Addind graphics.
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- README.md +86 -0
- model_card/density.js +174 -0
- model_card/layer_images/layer_0_attention_output_dense.png +0 -0
- model_card/layer_images/layer_0_attention_self_key.png +0 -0
- model_card/layer_images/layer_0_attention_self_query.png +0 -0
- model_card/layer_images/layer_0_attention_self_value.png +0 -0
- model_card/layer_images/layer_0_intermediate_dense.png +0 -0
- model_card/layer_images/layer_0_output_dense.png +0 -0
- model_card/layer_images/layer_10_attention_output_dense.png +0 -0
- model_card/layer_images/layer_10_attention_self_key.png +0 -0
- model_card/layer_images/layer_10_attention_self_query.png +0 -0
- model_card/layer_images/layer_10_attention_self_value.png +0 -0
- model_card/layer_images/layer_10_intermediate_dense.png +0 -0
- model_card/layer_images/layer_10_output_dense.png +0 -0
- model_card/layer_images/layer_11_attention_output_dense.png +0 -0
- model_card/layer_images/layer_11_attention_self_key.png +0 -0
- model_card/layer_images/layer_11_attention_self_query.png +0 -0
- model_card/layer_images/layer_11_attention_self_value.png +0 -0
- model_card/layer_images/layer_11_intermediate_dense.png +0 -0
- model_card/layer_images/layer_11_output_dense.png +0 -0
- model_card/layer_images/layer_1_attention_output_dense.png +0 -0
- model_card/layer_images/layer_1_attention_self_key.png +0 -0
- model_card/layer_images/layer_1_attention_self_query.png +0 -0
- model_card/layer_images/layer_1_attention_self_value.png +0 -0
- model_card/layer_images/layer_1_intermediate_dense.png +0 -0
- model_card/layer_images/layer_1_output_dense.png +0 -0
- model_card/layer_images/layer_2_attention_output_dense.png +0 -0
- model_card/layer_images/layer_2_attention_self_key.png +0 -0
- model_card/layer_images/layer_2_attention_self_query.png +0 -0
- model_card/layer_images/layer_2_attention_self_value.png +0 -0
- model_card/layer_images/layer_2_intermediate_dense.png +0 -0
- model_card/layer_images/layer_2_output_dense.png +0 -0
- model_card/layer_images/layer_3_attention_output_dense.png +0 -0
- model_card/layer_images/layer_3_attention_self_key.png +0 -0
- model_card/layer_images/layer_3_attention_self_query.png +0 -0
- model_card/layer_images/layer_3_attention_self_value.png +0 -0
- model_card/layer_images/layer_3_intermediate_dense.png +0 -0
- model_card/layer_images/layer_3_output_dense.png +0 -0
- model_card/layer_images/layer_4_attention_output_dense.png +0 -0
- model_card/layer_images/layer_4_attention_self_key.png +0 -0
- model_card/layer_images/layer_4_attention_self_query.png +0 -0
- model_card/layer_images/layer_4_attention_self_value.png +0 -0
- model_card/layer_images/layer_4_intermediate_dense.png +0 -0
- model_card/layer_images/layer_4_output_dense.png +0 -0
- model_card/layer_images/layer_5_attention_output_dense.png +0 -0
- model_card/layer_images/layer_5_attention_self_key.png +0 -0
- model_card/layer_images/layer_5_attention_self_query.png +0 -0
- model_card/layer_images/layer_5_attention_self_value.png +0 -0
- model_card/layer_images/layer_5_intermediate_dense.png +0 -0
- model_card/layer_images/layer_5_output_dense.png +0 -0
README.md
ADDED
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language: en
|
3 |
+
thumbnail:
|
4 |
+
license: mit
|
5 |
+
tags:
|
6 |
+
- question-answering
|
7 |
+
- bert
|
8 |
+
- bert-base
|
9 |
+
datasets:
|
10 |
+
- squad
|
11 |
+
metrics:
|
12 |
+
- squad
|
13 |
+
widget:
|
14 |
+
- text: "Where is located the Eiffel Tower?"
|
15 |
+
context: "The Eiffel Tower is a wrought-iron lattice tower on the Champ de Mars in Paris, France. It is named after the engineer Gustave Eiffel, whose company designed and built the tower."
|
16 |
+
- text: "Who is Frederic Chopin?"
|
17 |
+
context: "Frédéric François Chopin, born Fryderyk Franciszek Chopin (1 March 1810 – 17 October 1849), was a Polish composer and virtuoso pianist of the Romantic era who wrote primarily for solo piano."
|
18 |
+
---
|
19 |
+
|
20 |
+
## BERT-base uncased model fine-tuned on SQuAD v1
|
21 |
+
|
22 |
+
This model is [block-sparse](https://github.com/huggingface/pytorch_block_sparse).
