update

.idea/workspace.xml

@@ -1,62 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<project version="4">
-  <component name="AutoImportSettings">
-    <option name="autoReloadType" value="SELECTIVE" />
-  </component>
-  <component name="ChangeListManager">
-    <list default="true" id="c90ca726-b813-4875-9ed7-40059a328db6" name="Changes" comment="">
-      <change beforePath="$PROJECT_DIR$/README.md" beforeDir="false" afterPath="$PROJECT_DIR$/README.md" afterDir="false" />
-    </list>
-    <option name="SHOW_DIALOG" value="false" />
-    <option name="HIGHLIGHT_CONFLICTS" value="true" />
-    <option name="HIGHLIGHT_NON_ACTIVE_CHANGELIST" value="false" />
-    <option name="LAST_RESOLUTION" value="IGNORE" />
-  </component>
-  <component name="FileTemplateManagerImpl">
-    <option name="RECENT_TEMPLATES">
-      <list>
-        <option value="Python Script" />
-      </list>
-    </option>
-  </component>
-  <component name="Git.Settings">
-    <option name="RECENT_GIT_ROOT_PATH" value="$PROJECT_DIR$" />
-  </component>
-  <component name="MarkdownSettingsMigration">
-    <option name="stateVersion" value="1" />
-  </component>
-  <component name="ProjectId" id="2x4dTrhzelm4q7ZmUKxXU7syYIs" />
-  <component name="ProjectLevelVcsManager" settingsEditedManually="true" />
-  <component name="ProjectViewState">
-    <option name="hideEmptyMiddlePackages" value="true" />
-    <option name="showLibraryContents" value="true" />
-  </component>
-  <component name="PropertiesComponent">{
-  &quot;keyToString&quot;: {
-    &quot;RunOnceActivity.OpenProjectViewOnStart&quot;: &quot;true&quot;,
-    &quot;RunOnceActivity.ShowReadmeOnStart&quot;: &quot;true&quot;,
-    &quot;settings.editor.selected.configurable&quot;: &quot;reference.idesettings.debugger.python&quot;
-  }
-}</component>
-  <component name="SpellCheckerSettings" RuntimeDictionaries="0" Folders="0" CustomDictionaries="0" DefaultDictionary="application-level" UseSingleDictionary="true" transferred="true" />
-  <component name="TaskManager">
-    <task active="true" id="Default" summary="Default task">
-      <changelist id="c90ca726-b813-4875-9ed7-40059a328db6" name="Changes" comment="" />
-      <created>1747201290280</created>
-      <option name="number" value="Default" />
-      <option name="presentableId" value="Default" />
-      <updated>1747201290280</updated>
-    </task>
-    <servers />
-  </component>
-  <component name="XDebuggerManager">
-    <breakpoint-manager>
-      <breakpoints>
-        <line-breakpoint enabled="true" suspend="THREAD" type="python-line">
-          <url>file://$PROJECT_DIR$/model/utils.py</url>
-          <option name="timeStamp" value="1" />
-        </line-breakpoint>
-      </breakpoints>
-    </breakpoint-manager>
-  </component>
-</project>

Example.ipynb

@@ -19,7 +19,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "checkpoint_path=\"checkpoint-4120000\"\n",
+    "checkpoint_path=\"lamthuy/MorganGen\"\n",
     "model = AutoModelForSeq2SeqLM.from_pretrained(checkpoint_path)\n",
     "tokenizer = SmilesTokenizer(vocab_file=\"data/vocab_morgan.txt\")"
    ]
@@ -34,7 +34,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "[07:30:31] DEPRECATION WARNING: please use MorganGenerator\n"
+      "[22:30:12] DEPRECATION WARNING: please use MorganGenerator\n"
      ]
     }
    ],
@@ -108,16 +108,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 8,
    "id": "c4dcff84-4552-48ca-8b2c-8f2d4911ec8a",
    "metadata": {},
    "outputs": [
     {
      "data": {
-      "application/3dmoljs_load.v0": "<div id=\"3dmolviewer_17472043464774249\"  style=\"position: relative; width: 400px; height: 300px;\">\n        <p id=\"3dmolwarning_17472043464774249\" style=\"background-color:#ffcccc;color:black\">3Dmol.js failed to load for some reason.  Please check your browser console for error messages.<br></p>\n        </div>\n<script>\n\nvar loadScriptAsync = function(uri){\n  return new Promise((resolve, reject) => {\n    //this is to ignore the existence of requirejs amd\n    var savedexports, savedmodule;\n    if (typeof exports !== 'undefined') savedexports = exports;\n    else exports = {}\n    if (typeof module !