diff --git a/README.md b/README.md index 51f5cc688c9d12d56a3c96feed62f4d64ae971bb..e22df6c689b23706ba4ae734c4d23c0b75a42876 100644 --- a/README.md +++ b/README.md @@ -19,16 +19,13 @@ widget: ## BERT-base uncased model fine-tuned on SQuAD v1 -This model is block sparse: the **linear** layers contains **64.0%** of the original weights. +This model was created using the [nn_pruning](https://githbu.com/huggingface/nn_pruning) python library: the **linear** layers contains **64.0%** of the original weights. The model contains **36.0%** of the original weights **overall**. -The training use a modified version of Victor Sanh [Movement Pruning](https://arxiv.org/abs/2005.07683) method. - -That means that with the [block-sparse](https://github.com/huggingface/pytorch_block_sparse) runtime it ran **1.84x** faster than an dense networks on the evaluation, at the price of some impact on the accuracy (see below). - - +That means that with the [block-sparse](https://github.com/huggingface/pytorch_block_sparse) runtime it ran **1.84x as fast as BERT-base** on the evaluation, while its F1 is +88.72, compared with 88.5 for BERT-base, a **F1 gain of 0.22**. 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). This model is case-insensitive: it does not make a difference between english and English. @@ -38,9 +35,10 @@ A side-effect of the block pruning is that some of the attention heads are compl Here is a detailed view on how the remaining heads are distributed in the network after pruning. -
+
## Density plot +
## Details @@ -66,10 +64,10 @@ GPU driver: 455.23.05, CUDA: 11.1 **Pytorch model file size**: `379M` (original BERT: `438M`) -| Metric | # Value | # Original ([Table 2](https://www.aclweb.org/anthology/N19-1423.pdf))| -| ------ | --------- | --------- | -| **EM** | **81.69** | **80.8** | -| **F1** | **88.72** | **88.5** | +| Metric | # Value | # Original ([Table 2](https://www.aclweb.org/anthology/N19-1423.pdf))| Variation | +| ------ | --------- | --------- | --------- | +| **EM** | **81.69** | **80.8** | **+0.89**| +| **F1** | **88.72** | **88.5** | **+0.22**| ## Example Usage diff --git a/model_card/density_info.js b/model_card/density_info.js new file mode 100644 index 0000000000000000000000000000000000000000..4866c415652c876fd637c954c6ce845ca614710d --- /dev/null +++ b/model_card/density_info.js @@ -0,0 +1,174 @@ +(function() { + var fn = function() { + + (function(root) { + function now() { + return new Date(); + } + + var force = false; + + if (typeof root._bokeh_onload_callbacks === "undefined" || force === true) { + root._bokeh_onload_callbacks = []; + root._bokeh_is_loading = undefined; + } + + + + + var element = document.getElementById("1b3cca51-0673-438c-84f3-7abe6f955faa"); + if (element == null) { + console.warn("Bokeh: autoload.js configured with elementid '1b3cca51-0673-438c-84f3-7abe6f955faa' but no matching script tag was found.") + } + + + function run_callbacks() { + try { + root._bokeh_onload_callbacks.forEach(function(callback) { + if (callback != null) + callback(); + }); + } finally { + delete root._bokeh_onload_callbacks + } + console.debug("Bokeh: all callbacks have finished"); + } + + function load_libs(css_urls, js_urls, callback) { + if (css_urls == null) css_urls = []; + if (js_urls == null) js_urls = []; + + root._bokeh_onload_callbacks.push(callback); + if (root._bokeh_is_loading > 0) { + console.debug("Bokeh: BokehJS is being loaded, scheduling callback at", now()); + return null; + } + if (js_urls == null || js_urls.length === 0) { + run_callbacks(); + return null; + } + console.debug("Bokeh: BokehJS not loaded, scheduling load and callback at", now()); + root._bokeh_is_loading = css_urls.length + js_urls.length; + + function on_load() { + root._bokeh_is_loading--; + if (root._bokeh_is_loading === 0) { + console.debug("Bokeh: all BokehJS libraries/stylesheets loaded"); + run_callbacks() + } + } + + function on_error() { + console.error("failed to load " + url); + } + + for (var i = 0; i < css_urls.length; i++) { + var url = css_urls[i]; + const element = document.createElement("link"); + element.onload = on_load; + element.onerror = on_error; + element.rel = "stylesheet"; + element.type = "text/css"; + element.href = url; + console.debug("Bokeh: injecting link tag for BokehJS stylesheet: ", url); + document.body.appendChild(element); + } + + 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"}; + + for (var i = 0; i < js_urls.length; i++) { + var url = js_urls[i]; + var element = document.createElement('script'); + element.onload = on_load; + element.onerror = on_error; + element.async = false; + element.src = url; + if (url in hashes) { + element.crossOrigin = "anonymous"; + element.integrity = "sha384-" + hashes[url]; + } + console.debug("Bokeh: injecting script tag for BokehJS library: ", url); + document.head.appendChild(element); + } + }; + + function inject_raw_css(css) { + const element = document.createElement("style"); + element.appendChild(document.createTextNode(css)); + document.body.appendChild(element); + } + + + 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"]; + var css_urls = []; + + + var inline_js = [ + function(Bokeh) { + Bokeh.set_log_level("info"); + }, + + function(Bokeh) { + (function() { + var fn = function() { + Bokeh.safely(function() { + (function(root) { + function embed_document(root) { + + var docs_json = '{"acdcd0d9-882a-4f39-bfd2-8b82d263c2ff":{"roots":{"references":[{"attributes":{},"id":"1111","type":"BasicTicker"},{"attributes":{"source":{"id":"1116"}},"id":"1121","type":"CDSView"},{"attributes":{"fill_color":{"value":"#20cb97"},"line_color":{"value":"#20cb97"},"top":{"field":"height"},"width":{"value":0.125},"x":{"field":"x"}},"id":"1149","type":"VBar"},{"attributes":{"data":{"density":["1.00","0.24","0.24","1.00","0.27","0.27","1.00","0.32","0.32","1.00","0.33","0.33","1.00","0.34","0.34","1.00","0.32","0.32","1.00","0.24","0.24","1.00","0.18","0.18","1.00","0.10","0.10","1.00","0.04","0.04","1.00","0.04","0.04","1.00","0.10","0.10"],"height":[1.0,0.2386067658662796,0.2386067658662796,1.0,0.2724609375,0.2724609375,1.0,0.3229166567325592,0.3229166567325592,1.0,0.3297525942325592,0.3297525942325592,1.0,0.3427734375,0.3427734375,1.0,0.3209635317325592,0.3209635317325592,1.0,0.2405598908662796,0.2405598908662796,1.0,0.1796875,0.1796875,1.0,0.1005859375,0.1005859375,1.0,0.0442708320915699,0.0442708320915699,1.0,0.0358072929084301,0.0358072929084301,1.0,0.1028645858168602,0.1028645858168602],"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