|
23 |
+
|
24 |
+
That means that with the right runtime it can run roughly 3x faster than an dense network, with 25% of the original weights.
|
25 |
+
|
26 |
+
This of course has some impact on the accuracy (see below).
|
27 |
+
|
28 |
+
It uses a modified version of Victor Sanh [Movement Pruning](https://arxiv.org/abs/2005.07683) method.
|
29 |
+
|
30 |
+
This model was fine-tuned from the HuggingFace[BERT](https://www.aclweb.org/anthology/N19-1423/) base uncased checkpoint on [SQuAD1.1](https://rajpurkar.github.io/SQuAD-explorer), and distilled from the equivalent model [csarron/bert-base-uncased-squad-v1](https://huggingface.co/csarron/bert-base-uncased-squad-v1).
|
31 |
+
This model is case-insensitive: it does not make a difference between english and English.
|
32 |
+
|
33 |
+
## Pruning details
|
34 |
+

|
35 |
+
|
36 |
+
## Density plot
|
37 |
+
|
38 |
+
<script src="/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/density.js" id="4af67900-bd92-4310-973e-0cf20443efff"></script>
|
39 |
+
|
40 |
+
## Details
|
41 |
+
|
42 |
+
| Dataset | Split | # samples |
|
43 |
+
| -------- | ----- | --------- |
|
44 |
+
| SQuAD1.1 | train | 90.6K |
|
45 |
+
| SQuAD1.1 | eval | 11.1k |
|
46 |
+
|
47 |
+
### Fine-tuning
|
48 |
+
- Python: `3.8.5`
|
49 |
+
|
50 |
+
- Machine specs:
|
51 |
+
|
52 |
+
`CPU: Intel(R) Core(TM) i7-6700K CPU`
|
53 |
+
|
54 |
+
`Memory: 64 GiB`
|
55 |
+
|
56 |
+
`GPUs: 1 GeForce GTX 3090, with 24GiB memory`
|
57 |
+
|
58 |
+
`GPU driver: 455.23.05, CUDA: 11.1`
|
59 |
+
|
60 |
+
|
61 |
+
### Results
|
62 |
+
|
63 |
+
**Pytorch model file size**: `342`M (original BERT:`438M`)
|
64 |
+
|
65 |
+
| Metric | # Value | # Original ([Table 2](https://www.aclweb.org/anthology/N19-1423.pdf))|
|
66 |
+
| ------ | --------- | --------- |
|
67 |
+
| **EM** | **74.39** | **80.8** |
|
68 |
+
| **F1** | **83.26** | **88.5** |
|
69 |
+
|
70 |
+
## Example Usage
|
71 |
+
|
72 |
+
```python
|
73 |
+
from transformers import pipeline
|
74 |
+
|
75 |
+
qa_pipeline = pipeline(
|
76 |
+
"question-answering",
|
77 |
+
model="madlag/bert-base-uncased-squad-v1-sparse0.25",
|
78 |
+
tokenizer="madlag/bert-base-uncased-squad-v1-sparse0.25"
|
79 |
+
)
|
80 |
+
|
81 |
+
predictions = qa_pipeline({
|
82 |
+
'context': "Frédéric François Chopin, born Fryderyk Franciszek Chopin (1 March 1810 – 17 October 1849), was a Polish composer and virtuoso pianist of the Romantic era who wrote primarily for solo piano.",
|
83 |
+
'question': "Who is Frederic Chopin?",
|
84 |
+
})
|
85 |
+
|
86 |
+
print(predictions)
|
model_card/density.js
ADDED
@@ -0,0 +1,174 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
(function() {
|
2 |
+
var fn = function() {
|
3 |
+
|
4 |
+
(function(root) {
|
5 |
+
function now() {
|
6 |
+
return new Date();
|
7 |
+
}
|
8 |
+
|
9 |
+
var force = false;
|
10 |
+
|
11 |
+
if (typeof root._bokeh_onload_callbacks === "undefined" || force === true) {
|
12 |
+
root._bokeh_onload_callbacks = [];
|
13 |
+
root._bokeh_is_loading = undefined;
|
14 |
+
}
|
15 |
+
|
16 |
+
|
17 |
+
|
18 |
+
|
19 |
+
var element = document.getElementById("4af67900-bd92-4310-973e-0cf20443efff");
|
20 |
+
if (element == null) {
|
21 |
+
console.warn("Bokeh: autoload.js configured with elementid '4af67900-bd92-4310-973e-0cf20443efff' but no matching script tag was found.")