== 'undefined') savedmodule = module;\n    else module = {}\n\n    var tag = document.createElement('script');\n    tag.src = uri;\n    tag.async = true;\n    tag.onload = () => {\n        exports = savedexports;\n        module = savedmodule;\n        resolve();\n    };\n  var firstScriptTag = document.getElementsByTagName('script')[0];\n  firstScriptTag.parentNode.insertBefore(tag, firstScriptTag);\n});\n};\n\nif(typeof $3Dmolpromise === 'undefined') {\n$3Dmolpromise = null;\n  $3Dmolpromise = loadScriptAsync('https://cdnjs.cloudflare.com/ajax/libs/3Dmol/2.2.0/3Dmol-min.js');\n}\n\nvar viewer_17472043464774249 = null;\nvar warn = document.getElementById(\"3dmolwarning_17472043464774249\");\nif(warn) {\n    warn.parentNode.removeChild(warn);\n}\n$3Dmolpromise.then(function() {\nviewer_17472043464774249 = $3Dmol.createViewer(document.getElementById(\"3dmolviewer_17472043464774249\"),{backgroundColor:\"white\"});\nviewer_17472043464774249.zoomTo();\n\tviewer_17472043464774249.addModel(\"HETATM    1  C1  UNL     1      -2.945  -2.264  -0.022  1.00  0.00           C  \\nHETATM    2  C2  UNL     1      -2.075  -1.145  -0.483  1.00  0.00           C  \\nHETATM    3  O1  UNL     1      -2.368  -0.527  -1.543  1.00  0.00           O  \\nHETATM    4  O2  UNL     1      -0.889  -0.871   0.209  1.00  0.00           O  \\nHETATM    5  C3  UNL     1      -0.099   0.280   0.046  1.00  0.00           C  \\nHETATM    6  C4  UNL     1      -0.687   1.518  -0.278  1.00  0.00           C  \\nHETATM    7  C5  UNL     1       0.099   2.661  -0.426  1.00  0.00           C  \\nHETATM    8  C6  UNL     1       1.478   2.588  -0.241  1.00  0.00           C  \\nHETATM    9  C7  UNL     1       2.075   1.374   0.100  1.00  0.00           C  \\nHETATM   10  C8  UNL     1       1.301   0.208   0.254  1.00  0.00           C  \\nHETATM   11  C9  UNL     1       1.979  -1.063   0.620  1.00  0.00           C  \\nHETATM   12  O3  UNL     1       1.327  -2.135   0.744  1.00  0.00           O  \\nHETATM   13  O4  UNL     1       3.356  -1.085   0.829  1.00  0.00           O  \\nHETATM   14  H1  UNL     1      -4.010  -2.038  -0.245  1.00  0.00           H  \\nHETATM   15  H2  UNL     1      -2.831  -2.404   1.073  1.00  0.00           H  \\nHETATM   16  H3  UNL     1      -2.652  -3.199  -0.542  1.00  0.00           H  \\nHETATM   17  H4  UNL     1      -1.759   1.611  -0.389  1.00  0.00           H  \\nHETATM   18  H5  UNL     1      -0.364   3.607  -0.675  1.00  0.00           H  \\nHETATM   19  H6  UNL     1       2.085   3.477  -0.355  1.00  0.00           H  \\nHETATM   20  H7  UNL     1       3.148   1.351   0.244  1.00  0.00           H  \\nHETATM   21  H8  UNL     1       3.831  -1.944   1.078  1.00  0.00           H  \\nCONECT    1    2   14   15   16\\nCONECT    2    3    3    4\\nCONECT    4    5\\nCONECT    5    6    6   10\\nCONECT    6    7   17\\nCONECT    7    8    8   18\\nCONECT    8    9   19\\nCONECT    9   10   10   20\\nCONECT   10   11\\nCONECT   11   12   12   13\\nCONECT   13   21\\nEND\\n\",\"pdb\");\n\tviewer_17472043464774249.setStyle({\"stick\": {}});\n\tviewer_17472043464774249.zoomTo();\nviewer_17472043464774249.render();\n});\n</script>",
+      "application/3dmoljs_load.v0": "<div id=\"3dmolviewer_1747776613981611\"  style=\"position: relative; width: 400px; height: 300px;\">\n        <p id=\"3dmolwarning_1747776613981611\" style=\"background-color:#ffcccc;color:black\">3Dmol.js failed to load for some reason.  Please check your browser console for error messages.<br></p>\n        </div>\n<script>\n\nvar loadScriptAsync = function(uri){\n  return new Promise((resolve, reject) => {\n    //this is to ignore the existence of requirejs amd\n    var savedexports, savedmodule;\n    if (typeof exports !== 'undefined') savedexports = exports;\n    else exports = {}\n    if (typeof module !== 'undefined') savedmodule = module;\n    else module = {}\n\n    var tag = document.createElement('script');\n    tag.src = uri;\n    tag.async = true;\n    tag.onload = () => {\n        exports = savedexports;\n        module = savedmodule;\n        resolve();\n    };\n  var firstScriptTag = document.getElementsByTagName('script')[0];\n  firstScriptTag.parentNode.insertBefore(tag, firstScriptTag);\n});\n};\n\nif(typeof $3Dmolpromise === 'undefined') {\n$3Dmolpromise = null;\n  $3Dmolpromise = loadScriptAsync('https://cdnjs.cloudflare.com/ajax/libs/3Dmol/2.4.2/3Dmol-min.js');\n}\n\nvar viewer_1747776613981611 = null;\nvar warn = document.getElementById(\"3dmolwarning_1747776613981611\");\nif(warn) {\n    warn.parentNode.removeChild(warn);\n}\n$3Dmolpromise.then(function() {\nviewer_1747776613981611 = $3Dmol.createViewer(document.getElementById(\"3dmolviewer_1747776613981611\"),{backgroundColor:\"white\"});\nviewer_1747776613981611.zoomTo();\n\tviewer_1747776613981611.addModel(\"HETATM    