":["56px","96px","384px","40px","96px","384px","72px","96px","384px","72px","96px","384px","88px","96px","384px","80px","96px","384px","72px","96px","384px","64px","96px","384px","80px","96px","384px","48px","96px","384px","56px","96px","384px","40px","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":["/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_0_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_0_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_0_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_1_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_1_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_1_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_2_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_2_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_2_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_3_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_3_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_3_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_4_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_4_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_4_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_5_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_5_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_5_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_6_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_6_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_6_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_7_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_7_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_7_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_8_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_8_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_8_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_9_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_9_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_9_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_10_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_10_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_10_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_11_attention_output_dense.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_11_intermediate_dense.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/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":"1183"},"selection_policy":{"id":"1182"}},"id":"1165","type":"ColumnDataSource"},{"attributes":{},"id":"1104","type":"LinearScale"},{"attributes":{},"id":"1098","type":"DataRange1d"},{"attributes":{"data_source":{"id":"1131"},"glyph":{"id":"1133"},"hover_glyph":null,"muted_glyph":null,"name":"key","nonselection_glyph":{"id":"1134"},"selection_glyph":null,"view":{"id":"1136"}},"id":"1135","type":"GlyphRenderer"},{"attributes":{"label":{"value":"value"},"renderers":[{"id":"1151"}]},"id":"1164","type":"LegendItem"},{"attributes":{},"id":"1162","type":"UnionRenderers"},{"attributes":{"fill_color":{"value":"#ed5642"},"line_color":{"value":"#ed5642"},"top":{"field":"height"},"width":{"value":0.125},"x":{"field":"x"}},"id":"1133","type":"VBar"},{"attributes":{"text":"Transformer Layers"},"id":"1096","type":"Title"},{"attributes":{"source":{"id":"1147"}},"id":"1152","type":"CDSView"},{"attributes":{"fill_color":{"value":"#aa69f7"},"line_color":{"value":"#aa69f7"},"top":{"field":"height"},"width":{"value":0.125},"x":{"field":"x"}},"id":"1167","type":"VBar"},{"attributes":{},"id":"1183","type":"Selection"},{"attributes":{"label":{"value":"fully connected"},"renderers":[{"id":"1169"}]},"id":"1184","type":"LegendItem"},{"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":"1134","type":"VBar"},{"attributes":{"items":[{"id":"1130"},{"id":"1146"},{"id":"1164"},{"id":"1184"}],"location":"top_left","orientation":"horizontal"},"id":"1129","type":"Legend"},{"attributes":{},"id":"1145","type":"Selection"},{"attributes":{"source":{"id":"1165"}},"id":"1170","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":"1094","type":"HoverTool"},{"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":"1150","type":"VBar"},{"attributes":{"axis":{"id":"1106"},"grid_line_color":null,"ticker":null},"id":"1109","type":"Grid"},{"attributes":{"data_source":{"id":"1116"},"glyph":{"id":"1118"},"hover_glyph":null,"muted_glyph":null,"name":"query","nonselection_glyph":{"id":"1119"},"selection_glyph":null,"view":{"id":"1121"}},"id":"1120","type":"GlyphRenderer"},{"attributes":{},"id":"1128","type":"Selection"},{"attributes":{"source":{"id":"1131"}},"id":"1136","type":"CDSView"},{"attributes":{"axis_label":"Density","formatter":{"id":"1126"},"minor_tick_line_color":null,"ticker":{"id":"1111"}},"id":"1110","type":"LinearAxis"},{"attributes":{"data":{"density":["1.00","1.00","1.00","1.00","1.00","1.00","1.00","1.00","1.00","1.00","1.00","1.00"],"height":[1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0],"img_height":["56px","40px","72px","72px","88px","80px","72px","64px","80px","48px","56px","40px"],"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":["/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_0_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_1_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_2_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_3_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_4_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_5_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_6_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_7_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_8_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_9_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_10_attention_self_value.