|
22 |
+
}
|
23 |
+
|
24 |
+
|
25 |
+
function run_callbacks() {
|
26 |
+
try {
|
27 |
+
root._bokeh_onload_callbacks.forEach(function(callback) {
|
28 |
+
if (callback != null)
|
29 |
+
callback();
|
30 |
+
});
|
31 |
+
} finally {
|
32 |
+
delete root._bokeh_onload_callbacks
|
33 |
+
}
|
34 |
+
console.debug("Bokeh: all callbacks have finished");
|
35 |
+
}
|
36 |
+
|
37 |
+
function load_libs(css_urls, js_urls, callback) {
|
38 |
+
if (css_urls == null) css_urls = [];
|
39 |
+
if (js_urls == null) js_urls = [];
|
40 |
+
|
41 |
+
root._bokeh_onload_callbacks.push(callback);
|
42 |
+
if (root._bokeh_is_loading > 0) {
|
43 |
+
console.debug("Bokeh: BokehJS is being loaded, scheduling callback at", now());
|
44 |
+
return null;
|
45 |
+
}
|
46 |
+
if (js_urls == null || js_urls.length === 0) {
|
47 |
+
run_callbacks();
|
48 |
+
return null;
|
49 |
+
}
|
50 |
+
console.debug("Bokeh: BokehJS not loaded, scheduling load and callback at", now());
|
51 |
+
root._bokeh_is_loading = css_urls.length + js_urls.length;
|
52 |
+
|
53 |
+
function on_load() {
|
54 |
+
root._bokeh_is_loading--;
|
55 |
+
if (root._bokeh_is_loading === 0) {
|
56 |
+
console.debug("Bokeh: all BokehJS libraries/stylesheets loaded");
|
57 |
+
run_callbacks()
|
58 |
+
}
|
59 |
+
}
|
60 |
+
|
61 |
+
function on_error() {
|
62 |
+
console.error("failed to load " + url);
|
63 |
+
}
|
64 |
+
|
65 |
+
for (var i = 0; i < css_urls.length; i++) {
|
66 |
+
var url = css_urls[i];
|
67 |
+
const element = document.createElement("link");
|
68 |
+
element.onload = on_load;
|
69 |
+
element.onerror = on_error;
|
70 |
+
element.rel = "stylesheet";
|
71 |
+
element.type = "text/css";
|
72 |
+
element.href = url;
|
73 |
+
console.debug("Bokeh: injecting link tag for BokehJS stylesheet: ", url);
|
74 |
+
document.body.appendChild(element);
|
75 |
+
}
|
76 |
+
|
77 |
+
const hashes = {"https://cdn.bokeh.org/bokeh/release/bokeh-2.2.3.min.js": "T2yuo9Oe71Cz/I4X9Ac5+gpEa5a8PpJCDlqKYO0CfAuEszu1JrXLl8YugMqYe3sM", "https://cdn.bokeh.org/bokeh/release/bokeh-widgets-2.2.3.min.js": "98GDGJ0kOMCUMUePhksaQ/GYgB3+NH9h996V88sh3aOiUNX3N+fLXAtry6xctSZ6", "https://cdn.bokeh.org/bokeh/release/bokeh-tables-2.2.3.min.js": "89bArO+nlbP3sgakeHjCo1JYxYR5wufVgA3IbUvDY+K7w4zyxJqssu7wVnfeKCq8"};
|
78 |
+
|
79 |
+
for (var i = 0; i < js_urls.length; i++) {
|
80 |
+
var url = js_urls[i];
|
81 |
+
var element = document.createElement('script');
|
82 |
+
element.onload = on_load;
|
83 |
+
element.onerror = on_error;
|
84 |
+
element.async = false;
|
85 |
+
element.src = url;
|
86 |
+
if (url in hashes) {
|
87 |
+
element.crossOrigin = "anonymous";
|
88 |
+
element.integrity = "sha384-" + hashes[url];
|
89 |
+
}
|
90 |
+
console.debug("Bokeh: injecting script tag for BokehJS library: ", url);
|
91 |
+
document.head.appendChild(element);
|
92 |
+
}
|
93 |
+
};
|
94 |
+
|
95 |
+
function inject_raw_css(css) {
|
96 |
+
const element = document.createElement("style");
|
97 |
+
element.appendChild(document.createTextNode(css));
|
98 |
+
document.body.appendChild(element);
|
99 |
+
}
|
100 |
+
|
101 |
+
|
102 |
+
var js_urls = ["https://cdn.bokeh.org/bokeh/release/bokeh-2.2.3.min.js", "https://cdn.bokeh.org/bokeh/release/bokeh-widgets-2.2.3.min.js", "https://cdn.bokeh.org/bokeh/release/bokeh-tables-2.2.3.min.js"];
|
103 |
+
var css_urls = [];
|
104 |
+
|
105 |
+
|
106 |
+
var inline_js = [
|
107 |
+
function(Bokeh) {
|
108 |
+
Bokeh.set_log_level("info");
|
109 |
+
},
|
110 |
+
|
111 |
+
function(Bokeh) {
|
112 |
+
(function() {
|
113 |
+
var fn = function() {
|
114 |
+
Bokeh.safely(function() {
|
115 |
+
(function(root) {
|
116 |
+
function embed_document(root) {
|
117 |
+
|
118 |
+
var docs_json = '{"913c3228-db80-48c9-8309-97f33ce0691f":{"roots":{"references":[{"attributes":{"data_source":{"id":"1023"},"glyph":{"id":"1025"},"hover_glyph":null,"muted_glyph":null,"name":"query","nonselection_glyph":{"id":"1026"},"selection_glyph":null,"view":{"id":"1028"}},"id":"1027","type":"GlyphRenderer"},{"attributes":{"axis_label":"Density","formatter":{"id":"1031"},"minor_tick_line_color":null,"ticker":{"id":"1018"}},"id":"1017","type":"LinearAxis"},{"attributes":{},"id":"1051","type":"UnionRenderers"},{"attributes":{},"id":"1011","type":"LinearScale"},{"attributes":{},"id":"1052","type":"Selection"},{"attributes":{},"id":"1090","type":"Selection"},{"attributes":{"label":{"value":"value"},"renderers":[{"id":"1058"}]},"id":"1071","type":"LegendItem"},{"attributes":{},"id":"1069","type":"UnionRenderers"},{"attributes":{},"id":"1009","type":"LinearScale"},{"attributes":{},"id":"1033","type":"BasicTickFormatter"},{"attributes":{},"id":"1070","type":"Selection"},{"attributes":{"axis":{"id":"1017"},"dimension":1,"ticker":null},"id":"1020","type":"Grid"},{"attributes":{"items":[{"id":"1037"},{"id":"1053"},{"id":"1071"},{"id":"1091"}],"location":"top_left","orientation":"horizontal"},"id":"1036","type":"Legend"},{"attributes":{"fill_color":{"value":"#ed5642"},"line_color":{"value":"#ed5642"},"top":{"field":"height"},"width":{"value":0.125},"x":{"field":"x"}},"id":"1040","type":"VBar"},{"attributes":{"fill_alpha":{"value":0.1},"fill_color":{"value":"#6573f7"},"line_alpha":{"value":0.1},"line_color":{"value":"#6573f7"},"top":{"field":"height"},"width":{"value":0.125},"x":{"field":"x"}},"id":"1026","type":"VBar"},{"attributes":{"source":{"id":"1054"}},"id":"1059","type":"CDSView"},{"attributes":{"source":{"id":"1023"}},"id":"1028","type":"CDSView"},{"attributes":{"fill_color":{"value":"#6573f7"},"line_color":{"value":"#6573f7"},"top":{"field":"height"},"width":{"value":0.125},"x":{"field":"x"}},"id":"1025","type":"VBar"},{"attributes":{"label":{"value":"query"},"renderers":[{"id":"1027"}]},"id":"1037","type":"LegendItem"},{"attributes":{"data":{"density":["0.20","0.10","0.16","0.21","0.11","0.12","0.11","0.15","0.06","0.04","0.02","0.02"],"height":[0.1979166716337204,0.1024305522441864,0.1597222238779068,0.2083333283662796,0.1145833358168602,0.1180555522441864,0.1076388880610466,0.1475694477558136,0.0590277761220932,0.0364583320915699,0.0243055559694767,0.02083333395421505],"img_height":["96px","96px","96px","96px","96px","96px","96px","96px","96px","96px","96px","96px"],"img_width":["96px","96px","96px","96px","96px","96px","96px","96px","96px","96px","96px","96px"],"name":["0.attention.value","1.attention.value","2.attention.value","3.attention.value","4.attention.value","5.attention.value","6.attention.value","7.attention.value","8.attention.value","9.attention.value","10.attention.value","11.attention.value"],"url":["https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_0_attention_self_value.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_1_attention_self_value.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_2_attention_self_value.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_3_attention_self_value.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_4_attention_self_value.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_5_attention_self_value.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_6_attention_self_value.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_7_attention_self_value.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_8_attention_self_value.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_9_attention_self_value.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_10_attention_self_value.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_11_attention_self_value.png"],"x":[0.41666666666666663,1.4166666666666665,2.416666666666667,3.416666666666667,4.416666666666666,5.416666666666666,6.416666666666666,7.416666666666666,8.416666666666668,9.416666666666668,10.416666666666668,11.416666666666668]},"selected":{"id":"1070"},"selection_policy":{"id":"1069"}},"id":"1054","type":"ColumnDataSource"},{"attributes":{"fill_alpha":{"value":0.1},"fill_color":{"value":"#20cb97"},"line_alpha":{"value":0.1},"line_color":{"value":"#20cb97"},"top":{"field":"height"},"width":{"value":0.125},"x":{"field":"x"}},"id":"1057","type":"VBar"},{"attributes":{},"id":"1005","type":"DataRange1d"},{"attributes":{"data_source":{"id":"1054"},"glyph":{"id":"1056"},"hover_glyph":null,"muted_glyph":null,"name":"value","nonselection_glyph":{"id":"1057"},"selection_glyph":null,"view":{"id":"1059"}},"id":"1058","type":"GlyphRenderer"},{"attributes":{},"id":"1014","type":"BasicTicker"},{"attributes":{},"id":"1034","type":"UnionRenderers"},{"attributes":{"axis":{"id":"1013"},"grid_line_color":null,"ticker":null},"id":"1016","type":"Grid"},{"attributes":{"data":{"density":["0.15","0.13","0.17","0.23","0.11","0.10","0.09","0.11","0.07","0.12","0.06","0.06"],"height