1  C1  UNL     1      -2.960  -2.244  -0.038  1.00  0.00           C  \\nHETATM    2  C2  UNL     1      -2.082  -1.129  -0.492  1.00  0.00           C  \\nHETATM    3  O1  UNL     1      -2.368  -0.505  -1.549  1.00  0.00           O  \\nHETATM    4  O2  UNL     1      -0.895  -0.866   0.204  1.00  0.00           O  \\nHETATM    5  C3  UNL     1      -0.098   0.280   0.047  1.00  0.00           C  \\nHETATM    6  C4  UNL     1      -0.677   1.524  -0.273  1.00  0.00           C  \\nHETATM    7  C5  UNL     1       0.117   2.662  -0.414  1.00  0.00           C  \\nHETATM    8  C6  UNL     1       1.495   2.579  -0.227  1.00  0.00           C  \\nHETATM    9  C7  UNL     1       2.084   1.360   0.110  1.00  0.00           C  \\nHETATM   10  C8  UNL     1       1.302   0.198   0.258  1.00  0.00           C  \\nHETATM   11  C9  UNL     1       1.971  -1.079   0.619  1.00  0.00           C  \\nHETATM   12  O3  UNL     1       1.311  -2.146   0.738  1.00  0.00           O  \\nHETATM   13  O4  UNL     1       3.347  -1.111   0.831  1.00  0.00           O  \\nHETATM   14  H1  UNL     1      -4.022  -2.010  -0.262  1.00  0.00           H  \\nHETATM   15  H2  UNL     1      -2.849  -2.390   1.057  1.00  0.00           H  \\nHETATM   16  H3  UNL     1      -2.671  -3.179  -0.561  1.00  0.00           H  \\nHETATM   17  H4  UNL     1      -1.748   1.624  -0.386  1.00  0.00           H  \\nHETATM   18  H5  UNL     1      -0.339   3.613  -0.660  1.00  0.00           H  \\nHETATM   19  H6  UNL     1       2.109   3.465  -0.336  1.00  0.00           H  \\nHETATM   20  H7  UNL     1       3.157   1.329   0.256  1.00  0.00           H  \\nHETATM   21  H8  UNL     1       3.816  -1.974   1.077  1.00  0.00           H  \\nCONECT    1    2   14   15   16\\nCONECT    2    3    3    4\\nCONECT    4    5\\nCONECT    5    6    6   10\\nCONECT    6    7   17\\nCONECT    7    8    8   18\\nCONECT    8    9   19\\nCONECT    9   10   10   20\\nCONECT   10   11\\nCONECT   11   12   12   13\\nCONECT   13   21\\nEND\\n\",\"pdb\");\n\tviewer_1747776613981611.setStyle({\"stick\": {}});\n\tviewer_1747776613981611.zoomTo();\nviewer_1747776613981611.render();\n});\n</script>",
       "text/html": [
-       "<div id=\"3dmolviewer_17472043464774249\"  style=\"position: relative; width: 400px; height: 300px;\">\n",
-       "        <p id=\"3dmolwarning_17472043464774249\" style=\"background-color:#ffcccc;color:black\">3Dmol.js failed to load for some reason.  Please check your browser console for error messages.<br></p>\n",
+       "<div id=\"3dmolviewer_1747776613981611\"  style=\"position: relative; width: 400px; height: 300px;\">\n",
+       "        <p id=\"3dmolwarning_1747776613981611\" style=\"background-color:#ffcccc;color:black\">3Dmol.js failed to load for some reason.  Please check your browser console for error messages.<br></p>\n",
        "        </div>\n",
        "<script>\n",
        "\n",
@@ -145,21 +145,21 @@
        "\n",
        "if(typeof $3Dmolpromise === 'undefined') {\n",
        "$3Dmolpromise = null;\n",
-       "  $3Dmolpromise = loadScriptAsync('https://cdnjs.cloudflare.com/ajax/libs/3Dmol/2.2.0/3Dmol-min.js');\n",
+       "  $3Dmolpromise = loadScriptAsync('https://cdnjs.cloudflare.com/ajax/libs/3Dmol/2.4.2/3Dmol-min.js');\n",
        "}\n",
        "\n",
-       "var viewer_17472043464774249 = null;\n",
-       "var warn = document.getElementById(\"3dmolwarning_17472043464774249\");\n",
+       "var viewer_1747776613981611 = null;\n",
+       "var warn = document.getElementById(\"3dmolwarning_1747776613981611\");\n",
        "if(warn) {\n",
        "    warn.parentNode.removeChild(warn);\n",
        "}\n",
        "$3Dmolpromise.then(function() {\n",
-       "viewer_17472043464774249 = $3Dmol.createViewer(document.getElementById(\"3dmolviewer_17472043464774249\"),{backgroundColor:\"white\"});\n",
-       "viewer_17472043464774249.zoomTo();\n",