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/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":"1163"},"selection_policy":{"id":"1162"}},"id":"1147","type":"ColumnDataSource"},{"attributes":{"label":{"value":"key"},"renderers":[{"id":"1135"}]},"id":"1146","type":"LegendItem"},{"attributes":{},"id":"1107","type":"BasicTicker"},{"attributes":{},"id":"1163","type":"Selection"},{"attributes":{},"id":"1126","type":"BasicTickFormatter"},{"attributes":{"below":[{"id":"1106"}],"center":[{"id":"1109"},{"id":"1113"},{"id":"1129"}],"left":[{"id":"1110"}],"outline_line_color":null,"plot_height":300,"plot_width":505,"renderers":[{"id":"1120"},{"id":"1135"},{"id":"1151"},{"id":"1169"}],"title":{"id":"1096"},"toolbar":{"id":"1114"},"x_range":{"id":"1098"},"x_scale":{"id":"1102"},"y_range":{"id":"1100"},"y_scale":{"id":"1104"}},"id":"1095","subtype":"Figure","type":"Plot"},{"attributes":{"active_drag":"auto","active_inspect":"auto","active_multi":null,"active_scroll":"auto","active_tap":"auto","tools":[{"id":"1094"}]},"id":"1114","type":"Toolbar"},{"attributes":{},"id":"1144","type":"UnionRenderers"},{"attributes":{},"id":"1102","type":"LinearScale"},{"attributes":{"label":{"value":"query"},"renderers":[{"id":"1120"}]},"id":"1130","type":"LegendItem"},{"attributes":{"axis":{"id":"1110"},"dimension":1,"ticker":null},"id":"1113","type":"Grid"},{"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":"1168","type":"VBar"},{"attributes":{},"id":"1182","type":"UnionRenderers"},{"attributes":{},"id":"1124","type":"BasicTickFormatter"},{"attributes":{"data":{"density":["1.00","1.00","1.00","1.00","1.00","1.00","1.00","1.00","1.00","1.00","1.00","1.00"],"height":[1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0],"img_height":["56px","40px","72px","72px","88px","80px","72px","64px","80px","48px","56px","40px"],"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":["/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_0_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_1_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_2_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_3_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_4_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_5_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_6_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_7_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_8_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_9_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_10_attention_self_query.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/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":"1128"},"selection_policy":{"id":"1127"}},"id":"1116","type":"ColumnDataSource"},{"attributes":{"start":0},"id":"1100","type":"DataRange1d"},{"attributes":{"data":{"density":["1.00","1.00","1.00","1.00","1.00","1.00","1.00","1.00","1.00","1.00","1.00","1.00"],"height":[1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0],"img_height":["56px","40px","72px","72px","88px","80px","72px","64px","80px","48px","56px","40px"],"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":["/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_0_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_1_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_2_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_3_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_4_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_5_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_6_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_7_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_8_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_9_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/layer_10_attention_self_key.png","/madlag/bert-base-uncased-squadv1-x1.84-f88.7-d36-hybrid-filled-v1/raw/main/model_card/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":"1145"},"selection_policy":{"id":"1144"}},"id":"1131","type":"ColumnDataSource"},{"attributes":{"data_source":{"id":"1165"},"glyph":{"id":"1167"},"hover_glyph":null,"muted_glyph":null,"name":"fully connected","nonselection_glyph":{"id":"1168"},"selection_glyph":null,"view":{"id":"1170"}},"id":"1169","type":"GlyphRenderer"},{"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":"1119","type":"VBar"},{"attributes":{},"id":"1127","type":"UnionRenderers"},{"attributes":{"axis_label":"Layer","formatter":{"id":"1124"},"minor_tick_line_color":null,"ticker":{"id":"1107"}},"id":"1106","type":"LinearAxis"},{"attributes":{"fill_color":{"value":"#6573f7"},"line_color":{"value":"#6573f7"},"top":{"field":"height"},"width":{"value":0.125},"x":{"field":"x"}},"id":"1118","type":"VBar"},{"attributes":{"data_source":{"id":"1147"},"glyph":{"id":"1149"},"hover_glyph":null,"muted_glyph":null,"name":"value","nonselection_glyph":{"id":"1150"},"selection_glyph":null,"view":{"id":"1152"}},"id":"1151","type":"GlyphRenderer"}],"root_ids":["1095"]},"title":"Bokeh Application","version":"2.2.3"}}'; + var render_items = [{"docid":"acdcd0d9-882a-4f39-bfd2-8b82d263c2ff","root_ids":["1095"],"roots":{"1095":"1b3cca51-0673-438c-84f3-7abe6f955faa"}}]; + root.Bokeh.embed.embed_items(docs_json, render_items); + + } + if (root.Bokeh !== undefined) { + embed_document(root); + } else { + var attempts = 0; + var timer = setInterval(function(root) { + if (root.Bokeh !== undefined) { + clearInterval(timer); + embed_document(root); + } else { + attempts++; + if (attempts > 100) { + clearInterval(timer); + console.log("Bokeh: ERROR: Unable to run BokehJS code because BokehJS library is missing"); + } + } + }, 10, root) + } + })(window); + }); + }; + if (document.readyState != "loading") fn(); + else document.addEventListener("DOMContentLoaded", fn); + })(); + }, + function(Bokeh) { + + + } + ]; + + function run_inline_js() { + + for (var i = 0; i < inline_js.length; i++) { + inline_js[i].call(root, root.Bokeh); + } + + } + + if (root._bokeh_is_loading === 0) { + console.debug("Bokeh: BokehJS loaded, going straight to plotting"); + run_inline_js(); + } else { + load_libs(css_urls, js_urls, function() { + console.debug("Bokeh: BokehJS plotting callback run at", now()); + run_inline_js(); + }); + } + }(window)); + }; + if (document.readyState != "loading") fn(); + else document.addEventListener("DOMContentLoaded", fn); +})(); \ No newline at end of file diff --git a/model_card/images/layer_0_attention_output_dense.png b/model_card/images/layer_0_attention_output_dense.png new file mode 100644 index 0000000000000000000000000000000000000000..e472afdfa63212116ad0e5100ec44768b6a6e2eb Binary files /dev/null and b/model_card/images/layer_0_attention_output_dense.png differ diff --git a/model_card/images/layer_0_attention_self_key.png b/model_card/images/layer_0_attention_self_key.png new file mode 100644 index 0000000000000000000000000000000000000000..295696552ffa82db61b56404cf0f7007af2a2315 Binary files /dev/null and b/model_card/images/layer_0_attention_self_key.png differ diff --git a/model_card/images/layer_0_attention_self_query.png b/model_card/images/layer_0_attention_self_query.png new file mode 100644 index 0000000000000000000000000000000000000000..295696552ffa82db61b56404cf0f7007af2a2315 Binary files /dev/null and b/model_card/images/layer_0_attention_self_query.png