":[0.1527777761220932,0.1319444477558136,0.1684027761220932,0.2256944477558136,0.1111111119389534,0.0989583358168602,0.0920138880610466,0.1145833358168602,0.0694444477558136,0.1180555522441864,0.0642361119389534,0.0590277761220932],"img_height":["96px","96px","96px","96px","96px","96px","96px","96px","96px","96px","96px","96px"],"img_width":["96px","96px","96px","96px","96px","96px","96px","96px","96px","96px","96px","96px"],"name":["0.attention.query","1.attention.query","2.attention.query","3.attention.query","4.attention.query","5.attention.query","6.attention.query","7.attention.query","8.attention.query","9.attention.query","10.attention.query","11.attention.query"],"url":["https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_0_attention_self_query.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_1_attention_self_query.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_2_attention_self_query.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_3_attention_self_query.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_4_attention_self_query.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_5_attention_self_query.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_6_attention_self_query.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_7_attention_self_query.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_8_attention_self_query.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_9_attention_self_query.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_10_attention_self_query.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_11_attention_self_query.png"],"x":[0.08333333333333333,1.0833333333333333,2.0833333333333335,3.0833333333333335,4.083333333333333,5.083333333333333,6.083333333333333,7.083333333333333,8.083333333333334,9.083333333333334,10.083333333333334,11.083333333333334]},"selected":{"id":"1035"},"selection_policy":{"id":"1034"}},"id":"1023","type":"ColumnDataSource"},{"attributes":{},"id":"1035","type":"Selection"},{"attributes":{"data":{"density":["0.21","0.29","0.25","0.09","0.17","0.15","0.16","0.29","0.23","0.21","0.21","0.16","0.11","0.22","0.16","0.12","0.18","0.13","0.10","0.16","0.13","0.12","0.11","0.08","0.05","0.03","0.03","0.03","0.01","0.01","0.03","0.03","0.02","0.02","0.05","0.03"],"height":[0.2083333283662796,0.2894965410232544,0.2543402910232544,0.0885416641831398,0.1736111044883728,0.1488715261220932,0.1649305522441864,0.2938368022441864,0.2330729216337204,0.2083333283662796,0.2078993022441864,0.1584201455116272,0.1111111119389534,0.2239583283662796,0.1605902761220932,0.1197916641831398,0.1779513955116272,0.1267361044883728,0.0972222238779068,0.1627604216337204,0.1302083283662796,0.1197916641831398,0.1063368022441864,0.078125,0.0520833320915699,0.0342881940305233,0.02734375,0.0329861119389534,0.01128472201526165,0.0086805559694767,0.0295138880610466,0.0329861119389534,0.0234375,0.02083333395421505,0.0455729179084301,0.0290798619389534],"img_height":["96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px"],"img_width":["96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px","96px","96px","384px"],"name":["0.attention.output","0.intermediate","0.output","1.attention.output","1.intermediate","1.output","2.attention.output","2.intermediate","2.output","3.attention.output","3.intermediate","3.output","4.attention.output","4.intermediate","4.output","5.attention.output","5.intermediate","5.output","6.attention.output","6.intermediate","6.output","7.attention.output","7.intermediate","7.output","8.attention.output","8.intermediate","8.output","9.attention.output","9.intermediate","9.output","10.attention.output","10.intermediate","10.output","11.attention.output","11.intermediate","11.output"],"url":["https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_0_attention_output_dense.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_0_intermediate_dense.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_0_output_dense.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_1_attention_output_dense.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_1_intermediate_dense.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_1_output_dense.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_2_attention_output_dense.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_2_intermediate_dense.