-       "\tviewer_17472043464774249.addModel(\"HETATM    1  C1  UNL     1      -2.945  -2.264  -0.022  1.00  0.00           C  \\nHETATM    2  C2  UNL     1      -2.075  -1.145  -0.483  1.00  0.00           C  \\nHETATM    3  O1  UNL     1      -2.368  -0.527  -1.543  1.00  0.00           O  \\nHETATM    4  O2  UNL     1      -0.889  -0.871   0.209  1.00  0.00           O  \\nHETATM    5  C3  UNL     1      -0.099   0.280   0.046  1.00  0.00           C  \\nHETATM    6  C4  UNL     1      -0.687   1.518  -0.278  1.00  0.00           C  \\nHETATM    7  C5  UNL     1       0.099   2.661  -0.426  1.00  0.00           C  \\nHETATM    8  C6  UNL     1       1.478   2.588  -0.241  1.00  0.00           C  \\nHETATM    9  C7  UNL     1       2.075   1.374   0.100  1.00  0.00           C  \\nHETATM   10  C8  UNL     1       1.301   0.208   0.254  1.00  0.00           C  \\nHETATM   11  C9  UNL     1       1.979  -1.063   0.620  1.00  0.00           C  \\nHETATM   12  O3  UNL     1       1.327  -2.135   0.744  1.00  0.00           O  \\nHETATM   13  O4  UNL     1       3.356  -1.085   0.829  1.00  0.00           O  \\nHETATM   14  H1  UNL     1      -4.010  -2.038  -0.245  1.00  0.00           H  \\nHETATM   15  H2  UNL     1      -2.831  -2.404   1.073  1.00  0.00           H  \\nHETATM   16  H3  UNL     1      -2.652  -3.199  -0.542  1.00  0.00           H  \\nHETATM   17  H4  UNL     1      -1.759   1.611  -0.389  1.00  0.00           H  \\nHETATM   18  H5  UNL     1      -0.364   3.607  -0.675  1.00  0.00           H  \\nHETATM   19  H6  UNL     1       2.085   3.477  -0.355  1.00  0.00           H  \\nHETATM   20  H7  UNL     1       3.148   1.351   0.244  1.00  0.00           H  \\nHETATM   21  H8  UNL     1       3.831  -1.944   1.078  1.00  0.00           H  \\nCONECT    1    2   14   15   16\\nCONECT    2    3    3    4\\nCONECT    4    5\\nCONECT    5    6    6   10\\nCONECT    6    7   17\\nCONECT    7    8    8   18\\nCONECT    8    9   19\\nCONECT    9   10   10   20\\nCONECT   10   11\\nCONECT   11   12   12   13\\nCONECT   13   21\\nEND\\n\",\"pdb\");\n",
-       "\tviewer_17472043464774249.setStyle({\"stick\": {}});\n",
-       "\tviewer_17472043464774249.zoomTo();\n",
-       "viewer_17472043464774249.render();\n",
+       "viewer_1747776613981611 = $3Dmol.createViewer(document.getElementById(\"3dmolviewer_1747776613981611\"),{backgroundColor:\"white\"});\n",
+       "viewer_1747776613981611.zoomTo();\n",
+       "\tviewer_1747776613981611.addModel(\"HETATM    1  C1  UNL     1      -2.960  -2.244  -0.038  1.00  0.00           C  \\nHETATM    2  C2  UNL     1      -2.082  -1.129  -0.492  1.00  0.00           C  \\nHETATM    3  O1  UNL     1      -2.368  -0.505  -1.549  1.00  0.00           O  \\nHETATM    4  O2  UNL     1      -0.895  -0.866   0.204  1.00  0.00           O  \\nHETATM    5  C3  UNL     1      -0.098   0.280   0.047  1.00  0.00           C  \\nHETATM    6  C4  UNL     1      -0.677   1.524  -0.273  1.00  0.00           C  \\nHETATM    7  C5  UNL     1       0.117   2.662  -0.414  1.00  0.00           C  \\nHETATM    8  C6  UNL     1       1.495   2.579  -0.227  1.00  0.00           C  \\nHETATM    9  C7  UNL     1       2.084   1.360   0.110  1.00  0.00           C  \\nHETATM   10  C8  UNL     1       1.302   0.198   0.258  1.00  0.00           C  \\nHETATM   11  C9  UNL     1       1.971  -1.079   0.619  1.00  0.00           C  \\nHETATM   12  O3  UNL     1       1.311  -2.146   0.738  1.00  0.00           O  \\nHETATM   13  O4  UNL     1       3.347  -1.111   0.831  1.00  0.00           O  \\nHETATM   14  H1  UNL     1      -4.022  -2.010  -0.262  1.00  0.00           H  \\nHETATM   15  H2  UNL     1      -2.849  -2.390   1.057  1.00  0.00           H  \\nHETATM   16  H3  UNL     1      -2.671  -3.179  -0.561  1.00  0.00           H  \\nHETATM   17  H4  UNL     1      -1.748   1.624  -0.386  1.00  0.00           H  \\nHETATM   18  H5  UNL     1      -0.339   3.613  -0.660  1.00  0.00           H  \\nHETATM   19  H6  UNL     1       2.109   3.465  -0.336  1.00  0.00           H  \\nHETATM   20  H7  UNL     1       3.157   1.329   0.256  1.00  0.00           H  \\nHETATM   21  H8  UNL     1       3.816  -1.974   1.077  1.00  0.00           H  \\nCONECT    1    2   14   15   16\\nCONECT    2    3    3    4\\nCONECT    4    5\\nCONECT    5    6    6   10\\nCONECT    6    7   17\\nCONECT    7    8    8   18\\nCONECT    8    9   19\\nCONECT    9   10   10   20\\nCONECT   10   11\\nCONECT   11   12   12   13\\nCONECT   13   21\\nEND\\n\",\"pdb\");\n",
+       "\tviewer_1747776613981611.setStyle({\"stick\": {}});\n",
+       "\tviewer_1747776613981611.zoomTo();\n",
+       "viewer_1747776613981611.render();\n",
        "});\n",
        "</script>"
       ]
@@ -170,10 +170,10 @@
     {
      "data": {
       "text/plain": [
-       "<py3Dmol.view at 0x2e3934510>"
+       "<py3Dmol.view at 0x16c184d40>"
       ]
      },
-     "execution_count": 13,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -184,16 +184,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 9,