differ diff --git a/model_card/images/layer_0_attention_self_value.png b/model_card/images/layer_0_attention_self_value.png new file mode 100644 index 0000000000000000000000000000000000000000..295696552ffa82db61b56404cf0f7007af2a2315 Binary files /dev/null and b/model_card/images/layer_0_attention_self_value.png differ diff --git a/model_card/images/layer_0_intermediate_dense.png b/model_card/images/layer_0_intermediate_dense.png new file mode 100644 index 0000000000000000000000000000000000000000..649aeeb24c9c0e34c2c8127b1d5610aeb0351f5c Binary files /dev/null and b/model_card/images/layer_0_intermediate_dense.png differ diff --git a/model_card/images/layer_0_output_dense.png b/model_card/images/layer_0_output_dense.png new file mode 100644 index 0000000000000000000000000000000000000000..e26d4e82c08c876d48847e6bc43a84e087733379 Binary files /dev/null and b/model_card/images/layer_0_output_dense.png differ diff --git a/model_card/images/layer_10_attention_output_dense.png b/model_card/images/layer_10_attention_output_dense.png new file mode 100644 index 0000000000000000000000000000000000000000..e472afdfa63212116ad0e5100ec44768b6a6e2eb Binary files /dev/null and b/model_card/images/layer_10_attention_output_dense.png differ diff --git a/model_card/images/layer_10_attention_self_key.png b/model_card/images/layer_10_attention_self_key.png new file mode 100644 index 0000000000000000000000000000000000000000..295696552ffa82db61b56404cf0f7007af2a2315 Binary files /dev/null and b/model_card/images/layer_10_attention_self_key.png differ diff --git a/model_card/images/layer_10_attention_self_query.png b/model_card/images/layer_10_attention_self_query.png new file mode 100644 index 0000000000000000000000000000000000000000..295696552ffa82db61b56404cf0f7007af2a2315 Binary files /dev/null and b/model_card/images/layer_10_attention_self_query.png differ diff --git a/model_card/images/layer_10_attention_self_value.png b/model_card/images/layer_10_attention_self_value.png new file mode 100644 index 0000000000000000000000000000000000000000..295696552ffa82db61b56404cf0f7007af2a2315 Binary files /dev/null and b/model_card/images/layer_10_attention_self_value.png differ diff --git a/model_card/images/layer_10_intermediate_dense.png b/model_card/images/layer_10_intermediate_dense.png new file mode 100644 index 0000000000000000000000000000000000000000..5760f69fe205bf82688e2e3bd4e268d1319c3c55 Binary files /dev/null and b/model_card/images/layer_10_intermediate_dense.png differ diff --git a/model_card/images/layer_10_output_dense.png b/model_card/images/layer_10_output_dense.png new file mode 100644 index 0000000000000000000000000000000000000000..1d46e344e85af27a22b0c3a2f562d7f9e073ce48 Binary files /dev/null and b/model_card/images/layer_10_output_dense.png differ diff --git a/model_card/images/layer_11_attention_output_dense.png b/model_card/images/layer_11_attention_output_dense.png new file mode 100644 index 0000000000000000000000000000000000000000..285b2eadf328aa1ac4fb3d3574a8c2e553355955 Binary files /dev/null and b/model_card/images/layer_11_attention_output_dense.png differ diff --git a/model_card/images/layer_11_attention_self_key.png b/model_card/images/layer_11_attention_self_key.png new file mode 100644 index 0000000000000000000000000000000000000000..4c1fef3f08bd8f3899ceed62b86f2a75b18ecada Binary files /dev/null and b/model_card/images/layer_11_attention_self_key.png differ diff --git a/model_card/images/layer_11_attention_self_query.png b/model_card/images/layer_11_attention_self_query.png new file mode 100644 index 0000000000000000000000000000000000000000..4c1fef3f08bd8f3899ceed62b86f2a75b18ecada Binary files /dev/null and b/model_card/images/layer_11_attention_self_query.png differ diff --git a/model_card/images/layer_11_attention_self_value.png b/model_card/images/layer_11_attention_self_value.png new file mode 100644 index 0000000000000000000000000000000000000000..4c1fef3f08bd8f3899ceed62b86f2a75b18ecada Binary files /dev/null and b/model_card/images/layer_11_attention_self_value.png differ diff --git a/model_card/images/layer_11_intermediate_dense.png b/model_card/images/layer_11_intermediate_dense.png new file mode 100644 index 0000000000000000000000000000000000000000..205d5fa31f4bb86b1ba4c6a8b0b19d1ca023a572 Binary files /dev/null and b/model_card/images/layer_11_intermediate_dense.png differ diff --git a/model_card/images/layer_11_output_dense.png b/model_card/images/layer_11_output_dense.png new file mode 100644 index 0000000000000000000000000000000000000000..08241eeb74523a6f953052f7adedcaa3a93634aa Binary files /dev/null and b/model_card/images/layer_11_output_dense.png differ diff --git a/model_card/images/layer_1_attention_output_dense.png b/model_card/images/layer_1_attention_output_dense.png new file mode 100644 index 0000000000000000000000000000000000000000..285b2eadf328aa1ac4fb3d3574a8c2e553355955 Binary files /dev/null and b/model_card/images/layer_1_attention_output_dense.png differ diff --git a/model_card/images/layer_1_attention_self_key.png b/model_card/images/layer_1_attention_self_key.png new file mode 100644 index 0000000000000000000000000000000000000000..4c1fef3f08bd8f3899ceed62b86f2a75b18ecada Binary files /dev/null and b/model_card/images/layer_1_attention_self_key.png differ diff --git a/model_card/images/layer_1_attention_self_query.png b/model_card/images/layer_1_attention_self_query.png new file mode 100644 index 0000000000000000000000000000000000000000..4c1fef3f08bd8f3899ceed62b86f2a75b18ecada Binary files /dev/null and b/model_card/images/layer_1_attention_self_query.png differ diff --git a/model_card/images/layer_1_attention_self_value.png b/model_card/images/layer_1_attention_self_value.png new file mode 100644 index 0000000000000000000000000000000000000000..4c1fef3f08bd8f3899ceed62b86f2a75b18ecada Binary files /dev/null and b/model_card/images/layer_1_attention_self_value.png differ diff --git a/model_card/images/layer_1_intermediate_dense.png b/model_card/images/layer_1_intermediate_dense.png new file mode 100644 index 0000000000000000000000000000000000000000..b222cecaa5376557c86e9cc652ffa3415f3243a0 Binary files /dev/null and b/model_card/images/layer_1_intermediate_dense.png differ diff --git a/model_card/images/layer_1_output_dense.png b/model_card/images/layer_1_output_dense.png new file mode 100644 index 0000000000000000000000000000000000000000..b663bd24dbb51a20373d1cfb9646f534c4c70d62 Binary files /dev/null and b/model_card/images/layer_1_output_dense.png