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_2_output_dense.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_3_attention_output_dense.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_3_intermediate_dense.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_3_output_dense.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_4_attention_output_dense.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_4_intermediate_dense.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_4_output_dense.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_5_attention_output_dense.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_5_intermediate_dense.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_5_output_dense.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_6_attention_output_dense.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_6_intermediate_dense.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_6_output_dense.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_7_attention_output_dense.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_7_intermediate_dense.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_7_output_dense.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_8_attention_output_dense.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_8_intermediate_dense.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_8_output_dense.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_9_attention_output_dense.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_9_intermediate_dense.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_9_output_dense.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_10_attention_output_dense.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_10_intermediate_dense.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_10_output_dense.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_11_attention_output_dense.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_11_intermediate_dense.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_11_output_dense.png"],"x":[0.5833333333333334,0.75,0.9166666666666667,1.5833333333333333,1.75,1.9166666666666665,2.5833333333333335,2.75,2.916666666666667,3.5833333333333335,3.75,3.916666666666667,4.583333333333333,4.75,4.916666666666666,5.583333333333333,5.75,5.916666666666666,6.583333333333333,6.75,6.916666666666666,7.583333333333333,7.75,7.916666666666666,8.583333333333334,8.75,8.916666666666668,9.583333333333334,9.75,9.916666666666668,10.583333333333334,10.75,10.916666666666668,11.583333333333334,11.75,11.916666666666668]},"selected":{"id":"1090"},"selection_policy":{"id":"1089"}},"id":"1072","type":"ColumnDataSource"},{"attributes":{},"id":"1031","type":"BasicTickFormatter"},{"attributes":{"label":{"value":"fully connected"},"renderers":[{"id":"1076"}]},"id":"1091","type":"LegendItem"},{"attributes":{},"id":"1018","type":"BasicTicker"},{"attributes":{"text":"Transformer Layers"},"id":"1003","type":"Title"},{"attributes":{"fill_color":{"value":"#20cb97"},"line_color":{"value":"#20cb97"},"top":{"field":"height"},"width":{"value":0.125},"x":{"field":"x"}},"id":"1056","type":"VBar"},{"attributes":{"below":[{"id":"1013"}],"center":[{"id":"1016"},{"id":"1020"},{"id":"1036"}],"left":[{"id":"1017"}],"outline_line_color":null,"plot_height":300,"plot_width":505,"renderers":[{"id":"1027"},{"id":"1042"},{"id":"1058"},{"id":"1076"}],"title":{"id":"1003"},"toolbar":{"id":"1021"},"x_range":{"id":"1005"},"x_scale":{"id":"1009"},"y_range":{"id":"1007"},"y_scale":{"id":"1011"}},"id":"1002","subtype":"Figure","type":"Plot"},{"attributes":{"data":{"density":["0.16","0.14","0.17","0.25","0.12","0.11","0.11","0.13","0.08","0.11","0.06","0.06"],"height":[0.1597222238779068,0.1423611044883728,0.1684027761220932,0.2517361044883728,0.1180555522441864,0.1128472238779068,0.1059027761220932,0.1319444477558136,0.0833333358168602,0.109375,0.0590277761220932,0.0607638880610466],"img_height":["96px","96px","96px","96px","96px","96px","96px","96px","96px","96px","96px","96px"],"img_width":["96px","96px","96px","96px","96px","96px","96px","96px","96px","96px","96px","96px"],"name":["0.attention.key","1.attention.key","2.attention.key","3.attention.key","4.attention.key","5.attention.key","6.attention.key","7.attention.key","8.attention.key","9.attention.key","10.attention.key","11.attention.key"],"url":["https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_0_attention_self_key.