
+
[More Information Needed]
|
76 |
+
|
77 |
+
## Training Details
|
78 |
+
|
79 |
+
### Training Data
|
80 |
+
|
81 |
+
<!-- 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. -->
|
82 |
+
|
83 |
+
[More Information Needed]
|
84 |
+
|
85 |
+
### Training Procedure
|
86 |
+
|
87 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
88 |
+
|
89 |
+
#### Preprocessing [optional]
|
90 |
+
|
91 |
+
[More Information Needed]
|
92 |
+
|
93 |
+
|
94 |
+
#### Training Hyperparameters
|
95 |
+
|
96 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
97 |
+
|
98 |
+
#### Speeds, Sizes, Times [optional]
|
99 |
+
|
100 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
101 |
+
|
102 |
+
[More Information Needed]
|
103 |
+
|
104 |
+
## Evaluation
|
105 |
+
|
106 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
107 |
+
|
108 |
+
### Testing Data, Factors & Metrics
|
109 |
+
|
110 |
+
#### Testing Data
|
111 |
+
|
112 |
+
<!-- This should link to a Dataset Card if possible. -->
|
113 |
+
|
114 |
+
[More Information Needed]
|
115 |
+
|
116 |
+
#### Factors
|
117 |
+
|
118 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
119 |
+
|
120 |
+
[More Information Needed]
|
121 |
+
|
122 |
+
#### Metrics
|
123 |
+
|
124 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
125 |
+
|
126 |
+
[More Information Needed]
|
127 |
+
|
128 |
+
### Results
|
129 |
+
|
130 |
+
[More Information Needed]
|
131 |
+
|
132 |
+
#### Summary
|
133 |
+
|
134 |
+
|
135 |
+
|
136 |
+
## Model Examination [optional]
|
137 |
+
|
138 |
+
<!-- Relevant interpretability work for the model goes here -->
|
139 |
+
|
140 |
+
[More Information Needed]
|
141 |
+
|
142 |
+
## Environmental Impact
|
143 |
+
|
144 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
145 |
+
|
146 |
+
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).
|
147 |
+
|
148 |
+
- **Hardware Type:** [More Information Needed]
|
149 |
+
- **Hours used:** [More Information Needed]
|
150 |
+
- **Cloud Provider:** [More Information Needed]
|
151 |
+
- **Compute Region:** [More Information Needed]
|
152 |
+
- **Carbon Emitted:** [More Information Needed]
|
153 |
+
|
154 |
+
## Technical Specifications [optional]
|
155 |
+
|
156 |
+
### Model Architecture and Objective
|
157 |
+
|
158 |
+
[More Information Needed]
|
159 |
+
|
160 |
+
### Compute Infrastructure
|
161 |
+
|
162 |
+
[More Information Needed]
|
163 |
+
|
164 |
+
#### Hardware
|
165 |
+
|
166 |
+
[More Information Needed]
|
167 |
+
|
168 |
+
#### Software
|
169 |
+
|
170 |
+
[More Information Needed]
|
171 |
+
|
172 |
+
## Citation [optional]
|
173 |
+
|
174 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
175 |
+
|
176 |
+
**BibTeX:**
|
177 |
+
|
178 |
+
[More Information Needed]
|
179 |
+
|
180 |
+
**APA:**
|
181 |
+
|
182 |
+
[More Information Needed]
|
183 |
+
|
184 |
+
## Glossary [optional]
|
185 |
+
|
186 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
187 |
+
|
188 |
+
[More Information Needed]
|
189 |
+
|
190 |
+
## More Information [optional]
|
191 |
+
|
192 |
+
[More Information Needed]
|
193 |
+
|
194 |
+
## Model Card Authors [optional]
|
195 |
+
|
196 |
+
[More Information Needed]
|
197 |
+
|
198 |
+
## Model Card Contact
|
199 |
+
|
200 |
+
[More Information Needed]
|
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "osiria/minilm-l12-h384-italian-cross-encoder",
|
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": 384,
|
13 |
+
"id2label": {
|
14 |
+
"0": "LABEL_0"
|
15 |
+
},
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 1536,
|
18 |
+
"label2id": {
|
19 |
+
"LABEL_0": 0
|
20 |
+
},
|
21 |
+
"layer_norm_eps": 1e-05,
|
22 |
+
"max_position_embeddings": 514,
|
23 |
+
"model_type": "xlm-roberta",
|
24 |
+
"num_attention_heads": 12,
|
25 |
+
"num_hidden_layers": 12,
|
26 |
+
"pad_token_id": 1,
|
27 |
+
"position_embedding_type": "absolute",
|
28 |
+
"torch_dtype": "float32",
|
29 |
+
"transformers_version": "4.46.2",
|
30 |
+
"type_vocab_size": 1,
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 30498
|
33 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7791a8210854b9473e291ba138d2927fb68424143448a12e3b44857e9d7d63c9
|
3 |
+
size 133430100
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
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 |
+
"30497": {
|
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 |
+
}
|