differ diff --git a/model_card/images/layer_2_attention_output_dense.png b/model_card/images/layer_2_attention_output_dense.png new file mode 100644 index 0000000000000000000000000000000000000000..45cf07a92c4c1ca4791b33afb296c5e412aa338c Binary files /dev/null and b/model_card/images/layer_2_attention_output_dense.png differ diff --git a/model_card/images/layer_2_attention_self_key.png b/model_card/images/layer_2_attention_self_key.png new file mode 100644 index 0000000000000000000000000000000000000000..ffcfeb7adbd74ead361768768bc001333e5853c0 Binary files /dev/null and b/model_card/images/layer_2_attention_self_key.png differ diff --git a/model_card/images/layer_2_attention_self_query.png b/model_card/images/layer_2_attention_self_query.png new file mode 100644 index 0000000000000000000000000000000000000000..ffcfeb7adbd74ead361768768bc001333e5853c0 Binary files /dev/null and b/model_card/images/layer_2_attention_self_query.png differ diff --git a/model_card/images/layer_2_attention_self_value.png b/model_card/images/layer_2_attention_self_value.png new file mode 100644 index 0000000000000000000000000000000000000000..ffcfeb7adbd74ead361768768bc001333e5853c0 Binary files /dev/null and b/model_card/images/layer_2_attention_self_value.png differ diff --git a/model_card/images/layer_2_intermediate_dense.png b/model_card/images/layer_2_intermediate_dense.png new file mode 100644 index 0000000000000000000000000000000000000000..609b7c558a5a19aa9316289e975b8129457d0d41 Binary files /dev/null and b/model_card/images/layer_2_intermediate_dense.png differ diff --git a/model_card/images/layer_2_output_dense.png b/model_card/images/layer_2_output_dense.png new file mode 100644 index 0000000000000000000000000000000000000000..eec84b01133e462ae8ff8f3421803e119d9f54e1 Binary files /dev/null and b/model_card/images/layer_2_output_dense.png differ diff --git a/model_card/images/layer_3_attention_output_dense.png b/model_card/images/layer_3_attention_output_dense.png new file mode 100644 index 0000000000000000000000000000000000000000..45cf07a92c4c1ca4791b33afb296c5e412aa338c Binary files /dev/null and b/model_card/images/layer_3_attention_output_dense.png differ diff --git a/model_card/images/layer_3_attention_self_key.png b/model_card/images/layer_3_attention_self_key.png new file mode 100644 index 0000000000000000000000000000000000000000..ffcfeb7adbd74ead361768768bc001333e5853c0 Binary files /dev/null and b/model_card/images/layer_3_attention_self_key.png differ diff --git a/model_card/images/layer_3_attention_self_query.png b/model_card/images/layer_3_attention_self_query.png new file mode 100644 index 0000000000000000000000000000000000000000..ffcfeb7adbd74ead361768768bc001333e5853c0 Binary files /dev/null and b/model_card/images/layer_3_attention_self_query.png differ diff --git a/model_card/images/layer_3_attention_self_value.png b/model_card/images/layer_3_attention_self_value.png new file mode 100644 index 0000000000000000000000000000000000000000..ffcfeb7adbd74ead361768768bc001333e5853c0 Binary files /dev/null and b/model_card/images/layer_3_attention_self_value.png differ diff --git a/model_card/images/layer_3_intermediate_dense.png b/model_card/images/layer_3_intermediate_dense.png new file mode 100644 index 0000000000000000000000000000000000000000..f8698f74016b35a7c8ae4e2c9af65a9781899fe6 Binary files /dev/null and b/model_card/images/layer_3_intermediate_dense.png differ diff --git a/model_card/images/layer_3_output_dense.png b/model_card/images/layer_3_output_dense.png new file mode 100644 index 0000000000000000000000000000000000000000..bc6ffb0f7fd6190be0c9674e5c6dc1179af95d85 Binary files /dev/null and b/model_card/images/layer_3_output_dense.png differ diff --git a/model_card/images/layer_4_attention_output_dense.png b/model_card/images/layer_4_attention_output_dense.png new file mode 100644 index 0000000000000000000000000000000000000000..356d405672c91fb1859f4956d1672c117b834d51 Binary files /dev/null and b/model_card/images/layer_4_attention_output_dense.png differ diff --git a/model_card/images/layer_4_attention_self_key.png b/model_card/images/layer_4_attention_self_key.png new file mode 100644 index 0000000000000000000000000000000000000000..ea80e3b1550733330c043dc0792df62aa1d070a7 Binary files /dev/null and b/model_card/images/layer_4_attention_self_key.png differ diff --git a/model_card/images/layer_4_attention_self_query.png b/model_card/images/layer_4_attention_self_query.png new file mode 100644 index 0000000000000000000000000000000000000000..ea80e3b1550733330c043dc0792df62aa1d070a7 Binary files /dev/null and b/model_card/images/layer_4_attention_self_query.png differ diff --git a/model_card/images/layer_4_attention_self_value.png b/model_card/images/layer_4_attention_self_value.png new file mode 100644 index 0000000000000000000000000000000000000000..ea80e3b1550733330c043dc0792df62aa1d070a7 Binary files /dev/null and b/model_card/images/layer_4_attention_self_value.png differ diff --git a/model_card/images/layer_4_intermediate_dense.png b/model_card/images/layer_4_intermediate_dense.png new file mode 100644 index 0000000000000000000000000000000000000000..b3fbb3ff79c810f418061032a1c0be2e0a8e87ee Binary files /dev/null and b/model_card/images/layer_4_intermediate_dense.png differ diff --git a/model_card/images/layer_4_output_dense.png b/model_card/images/layer_4_output_dense.png new file mode 100644 index 0000000000000000000000000000000000000000..2b2f7e262cfcdc568c08560ea4530789ff489bfb Binary files /dev/null and b/model_card/images/layer_4_output_dense.png differ diff --git a/model_card/images/layer_5_attention_output_dense.png b/model_card/images/layer_5_attention_output_dense.png new file mode 100644 index 0000000000000000000000000000000000000000..fd061364f95580bd72d9c356b5fc4c479bdea1cd Binary files /dev/null and b/model_card/images/layer_5_attention_output_dense.png differ diff --git a/model_card/images/layer_5_attention_self_key.png b/model_card/images/layer_5_attention_self_key.png new file mode 100644 index 0000000000000000000000000000000000000000..66df60b2ef6c6e0550cf6f181b0ea931691f4a94 Binary files /dev/null and b/model_card/images/layer_5_attention_self_key.png differ diff --git a/model_card/images/layer_5_attention_self_query.png b/model_card/images/layer_5_attention_self_query.png new file mode 100644 index 0000000000000000000000000000000000000000..66df60b2ef6c6e0550cf6f181b0ea931691f4a94 Binary files /dev/null and b/model_card/images/layer_5_attention_self_query.png differ diff --git