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_1_attention_self_key.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_2_attention_self_key.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_3_attention_self_key.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_4_attention_self_key.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_5_attention_self_key.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_6_attention_self_key.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_7_attention_self_key.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_8_attention_self_key.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_9_attention_self_key.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_10_attention_self_key.png","https://huggingface.co/madlag/bert-base-uncased-squad1.1-block-sparse-0.13-v1/raw/main/model_card/layer_images/layer_11_attention_self_key.png"],"x":[0.25,1.25,2.25,3.25,4.25,5.25,6.25,7.25,8.25,9.25,10.25,11.25]},"selected":{"id":"1052"},"selection_policy":{"id":"1051"}},"id":"1038","type":"ColumnDataSource"},{"attributes":{"label":{"value":"key"},"renderers":[{"id":"1042"}]},"id":"1053","type":"LegendItem"},{"attributes":{"fill_color":{"value":"#aa69f7"},"line_color":{"value":"#aa69f7"},"top":{"field":"height"},"width":{"value":0.125},"x":{"field":"x"}},"id":"1074","type":"VBar"},{"attributes":{"data_source":{"id":"1072"},"glyph":{"id":"1074"},"hover_glyph":null,"muted_glyph":null,"name":"fully connected","nonselection_glyph":{"id":"1075"},"selection_glyph":null,"view":{"id":"1077"}},"id":"1076","type":"GlyphRenderer"},{"attributes":{"data_source":{"id":"1038"},"glyph":{"id":"1040"},"hover_glyph":null,"muted_glyph":null,"name":"key","nonselection_glyph":{"id":"1041"},"selection_glyph":null,"view":{"id":"1043"}},"id":"1042","type":"GlyphRenderer"},{"attributes":{"fill_alpha":{"value":0.1},"fill_color":{"value":"#aa69f7"},"line_alpha":{"value":0.1},"line_color":{"value":"#aa69f7"},"top":{"field":"height"},"width":{"value":0.125},"x":{"field":"x"}},"id":"1075","type":"VBar"},{"attributes":{"fill_alpha":{"value":0.1},"fill_color":{"value":"#ed5642"},"line_alpha":{"value":0.1},"line_color":{"value":"#ed5642"},"top":{"field":"height"},"width":{"value":0.125},"x":{"field":"x"}},"id":"1041","type":"VBar"},{"attributes":{"active_drag":"auto","active_inspect":"auto","active_multi":null,"active_scroll":"auto","active_tap":"auto","tools":[{"id":"1001"}]},"id":"1021","type":"Toolbar"},{"attributes":{"source":{"id":"1072"}},"id":"1077","type":"CDSView"},{"attributes":{"axis_label":"Layer","formatter":{"id":"1033"},"minor_tick_line_color":null,"ticker":{"id":"1014"}},"id":"1013","type":"LinearAxis"},{"attributes":{"source":{"id":"1038"}},"id":"1043","type":"CDSView"},{"attributes":{"callback":null,"tooltips":"\\n <div>\\n <div style=\\"margin-bottom:10px\\">\\n <span style=\\"font-size: 15px;\\"><b>@name</b><br/>density=@density</span>\\n </div>\\n <div> \\n <img\\n src=\\"@url\\" height=\\"@img_height\\" width=\\"@img_width\\" alt=\\"@url\\"\\n style=\\"float: left; margin: 0px 15px 15px 0px;\\"\\n border=\\"0\\"\\n />\\n </div>\\n </div>\\n "},"id":"1001","type":"HoverTool"},{"attributes":{"start":0},"id":"1007","type":"DataRange1d"},{"attributes":{},"id":"1089","type":"UnionRenderers"}],"root_ids":["1002"]},"title":"Bokeh Application","version":"2.2.3"}}';
|
119 |
+
var render_items = [{"docid":"913c3228-db80-48c9-8309-97f33ce0691f","root_ids":["1002"],"roots":{"1002":"4af67900-bd92-4310-973e-0cf20443efff"}}];
|
120 |
+
root.Bokeh.embed.embed_items(docs_json, render_items);
|
121 |
+
|
122 |
+
}
|
123 |
+
if (root.Bokeh !== undefined) {
|
124 |
+
embed_document(root);
|
125 |
+
} else {
|
126 |
+
var attempts = 0;
|
127 |
+
var timer = setInterval(function(root) {
|
128 |
+
if (root.Bokeh !== undefined) {
|
129 |
+
clearInterval(timer);
|
130 |
+
embed_document(root);
|
131 |
+
} else {
|
132 |
+
attempts++;
|
133 |
+
if (attempts > 100) {
|
134 |
+
clearInterval(timer);
|
135 |
+
console.log("Bokeh: ERROR: Unable to run BokehJS code because BokehJS library is missing");
|
136 |
+
}
|
137 |
+
}
|
138 |
+
}, 10, root)
|
139 |
+
}
|
140 |
+