    "id": "e3f26dd2-4ef5-44cd-b52c-103feb68aea8",
    "metadata": {},
    "outputs": [
     {
      "data": {
-      "application/3dmoljs_load.v0": "<div id=\"3dmolviewer_174720434115202\"  style=\"position: relative; width: 400px; height: 300px;\">\n        <p id=\"3dmolwarning_174720434115202\" style=\"background-color:#ffcccc;color:black\">3Dmol.js failed to load for some reason.  Please check your browser console for error messages.<br></p>\n        </div>\n<script>\n\nvar loadScriptAsync = function(uri){\n  return new Promise((resolve, reject) => {\n    //this is to ignore the existence of requirejs amd\n    var savedexports, savedmodule;\n    if (typeof exports !== 'undefined') savedexports = exports;\n    else exports = {}\n    if (typeof module !== 'undefined') savedmodule = module;\n    else module = {}\n\n    var tag = document.createElement('script');\n    tag.src = uri;\n    tag.async = true;\n    tag.onload = () => {\n        exports = savedexports;\n        module = savedmodule;\n        resolve();\n    };\n  var firstScriptTag = document.getElementsByTagName('script')[0];\n  firstScriptTag.parentNode.insertBefore(tag, firstScriptTag);\n});\n};\n\nif(typeof $3Dmolpromise === 'undefined') {\n$3Dmolpromise = null;\n  $3Dmolpromise = loadScriptAsync('https://cdnjs.cloudflare.com/ajax/libs/3Dmol/2.2.0/3Dmol-min.js');\n}\n\nvar viewer_174720434115202 = null;\nvar warn = document.getElementById(\"3dmolwarning_174720434115202\");\nif(warn) {\n    warn.parentNode.removeChild(warn);\n}\n$3Dmolpromise.then(function() {\nviewer_174720434115202 = $3Dmol.createViewer(document.getElementById(\"3dmolviewer_174720434115202\"),{backgroundColor:\"white\"});\nviewer_174720434115202.zoomTo();\n\tviewer_174720434115202.addModel(\"HETATM    1  C1  UNL     1      -4.710   0.483  -2.389  1.00  0.00           C  \\nHETATM    2  C2  UNL     1      -3.254   0.734  -2.191  1.00  0.00           C  \\nHETATM    3  O1  UNL     1      -2.675   1.612  -2.887  1.00  0.00           O  \\nHETATM    4  O2  UNL     1      -2.582   0.069  -1.158  1.00  0.00           O  \\nHETATM    5  C3  UNL     1      -1.192   0.054  -0.972  1.00  0.00           C  \\nHETATM    6  C4  UNL     1      -0.319   0.062  -2.076  1.00  0.00           C  \\nHETATM    7  C5  UNL     1       1.063   0.034  -1.891  1.00  0.00           C  \\nHETATM    8  C6  UNL     1       1.605  -0.028  -0.607  1.00  0.00           C  \\nHETATM    9  O3  UNL     1       3.000  -0.043  -0.469  1.00  0.00           O  \\nHETATM   10  C7  UNL     1       3.699  -0.667   0.574  1.00  0.00           C  \\nHETATM   11  O4  UNL     1       3.059  -1.628   1.363  1.00  0.00           O  \\nHETATM   12  C8  UNL     1       4.989  -0.363   0.778  1.00  0.00           C  \\nHETATM   13  C9  UNL     1       5.682   0.655  -0.083  1.00  0.00           C  \\nHETATM   14  O5  UNL     1       5.698  -0.995   1.800  1.00  0.00           O  \\nHETATM   15  C10 UNL     1       0.743  -0.034   0.502  1.00  0.00           C  \\nHETATM   16  C11 UNL     1      -0.649  -0.005   0.336  1.00  0.00           C  \\nHETATM   17  O6  UNL     1      -1.430  -0.020   1.505  1.00  0.00           O  \\nHETATM   18  C12 UNL     1      -2.853  -0.040   1.551  1.00  0.00           C  \\nHETATM   19  C13 UNL     1      -3.491   1.337   1.537  1.00  0.00           C  \\nHETATM   20  C14 UNL     1      -3.397   0.552   2.836  1.00  0.00           C  \\nHETATM   21  H1  UNL     1      -4.976   0.597  -3.461  1.00  0.00           H  \\nHETATM   22  H2  UNL     1      -4.963  -0.548  -2.064  1.00  0.00           H  \\nHETATM   23  H3  UNL     1      -5.295   1.209  -1.786  1.00  0.00           H  \\nHETATM   24  H4  UNL     1      -0.706   0.063  -3.086  1.00  0.00           H  \\nHETATM   25  H5  UNL     1       1.718   0.043  -2.754  1.00  0.00           H  \\nHETATM   26  H6  UNL     1       3.523  -2.113   2.121  1.00  0.00           H  \\nHETATM   27  H7  UNL     1       6.737   0.788   0.236  1.00  0.00           H  \\nHETATM   28  H8  UNL     1       5.675   0.321  -1.142  1.00  0.00           H  \\nHETATM   29  H9  UNL     1       5.165   1.635  -0.002  1.00  0.00           H  \\nHETATM   30  H10 UNL     1       6.673  -0.786   1.979  1.00  0.00           H  \\nHETATM   31  H11 UNL     1       1.145  -0.031   1.506  1.00  0.00           H  \\nHETATM   32  H12 UNL     1      -3.410  -0.912   1.146  1.00  0.00           H  \\nHETATM   33  H13 UNL     1      -2.773   2.181   1.454  1.00  0.00           