a/model_card/images/layer_5_attention_self_value.png b/model_card/images/layer_5_attention_self_value.png new file mode 100644 index 0000000000000000000000000000000000000000..66df60b2ef6c6e0550cf6f181b0ea931691f4a94 Binary files /dev/null and b/model_card/images/layer_5_attention_self_value.png differ diff --git a/model_card/images/layer_5_intermediate_dense.png b/model_card/images/layer_5_intermediate_dense.png new file mode 100644 index 0000000000000000000000000000000000000000..609b7c558a5a19aa9316289e975b8129457d0d41 Binary files /dev/null and b/model_card/images/layer_5_intermediate_dense.png differ diff --git a/model_card/images/layer_5_output_dense.png b/model_card/images/layer_5_output_dense.png new file mode 100644 index 0000000000000000000000000000000000000000..eec84b01133e462ae8ff8f3421803e119d9f54e1 Binary files /dev/null and b/model_card/images/layer_5_output_dense.png differ diff --git a/model_card/images/layer_6_attention_output_dense.png b/model_card/images/layer_6_attention_output_dense.png new file mode 100644 index 0000000000000000000000000000000000000000..45cf07a92c4c1ca4791b33afb296c5e412aa338c Binary files /dev/null and b/model_card/images/layer_6_attention_output_dense.png differ diff --git a/model_card/images/layer_6_attention_self_key.png b/model_card/images/layer_6_attention_self_key.png new file mode 100644 index 0000000000000000000000000000000000000000..ffcfeb7adbd74ead361768768bc001333e5853c0 Binary files /dev/null and b/model_card/images/layer_6_attention_self_key.png differ diff --git a/model_card/images/layer_6_attention_self_query.png b/model_card/images/layer_6_attention_self_query.png new file mode 100644 index 0000000000000000000000000000000000000000..ffcfeb7adbd74ead361768768bc001333e5853c0 Binary files /dev/null and b/model_card/images/layer_6_attention_self_query.png differ diff --git a/model_card/images/layer_6_attention_self_value.png b/model_card/images/layer_6_attention_self_value.png new file mode 100644 index 0000000000000000000000000000000000000000..ffcfeb7adbd74ead361768768bc001333e5853c0 Binary files /dev/null and b/model_card/images/layer_6_attention_self_value.png differ diff --git a/model_card/images/layer_6_intermediate_dense.png b/model_card/images/layer_6_intermediate_dense.png new file mode 100644 index 0000000000000000000000000000000000000000..06c3def32f0f554b597458086d6ec74c527505a9 Binary files /dev/null and b/model_card/images/layer_6_intermediate_dense.png differ diff --git a/model_card/images/layer_6_output_dense.png b/model_card/images/layer_6_output_dense.png new file mode 100644 index 0000000000000000000000000000000000000000..fa580fa40ecb6cede9c676dc28a24d5a7071ca9f Binary files /dev/null and b/model_card/images/layer_6_output_dense.png differ diff --git a/model_card/images/layer_7_attention_output_dense.png b/model_card/images/layer_7_attention_output_dense.png new file mode 100644 index 0000000000000000000000000000000000000000..e1dd9d7b91bb91834da5762f6857d55af1e6034a Binary files /dev/null and b/model_card/images/layer_7_attention_output_dense.png differ diff --git a/model_card/images/layer_7_attention_self_key.png b/model_card/images/layer_7_attention_self_key.png new file mode 100644 index 0000000000000000000000000000000000000000..45e35c86fa5a2a0b337f449ab82e062ce31742d6 Binary files /dev/null and b/model_card/images/layer_7_attention_self_key.png differ diff --git a/model_card/images/layer_7_attention_self_query.png b/model_card/images/layer_7_attention_self_query.png new file mode 100644 index 0000000000000000000000000000000000000000..45e35c86fa5a2a0b337f449ab82e062ce31742d6 Binary files /dev/null and b/model_card/images/layer_7_attention_self_query.png differ diff --git a/model_card/images/layer_7_attention_self_value.png b/model_card/images/layer_7_attention_self_value.png new file mode 100644 index 0000000000000000000000000000000000000000..45e35c86fa5a2a0b337f449ab82e062ce31742d6 Binary files /dev/null and b/model_card/images/layer_7_attention_self_value.png differ diff --git a/model_card/images/layer_7_intermediate_dense.png b/model_card/images/layer_7_intermediate_dense.png new file mode 100644 index 0000000000000000000000000000000000000000..9c9964eb23650f1e57068f22497441a5bf66658b Binary files /dev/null and b/model_card/images/layer_7_intermediate_dense.png differ diff --git a/model_card/images/layer_7_output_dense.png b/model_card/images/layer_7_output_dense.png new file mode 100644 index 0000000000000000000000000000000000000000..1db61fe5570a3fa0a3bc21785377c83e5a86e84c Binary files /dev/null and b/model_card/images/layer_7_output_dense.png differ diff --git a/model_card/images/layer_8_attention_output_dense.png b/model_card/images/layer_8_attention_output_dense.png new file mode 100644 index 0000000000000000000000000000000000000000..fd061364f95580bd72d9c356b5fc4c479bdea1cd Binary files /dev/null and b/model_card/images/layer_8_attention_output_dense.png differ diff --git a/model_card/images/layer_8_attention_self_key.png b/model_card/images/layer_8_attention_self_key.png new file mode 100644 index 0000000000000000000000000000000000000000..66df60b2ef6c6e0550cf6f181b0ea931691f4a94 Binary files /dev/null and b/model_card/images/layer_8_attention_self_key.png differ diff --git a/model_card/images/layer_8_attention_self_query.png b/model_card/images/layer_8_attention_self_query.png new file mode 100644 index 0000000000000000000000000000000000000000..66df60b2ef6c6e0550cf6f181b0ea931691f4a94 Binary files /dev/null and b/model_card/images/layer_8_attention_self_query.png differ diff --git a/model_card/images/layer_8_attention_self_value.png b/model_card/images/layer_8_attention_self_value.png new file mode 100644 index 0000000000000000000000000000000000000000..66df60b2ef6c6e0550cf6f181b0ea931691f4a94 Binary files /dev/null and b/model_card/images/layer_8_attention_self_value.png differ diff --git a/model_card/images/layer_8_intermediate_dense.png b/model_card/images/layer_8_intermediate_dense.png new file mode 100644 index 0000000000000000000000000000000000000000..205d5fa31f4bb86b1ba4c6a8b0b19d1ca023a572 Binary files /dev/null and b/model_card/images/layer_8_intermediate_dense.png differ diff --git a/model_card/images/layer_8_output_dense.png b/model_card/images/layer_8_output_dense.png new file mode 100644 index 0000000000000000000000000000000000000000..08241eeb74523a6f953052f7adedcaa3a93634aa Binary files /dev/null and b/model_card/images/layer_8_output_dense.png differ diff --git a/model_card/images/layer_9_attention_output_dense.png