})(window);
|
141 |
+
});
|
142 |
+
};
|
143 |
+
if (document.readyState != "loading") fn();
|
144 |
+
else document.addEventListener("DOMContentLoaded", fn);
|
145 |
+
})();
|
146 |
+
},
|
147 |
+
function(Bokeh) {
|
148 |
+
|
149 |
+
|
150 |
+
}
|
151 |
+
];
|
152 |
+
|
153 |
+
function run_inline_js() {
|
154 |
+
|
155 |
+
for (var i = 0; i < inline_js.length; i++) {
|
156 |
+
inline_js[i].call(root, root.Bokeh);
|
157 |
+
}
|
158 |
+
|
159 |
+
}
|
160 |
+
|
161 |
+
if (root._bokeh_is_loading === 0) {
|
162 |
+
console.debug("Bokeh: BokehJS loaded, going straight to plotting");
|
163 |
+
run_inline_js();
|
164 |
+
} else {
|
165 |
+
load_libs(css_urls, js_urls, function() {
|
166 |
+
console.debug("Bokeh: BokehJS plotting callback run at", now());
|
167 |
+
run_inline_js();
|
168 |
+
});
|
169 |
+
}
|
170 |
+
}(window));
|
171 |
+
};
|
172 |
+
if (document.readyState != "loading") fn();
|
173 |
+
else document.addEventListener("DOMContentLoaded", fn);
|
174 |
+
})();
|
model_card/layer_images/layer_0_attention_output_dense.png
ADDED
![]() |
model_card/layer_images/layer_0_attention_self_key.png
ADDED
![]() |
model_card/layer_images/layer_0_attention_self_query.png
ADDED
![]() |
model_card/layer_images/layer_0_attention_self_value.png
ADDED
![]() |
model_card/layer_images/layer_0_intermediate_dense.png
ADDED
![]() |
model_card/layer_images/layer_0_output_dense.png
ADDED
![]() |
model_card/layer_images/layer_10_attention_output_dense.png
ADDED
![]() |
model_card/layer_images/layer_10_attention_self_key.png
ADDED
![]() |
model_card/layer_images/layer_10_attention_self_query.png
ADDED
![]() |
model_card/layer_images/layer_10_attention_self_value.png
ADDED
![]() |
model_card/layer_images/layer_10_intermediate_dense.png
ADDED
![]() |
model_card/layer_images/layer_10_output_dense.png
ADDED
![]() |
model_card/layer_images/layer_11_attention_output_dense.png
ADDED
![]() |
model_card/layer_images/layer_11_attention_self_key.png
ADDED
![]() |
model_card/layer_images/layer_11_attention_self_query.png
ADDED
![]() |
model_card/layer_images/layer_11_attention_self_value.png
ADDED
![]() |
model_card/layer_images/layer_11_intermediate_dense.png
ADDED
![]() |
model_card/layer_images/layer_11_output_dense.png
ADDED
![]() |
model_card/layer_images/layer_1_attention_output_dense.png
ADDED
![]() |
model_card/layer_images/layer_1_attention_self_key.png
ADDED
![]() |
model_card/layer_images/layer_1_attention_self_query.png
ADDED
![]() |
model_card/layer_images/layer_1_attention_self_value.png
ADDED
![]() |
model_card/layer_images/layer_1_intermediate_dense.png
ADDED
![]() |
model_card/layer_images/layer_1_output_dense.png
ADDED
![]() |
model_card/layer_images/layer_2_attention_output_dense.png
ADDED
![]() |
model_card/layer_images/layer_2_attention_self_key.png
ADDED
![]() |
model_card/layer_images/layer_2_attention_self_query.png
ADDED
![]() |
model_card/layer_images/layer_2_attention_self_value.png
ADDED
![]() |
model_card/layer_images/layer_2_intermediate_dense.png
ADDED
![]() |
model_card/layer_images/layer_2_output_dense.png
ADDED
![]() |
model_card/layer_images/layer_3_attention_output_dense.png
ADDED
![]() |
model_card/layer_images/layer_3_attention_self_key.png
ADDED
![]() |
model_card/layer_images/layer_3_attention_self_query.png
ADDED
![]() |
model_card/layer_images/layer_3_attention_self_value.png
ADDED
![]() |
model_card/layer_images/layer_3_intermediate_dense.png
ADDED
![]() |
model_card/layer_images/layer_3_output_dense.png
ADDED
![]() |
model_card/layer_images/layer_4_attention_output_dense.png
ADDED
![]() |
model_card/layer_images/layer_4_attention_self_key.png
ADDED
![]() |
model_card/layer_images/layer_4_attention_self_query.png
ADDED
![]() |
model_card/layer_images/layer_4_attention_self_value.png
ADDED
![]() |
model_card/layer_images/layer_4_intermediate_dense.png
ADDED
![]() |
model_card/layer_images/layer_4_output_dense.png
ADDED
![]() |
model_card/layer_images/layer_5_attention_output_dense.png
ADDED
![]() |
model_card/layer_images/layer_5_attention_self_key.png
ADDED
![]() |
model_card/layer_images/layer_5_attention_self_query.png
ADDED
![]() |
model_card/layer_images/layer_5_attention_self_value.png
ADDED
![]() |
model_card/layer_images/layer_5_intermediate_dense.png
ADDED
![]() |
model_card/layer_images/layer_5_output_dense.png
ADDED
![]() |