H  \\nHETATM   34  H14 UNL     1      -4.503   1.359   1.081  1.00  0.00           H  \\nHETATM   35  H15 UNL     1      -4.364   0.118   3.171  1.00  0.00           H  \\nHETATM   36  H16 UNL     1      -2.633   0.938   3.544  1.00  0.00           H  \\nCONECT    1    2   21   22   23\\nCONECT    2    3    3    4\\nCONECT    4    5\\nCONECT    5    6    6   16\\nCONECT    6    7   24\\nCONECT    7    8    8   25\\nCONECT    8    9   15\\nCONECT    9   10\\nCONECT   10   11   12   12\\nCONECT   11   26\\nCONECT   12   13   14\\nCONECT   13   27   28   29\\nCONECT   14   30\\nCONECT   15   16   16   31\\nCONECT   16   17\\nCONECT   17   18\\nCONECT   18   19   20   32\\nCONECT   19   20   33   34\\nCONECT   20   35   36\\nEND\\n\",\"pdb\");\n\tviewer_174720434115202.setStyle({\"stick\": {}});\n\tviewer_174720434115202.zoomTo();\nviewer_174720434115202.render();\n});\n</script>",
+      "application/3dmoljs_load.v0": "<div id=\"3dmolviewer_1747776614005095\"  style=\"position: relative; width: 400px; height: 300px;\">\n        <p id=\"3dmolwarning_1747776614005095\" style=\"background-color:#ffcccc;color:black\">3Dmol.js failed to load for some reason.  Please check your browser console for error messages.<br></p>\n        </div>\n<script>\n\nvar loadScriptAsync = function(uri){\n  return new Promise((resolve, reject) => {\n    //this is to ignore the existence of requirejs amd\n    var savedexports, savedmodule;\n    if (typeof exports !== 'undefined') savedexports = exports;\n    else exports = {}\n    if (typeof module !== 'undefined') savedmodule = module;\n    else module = {}\n\n    var tag = document.createElement('script');\n    tag.src = uri;\n    tag.async = true;\n    tag.onload = () => {\n        exports = savedexports;\n        module = savedmodule;\n        resolve();\n    };\n  var firstScriptTag = document.getElementsByTagName('script')[0];\n  firstScriptTag.parentNode.insertBefore(tag, firstScriptTag);\n});\n};\n\nif(typeof $3Dmolpromise === 'undefined') {\n$3Dmolpromise = null;\n  $3Dmolpromise = loadScriptAsync('https://cdnjs.cloudflare.com/ajax/libs/3Dmol/2.4.2/3Dmol-min.js');\n}\n\nvar viewer_1747776614005095 = null;\nvar warn = document.getElementById(\"3dmolwarning_1747776614005095\");\nif(warn) {\n    warn.parentNode.removeChild(warn);\n}\n$3Dmolpromise.then(function() {\nviewer_1747776614005095 = $3Dmol.createViewer(document.getElementById(\"3dmolviewer_1747776614005095\"),{backgroundColor:\"white\"});\nviewer_1747776614005095.zoomTo();\n\tviewer_1747776614005095.addModel(\"HETATM    1  C1  UNL     1      -4.717   0.510  -2.372  1.00  0.00           C  \\nHETATM    2  C2  UNL     1      -3.261   0.760  -2.175  1.00  0.00           C  \\nHETATM    3  O1  UNL     1      -2.685   1.648  -2.859  1.00  0.00           O  \\nHETATM    4  O2  UNL     1      -2.584   0.082  -1.153  1.00  0.00           O  \\nHETATM    5  C3  UNL     1      -1.194   0.066  -0.970  1.00  0.00           C  \\nHETATM    6  C4  UNL     1      -0.325   0.091  -2.077  1.00  0.00           C  \\nHETATM    7  C5  UNL     1       1.058   0.063  -1.896  1.00  0.00           C  \\nHETATM    8  C6  UNL     1       1.603  -0.017  -0.614  1.00  0.00           C  \\nHETATM    9  O3  UNL     1       2.999  -0.032  -0.480  1.00  0.00           O  \\nHETATM   10  C7  UNL     1       3.701  -0.669   0.552  1.00  0.00           C  \\nHETATM   11  O4  UNL     1       3.065  -1.642   1.329  1.00  0.00           O  \\nHETATM   12  C8  UNL     1       4.992  -0.366   0.757  1.00  0.00           C  \\nHETATM   13  C9  UNL     1       5.681   0.665  -0.092  1.00  0.00           C  \\nHETATM   14  O5  UNL     1       5.704  -1.011   1.768  1.00  0.00           O  \\nHETATM   15  C10 UNL     1       0.744  -0.039   0.497  1.00  0.00           C  \\nHETATM   16  C11 UNL     1      -0.647  -0.011   0.335  1.00  0.00           C  \\nHETATM   17  O6  UNL     1      -1.425  -0.044   1.506  1.00  0.00           O  \\nHETATM   18  C12 UNL     1      -2.848  -0.066   1.555  1.00  0.00           C  \\nHETATM   19  C13 UNL     1      -3.488   1.310   1.563  1.00  0.00           C  \\nHETATM   20  C14 UNL     1      -3.391   0.506   2.850  1.00  0.00           C  \\nHETATM   21  H1  UNL     1      -4.986   0.638  -3.442  1.00  0.00           H  \\nHETATM   22  H2  UNL     1      -4.967  -0.526  -2.061  1.00  0.00           H  \\nHETATM   23  H3  UNL     1      -5.301   1.225  -1.757  1.00  0.00           H  \\nHETATM   24  H4  UNL     1      -0.714   0.105  -3.086  1.00  0.00           H  \\nHETATM   25  H5  UNL     1       1.711   0.084  -2.760  1.00  0.00           H  \\nHETATM   26  H6  UNL     1       3.532  -2.137   2.080  1.00  0.00           H  \\nHETATM   27  H7  UNL     1       6.737   0.795   0.227  1.00  0.00           H  \\nHETATM   28  H8  UNL     1       5.672   0.346  -1.155  1.00  0.00           H  \\nHETATM   29  H9  UNL     1       5.163   1.642   0.004  1.00  0.00           H  \\nHETATM   30  H10 UNL     1       6.680  -0.804   1.947  1.00  0.00           H  \\nHETATM   31  H11 UNL     1       1.150  -0.050   1.500  1.00  0.00           H  \\nHETATM   32  H12 UNL     1      -3.405  -0.933   1.139  1.00  0.00           H  \\nHETATM   33  H13 UNL     1      -2.773   2.156   1.490  1.00  0.00           H  \\nHETATM   34  H14 UNL     1      -4.502   1.336   1.110  1.00  0.00           H  \\nHETATM   35  H15 UNL     1      -4.355   0.066   3.181  1.00  0.00           H  \\nHETATM   36  H16 UNL     1      -2.625   0.884   3.562  1.00  0.00           H  \\nCONECT    1    2   21   22   23\\nCONECT    2    3    3    4\\nCONECT    4    5\\nCONECT    5    6    6   16\\nCONECT    6    7   24\\nCONECT    7    8    8   25\\nCONECT    8    9   15\\nCONECT    9   10\\nCONECT   10   11   12   12\\nCONECT   11   26\\nCONECT   12   13   14\\nCONECT   13   27   28   29\\nCONECT   14   30\\nCONECT   15   16   16   31\\nCONECT   16   17\\nCONECT   17   18\\nCONECT   18   19   20   32\\nCONECT   19   20   33   34\\nCONECT   20   35   36\\nEND\\n\",\"pdb\");\n\tviewer_1747776614005095.setStyle({\"stick\": {}});\n\tviewer_1747776614005095.zoomTo();\nviewer_1747776614005095.render();\n});\n</script>",
       "text/html": [
-       "<div id=\"3dmolviewer_174720434115202\"  style=\"position: relative; width: 400px; height: 300px;\">\n",
-       "        <p id=\"3dmolwarning_174720434115202\" style=\"background-color:#ffcccc;color:black\">3Dmol.js failed to load for some reason.  Please check your browser console for error messages.<br></p>\n",
+       "<div id=\"3dmolviewer_1747776614005095\"  style=\"position: relative; width: 400px; height: 300px;\">\n",
+       "        <p id=\"3dmolwarning_1747776614005095\" style=\"background-color:#ffcccc;color:black\">3Dmol.js failed to load for some reason.  Please check your browser console for error messages.<br></p>\n",
        "        </div>\n",
        "<script>\n",
        "\n",
@@ -221,21 +221,21 @@
        "\n",
        "if(typeof $3Dmolpromise === 'undefined') {\n",
        "$3Dmolpromise = null;\n",
-       "  $3Dmolpromise = loadScriptAsync('https://cdnjs.cloudflare.com/ajax/libs/3Dmol/2.2.0/3Dmol-min.js');\n",
+       "  $3Dmolpromise = loadScriptAsync('https://cdnjs.cloudflare.com/ajax/libs/3Dmol/2.4.2/3Dmol-min.js');\n",
        "}\n",
        "\n",
-       "var viewer_174720434115202 = null;\n",
-       "var warn = document.getElementById(\"3dmolwarning_174720434115202\");\n",
+       "var viewer_1747776614005095 = null;\n",
+       "var warn = document.getElementById(\"3dmolwarning_1747776614005095\");\n",
        "if(warn) {\n",
        "    warn.parentNode.removeChild(warn);\n",
        "}\n",
        "$3Dmolpromise.then(function() {\n",
-       "viewer_174720434115202 = $3Dmol.createViewer(document.getElementById(\"3dmolviewer_174720434115202\"),{backgroundColor:\"white\"});\n",
-       "viewer_174720434115202.zoomTo();\n",
-       "\tviewer_174720434115202.addModel(\"HETATM    1  C1  UNL     1      -4.710   0.483  -2.389  1.00  0.00           C  \\nHETATM    2  C2  UNL     1      -3.254   0.734  -2.191  1.00  0.00           C  \\nHETATM    3  O1  UNL     1      -2.675   1.612  -2.887  1.00  0.00           O  \\nHETATM    4  O2  UNL     1      -2.582   0.069  -1.158  1.00  0.00           O  \\nHETATM    5  C3  UNL     1      -1.192   0.054  -0.972  1.00  0.00           C  \\nHETATM    6  C4  UNL     1      -0.319   0.062  -2.076  1.00  0.00           C  \\nHETATM    7  C5  UNL     1       1.063   0.034  -1.891  1.00  0.00           C  \\nHETATM    8  C6  UNL     1       1.605  -0.028  -0.607  1.00  0.00           C  \\nHETATM    9  O3  UNL     1       3.000  -0.043  -0.469  1.00  0.00           O  \\nHETATM   10  C7  UNL     1       3.699  -0.667   0.574  1.00  0.00           C  \\nHETATM   11  O4  UNL     1       3.059  -1.628   1.363  1.00  0.00           O  \\nHETATM   12  C8  UNL     1       4.989  -0.363   0.778  1.00  0.00           C  \\nHETATM   13  C9  UNL     1       5.682   0.655  -0.083  1.00  0.00           