b/model_card/images/layer_9_attention_output_dense.png new file mode 100644 index 0000000000000000000000000000000000000000..cddee01449ffc5291880e5ed070f4bb5c2431134 Binary files /dev/null and b/model_card/images/layer_9_attention_output_dense.png differ diff --git a/model_card/images/layer_9_attention_self_key.png b/model_card/images/layer_9_attention_self_key.png new file mode 100644 index 0000000000000000000000000000000000000000..838a4814aa2e5e5385afdbddee234b2dd8b740cf Binary files /dev/null and b/model_card/images/layer_9_attention_self_key.png differ diff --git a/model_card/images/layer_9_attention_self_query.png b/model_card/images/layer_9_attention_self_query.png new file mode 100644 index 0000000000000000000000000000000000000000..838a4814aa2e5e5385afdbddee234b2dd8b740cf Binary files /dev/null and b/model_card/images/layer_9_attention_self_query.png differ diff --git a/model_card/images/layer_9_attention_self_value.png b/model_card/images/layer_9_attention_self_value.png new file mode 100644 index 0000000000000000000000000000000000000000..838a4814aa2e5e5385afdbddee234b2dd8b740cf Binary files /dev/null and b/model_card/images/layer_9_attention_self_value.png differ diff --git a/model_card/images/layer_9_intermediate_dense.png b/model_card/images/layer_9_intermediate_dense.png new file mode 100644 index 0000000000000000000000000000000000000000..191674c88370d7e5e07852b9bafe55d79abd19d8 Binary files /dev/null and b/model_card/images/layer_9_intermediate_dense.png differ diff --git a/model_card/images/layer_9_output_dense.png b/model_card/images/layer_9_output_dense.png new file mode 100644 index 0000000000000000000000000000000000000000..46638f4ef2c21b0280de4715cd4720d921424c22 Binary files /dev/null and b/model_card/images/layer_9_output_dense.png differ diff --git a/model_card/pruning_info.js b/model_card/pruning_info.js index 7bd862c1c1f9af53f32746d2ae65b5b4464271d5..959ab3109451f6106a52e534122b155811e628a9 100644 --- a/model_card/pruning_info.js +++ b/model_card/pruning_info.js @@ -16,9 +16,9 @@ - var element = document.getElementById("f7197e6f-ccea-4a42-8fb9-7a8fe7136cf0"); + var element = document.getElementById("b1676015-bd1f-421f-9c37-1ae60c623ec3"); if (element == null) { - console.warn("Bokeh: autoload.js configured with elementid 'f7197e6f-ccea-4a42-8fb9-7a8fe7136cf0' but no matching script tag was found.") + console.warn("Bokeh: autoload.js configured with elementid 'b1676015-bd1f-421f-9c37-1ae60c623ec3' but no matching script tag was found.") } @@ -115,8 +115,8 @@ (function(root) { function embed_document(root) { - var docs_json = '{"9e93a1e1-e869-4f7b-a3ab-1626817aa47f":{"roots":{"references":[{"attributes":{"factors":["0","1","2","3","4","5","6","7","8","9","10","11"],"range_padding":0.1},"id":"1004","type":"FactorRange"},{"attributes":{},"id":"1052","type":"UnionRenderers"},{"attributes":{"axis":{"id":"1012"},"grid_line_color":null,"ticker":null},"id":"1014","type":"Grid"},{"attributes":{"text":"Pruned Transformer Heads"},"id":"1002","type":"Title"},{"attributes":{},"id":"1053","type":"Selection"},{"attributes":{"axis_label":"Layer index","formatter":{"id":"1034"},"minor_tick_line_color":null,"ticker":{"id":"1013"}},"id":"1012","type":"CategoricalAxis"},{"attributes":{},"id":"1013","type":"CategoricalTicker"},{"attributes":{},"id":"1034","type":"CategoricalTickFormatter"},{"attributes":{"fields":[]},"id":"1020","type":"Stack"},{"attributes":{},"id":"1010","type":"LinearScale"},{"attributes":{"fields":["active","pruned"]},"id":"1023","type":"Stack"},{"attributes":{"source":{"id":"1024"}},"id":"1029","type":"CDSView"},{"attributes":{"above":[{"id":"1055"}],"below":[{"id":"1012"}],"center":[{"id":"1014"},{"id":"1018"},{"id":"1037"}],"left":[{"id":"1015"}],"outline_line_color":null,"plot_height":400,"renderers":[{"id":"1028"},{"id":"1043"}],"title":{"id":"1002"},"toolbar":{"id":"1019"},"toolbar_location":null,"x_range":{"id":"1004"},"x_scale":{"id":"1008"},"y_range":{"id":"1006"},"y_scale":{"id":"1010"}},"id":"1001","subtype":"Figure","type":"Plot"},{"attributes":{"label":{"value":"active"},"renderers":[{"id":"1028"}]},"id":"1038","type":"LegendItem"},{"attributes":{},"id":"1016","type":"BasicTicker"},{"attributes":{"bottom":{"expr":{"id":"1020"}},"fill_alpha":{"value":0.1},"fill_color":{"value":"#0000ff"},"line_alpha":{"value":0.1},"line_color":{"value":"#0000ff"},"top":{"expr":{"id":"1021"}},"width":{"value":0.9},"x":{"field":"layers"}},"id":"1027","type":"VBar"},{"attributes":{"axis_label":"Heads count","formatter":{"id":"1032"},"minor_tick_line_color":null,"ticker":{"id":"1016"}},"id":"1015","type":"LinearAxis"},{"attributes":{"data_source":{"id":"1024"},"glyph":{"id":"1026"},"hover_glyph":null,"muted_glyph":null,"name":"active","nonselection_glyph":{"id":"1027"},"selection_glyph":null,"view":{"id":"1029"}},"id":"1028","type":"GlyphRenderer"},{"attributes":{},"id":"1035","type":"UnionRenderers"},{"attributes":{"label":{"value":"pruned"},"renderers":[{"id":"1043"}]},"id":"1057","type":"LegendItem"},{"attributes":{},"id":"1036","type":"Selection"},{"attributes":{"items":[{"id":"1038"},{"id":"1054"}],"location":null},"id":"1037","type":"Legend"},{"attributes":{"label":{"value":"active"},"renderers":[{"id":"1028"}]},"id":"1056","type":"LegendItem"},{"attributes":{"axis":{"id":"1015"},"dimension":1,"ticker":null},"id":"1018","type":"Grid"},{"attributes":{"fields":["active"]},"id":"1022","type":"Stack"},{"attributes":{"data_source":{"id":"1039"},"glyph":{"id":"1041"},"hover_glyph":null,"muted_glyph":null,"name":"pruned","nonselection_glyph":{"id":"1042"},"selection_glyph":null,"view":{"id":"1044"}},"id":"1043","type":"GlyphRenderer"},{"attributes":{},"id":"1032","type":"BasicTickFormatter"},{"attributes":{"active_drag":"auto","active_inspect":"auto","active_multi":null,"active_scroll":"auto","active_tap":"auto"},"id":"1019","type":"Toolbar"},{"attributes":{"bottom":{"expr":{"id":"1022"}},"fill_alpha":{"value":0.1},"fill_color":{"value":"#ffcccc"},"line_alpha":{"value":0.1},"line_color":{"value":"#ffcccc"},"top":{"expr":{"id":"1023"}},"width":{"value":0.9},"x":{"field":"layers"}},"id":"1042","type":"VBar"},{"attributes":{"fields":["active"]},"id":"1021","type":"Stack"},{"attributes":{"data":{"active":[7,5,9,9,11,10,9,8,10,6,7,5],"layers":["0","1","2","3","4","5","6","7","8","9","10","11"],"pruned":[5,7,3,3,1,2,3,4,2,6,5,7]},"selected":{"id":"1036"},"selection_policy":{"id":"1035"}},"id":"1024","type":"ColumnDataSource"},{"attributes":{"bottom":{"expr":{"id":"1022"}},"fill_color":{"value":"#ffcccc"},"line_color":{"value":"#ffcccc"},"top":{"expr":{"id":"1023"}},"width":{"value":0.9},"x":{"field":"layers"}},"id":"1041","type":"VBar"},{"attributes":{},"id":"1008","type":"CategoricalScale"},{"attributes":{"label":{"value":"pruned"},"renderers":[{"id":"1043"}]},"id":"1054","type":"LegendItem"},{"attributes":{"start":0},"id":"1006","type":"DataRange1d"},{"attributes":{"items":[{"id":"1056"},{"id":"1057"}],"location":[10,0],"orientation":"horizontal"},"id":"1055","type":"Legend"},{"attributes":{"bottom":{"expr":{"id":"1020"}},"fill_color":{"value":"#0000ff"},"line_color":{"value":"#0000ff"},"top":{"expr":{"id":"1021"}},"width":{"value":0.9},"x":{"field":"layers"}},"id":"1026","type":"VBar"},{"attributes":{"source":{"id":"1039"}},"id":"1044","type":"CDSView"},{"attributes":{"data":{"active":[7,5,9,9,11,10,9,8,10,6,7,5],"layers":["0","1","2","3","4","5","6","7","8","9","10","11"],"pruned":[5,7,3,3,1,2,3,4,2,6,5,7]},"selected":{"id":"1053"},"selection_policy":{"id":"1052"}},"id":"1039","type":"ColumnDataSource"}],"root_ids":["1001"]},"title":"Bokeh Application","version":"2.2.3"}}'; - var render_items = [{"docid":"9e93a1e1-e869-4f7b-a3ab-1626817aa47f","root_ids":["1001"],"roots":{"1001":"f7197e6f-ccea-4a42-8fb9-7a8fe7136cf0"}}]; + var docs_json = '{"28cf69ed-fc07-48ce-a7e7-7e4f2088f156":{"roots":{"references":[{"attributes":{"bottom":{"expr":{"id":"1020"}},"fill_color":{"value":"#0000ff"},"line_color":{"value":"#0000ff"},"top":{"expr":{"id":"1021"}},"width":{"value":0.9},"x":{"field":"layers"}},"id":"1026","type":"VBar"},{"attributes":{"bottom":{"expr":{"id":"1022"}},"fill_alpha":{"value":0.1},"fill_color":{"value":"#ffcccc"},"line_alpha":{"value":0.1},"line_color":{"value":"#ffcccc"},"top":{"expr":{"id":"1023"}},"width":{"value":0.9},"x":{"field":"layers"}},"id":"1042","type":"VBar"},{"attributes":{},"id":"1034","type":"BasicTickFormatter"},{"attributes":{},"id":"1032","type":"CategoricalTickFormatter"},{"attributes":{"label":{"value":"pruned"},"renderers":[{"id":"1043"}]},"id":"1054","type":"LegendItem"},{"attributes":{"fields":["active","pruned"]},"id":"1023","type":"Stack"},{"attributes":{"start":0},"id":"1006","type":"DataRange1d"},{"attributes":{"axis_label":"Layer index","formatter":{"id":"1032"},"minor_tick_line_color":null,"ticker":{"id":"1013"}},"id":"1012","type":"CategoricalAxis"},{"attributes":{"fields":["active"]},"id":"1021","type":"Stack"},{"attributes":{},"id":"1010","type":"LinearScale"},{"attributes":{"fields":["active"]},"id":"1022","type":"Stack"},{"attributes":{},"id":"1052","type":"UnionRenderers"},{"attributes":{},"id":"1008","type":"CategoricalScale"},{"attributes":{},"id":"1053","type":"Selection"},{"attributes":{},"id":"1013","type":"CategoricalTicker"},{"attributes":{},"id":"1035","type":"UnionRenderers"},{"attributes":{},"id":"1036","type":"Selection"},{"attributes":{"source":{"id":"1024"}},"id":"1029","type":"CDSView"},{"attributes":{"axis":{"id":"1012"},"grid_line_color":null,"ticker":null},"id":"1014","type":"Grid"},{"attributes":{"factors":["0","1","2","3","4","5","6","7","8","9","10","11"],"range_padding":0.1},"id":"1004","type":"FactorRange"},{"attributes":{"data_source":{"id":"1024"},"glyph":{"id":"1026"},"hover_glyph":null,"muted_glyph":null,"name":"active","nonselection_glyph":{"id":"1027"},"selection_glyph":null,"view":{"id":"1029"}},"id":"1028","type":"GlyphRenderer"},{"attributes":{"above":[{"id":"1055"}],"below":[{"id":"1012"}],"center":[{"id":"1014"},{"id":"1018"},{"id":"1037"}],"left":[{"id":"1015"}],"outline_line_color":null,"plot_height":400,"renderers":[{"id":"1028"},{"id":"1043"}],"title":{"id":"1002"},"toolbar":{"id":"1019"},"toolbar_location":null,"x_range":{"id":"1004"},"x_scale":{"id":"1008"},"y_range":{"id":"1006"},"y_scale":{"id":"1010"}},"id":"1001","subtype":"Figure","type":"Plot"},{"attributes":{"bottom":{"expr":{"id":"1020"}},"fill_alpha":{"value":0.1},"fill_color":{"value":"#0000ff"},"line_alpha":{"value":0.1},"line_color":{"value":"#0000ff"},"top":{"expr":{"id":"1021"}},"width":{"value":0.9},"x":{"field":"layers"}},"id":"1027","type":"VBar"},{"attributes":{"items":[{"id":"1056"},{"id":"1057"}],"location":[10,0],"orientation":"horizontal"},"id":"1055","type":"Legend"},{"attributes":{"fields":[]},"id":"1020","type":"Stack"},{"attributes":{"data":{"active":[7,5,9,9,11,10,9,8,10,6,7,5],"layers":["0","1","2","3","4","5","6","7","8","9","10","11"],"pruned":[5,7,3,3,1,2,3,4,2,6,5,7]},"selected":{"id":"1036"},"selection_policy":{"id":"1035"}},"id":"1024","type":"ColumnDataSource"},{"attributes":{"label":{"value":"active"},"renderers":[{"id":"1028"}]},"id":"1056","type":"LegendItem"},{"attributes":{"axis":{"id":"1015"},"dimension":1,"ticker":null},"id":"1018","type":"Grid"},{"attributes":{"data":{"active":[7,5,9,9,11,10,9,8,10,6,7,5],"layers":["0","1","2","3","4","5","6","7","8","9","10","11"],"pruned":[5,7,3,3,1,2,3,4,2,6,5,7]},"selected":{"id":"1053"},"selection_policy":{"id":"1052"}},"id":"1039","type":"ColumnDataSource"},{"attributes":{"axis_label":"Heads count","formatter":{"id":"1034"},"minor_tick_line_color":null,"ticker":{"id":"1016"}},"id":"1015","type":"LinearAxis"},{"attributes":{"items":[{"id":"1038"},{"id":"1054"}],"location":null},"id":"1037","type":"Legend"},{"attributes":{"label":{"value":"pruned"},"renderers":[{"id":"1043"}]},"id":"1057","type":"LegendItem"},{"attributes":{},"id":"1016","type":"BasicTicker"},{"attributes":{"bottom":{"expr":{"id":"1022"}},"fill_color":{"value":"#ffcccc"},"line_color":{"value":"#ffcccc"},"top":{"expr":{"id":"1023"}},"width":{"value":0.9},"x":{"field":"layers"}},"id":"1041","type":"VBar"},{"attributes":{"label":{"value":"active"},"renderers":[{"id":"1028"}]},"id":"1038","type":"LegendItem"},{"attributes":{"active_drag":"auto","active_inspect":"auto","active_multi":null,"active_scroll":"auto","active_tap":"auto"},"id":"1019","type":"Toolbar"},{"attributes":{"source":{"id":"1039"}},"id":"1044","type":"CDSView"},{"attributes":{"text":"Pruned Transformer Heads"},"id":"1002","type":"Title"},{"attributes":{"data_source":{"id":"1039"},"glyph":{"id":"1041"},"hover_glyph":null,"muted_glyph":null,"name":"pruned","nonselection_glyph":{"id":"1042"},"selection_glyph":null,"view":{"id":"1044"}},"id":"1043","type":"GlyphRenderer"}],"root_ids":["1001"]},"title":"Bokeh Application","version":"2.2.3"}}'; + var render_items = [{"docid":"28cf69ed-fc07-48ce-a7e7-7e4f2088f156","root_ids":["1001"],"roots":{"1001":"b1676015-bd1f-421f-9c37-1ae60c623ec3"}}]; root.Bokeh.embed.embed_items(docs_json, render_items); }