C  \\nHETATM   14  O5  UNL     1       5.698  -0.995   1.800  1.00  0.00           O  \\nHETATM   15  C10 UNL     1       0.743  -0.034   0.502  1.00  0.00           C  \\nHETATM   16  C11 UNL     1      -0.649  -0.005   0.336  1.00  0.00           C  \\nHETATM   17  O6  UNL     1      -1.430  -0.020   1.505  1.00  0.00           O  \\nHETATM   18  C12 UNL     1      -2.853  -0.040   1.551  1.00  0.00           C  \\nHETATM   19  C13 UNL     1      -3.491   1.337   1.537  1.00  0.00           C  \\nHETATM   20  C14 UNL     1      -3.397   0.552   2.836  1.00  0.00           C  \\nHETATM   21  H1  UNL     1      -4.976   0.597  -3.461  1.00  0.00           H  \\nHETATM   22  H2  UNL     1      -4.963  -0.548  -2.064  1.00  0.00           H  \\nHETATM   23  H3  UNL     1      -5.295   1.209  -1.786  1.00  0.00           H  \\nHETATM   24  H4  UNL     1      -0.706   0.063  -3.086  1.00  0.00           H  \\nHETATM   25  H5  UNL     1       1.718   0.043  -2.754  1.00  0.00           H  \\nHETATM   26  H6  UNL     1       3.523  -2.113   2.121  1.00  0.00           H  \\nHETATM   27  H7  UNL     1       6.737   0.788   0.236  1.00  0.00           H  \\nHETATM   28  H8  UNL     1       5.675   0.321  -1.142  1.00  0.00           H  \\nHETATM   29  H9  UNL     1       5.165   1.635  -0.002  1.00  0.00           H  \\nHETATM   30  H10 UNL     1       6.673  -0.786   1.979  1.00  0.00           H  \\nHETATM   31  H11 UNL     1       1.145  -0.031   1.506  1.00  0.00           H  \\nHETATM   32  H12 UNL     1      -3.410  -0.912   1.146  1.00  0.00           H  \\nHETATM   33  H13 UNL     1      -2.773   2.181   1.454  1.00  0.00           H  \\nHETATM   34  H14 UNL     1      -4.503   1.359   1.081  1.00  0.00           H  \\nHETATM   35  H15 UNL     1      -4.364   0.118   3.171  1.00  0.00           H  \\nHETATM   36  H16 UNL     1      -2.633   0.938   3.544  1.00  0.00           H  \\nCONECT    1    2   21   22   23\\nCONECT    2    3    3    4\\nCONECT    4    5\\nCONECT    5    6    6   16\\nCONECT    6    7   24\\nCONECT    7    8    8   25\\nCONECT    8    9   15\\nCONECT    9   10\\nCONECT   10   11   12   12\\nCONECT   11   26\\nCONECT   12   13   14\\nCONECT   13   27   28   29\\nCONECT   14   30\\nCONECT   15   16   16   31\\nCONECT   16   17\\nCONECT   17   18\\nCONECT   18   19   20   32\\nCONECT   19   20   33   34\\nCONECT   20   35   36\\nEND\\n\",\"pdb\");\n",
-       "\tviewer_174720434115202.setStyle({\"stick\": {}});\n",
-       "\tviewer_174720434115202.zoomTo();\n",
-       "viewer_174720434115202.render();\n",
+       "viewer_1747776614005095 = $3Dmol.createViewer(document.getElementById(\"3dmolviewer_1747776614005095\"),{backgroundColor:\"white\"});\n",
+       "viewer_1747776614005095.zoomTo();\n",
+       "\tviewer_1747776614005095.addModel(\"HETATM    1  C1  UNL     1      -4.717   0.510  -2.372  1.00  0.00           C  \\nHETATM    2  C2  UNL     1      -3.261   0.760  -2.175  1.00  0.00           C  \\nHETATM    3  O1  UNL     1      -2.685   1.648  -2.859  1.00  0.00           O  \\nHETATM    4  O2  UNL     1      -2.584   0.082  -1.153  1.00  0.00           O  \\nHETATM    5  C3  UNL     1      -1.194   0.066  -0.970  1.00  0.00           C  \\nHETATM    6  C4  UNL     1      -0.325   0.091  -2.077  1.00  0.00           C  \\nHETATM    7  C5  UNL     1       1.058   0.063  -1.896  1.00  0.00           C  \\nHETATM    8  C6  UNL     1       1.603  -0.017  -0.614  1.00  0.00           C  \\nHETATM    9  O3  UNL     1       2.999  -0.032  -0.480  1.00  0.00           O  \\nHETATM   10  C7  UNL     1       3.701  -0.669   0.552  1.00  0.00           C  \\nHETATM   11  O4  UNL     1       3.065  -1.642   1.329  1.00  0.00           O  \\nHETATM   12  C8  UNL     1       4.992  -0.366   0.757  1.00  0.00           C  \\nHETATM   13  C9  UNL     1       5.681   0.665  -0.092  1.00  0.00           C  \\nHETATM   14  O5  UNL     1       5.704  -1.011   1.768  1.00  0.00           O  \\nHETATM   15  C10 UNL     1       0.744  -0.039   0.497  1.00  0.00           C  \\nHETATM   16  C11 UNL     1      -0.647  -0.011   0.335  1.00  0.00           C  \\nHETATM   17  O6  UNL     1      -1.425  -0.044   1.506  1.00  0.00           O  \\nHETATM   18  C12 UNL     1      -2.848  -0.066   1.555  1.00  0.00           C  \\nHETATM   19  C13 UNL     1      -3.488   1.310   1.563  1.00  0.00           C  \\nHETATM   20  C14 UNL     1      -3.391   0.506   2.850  1.00  0.00           C  \\nHETATM   21  H1  UNL     1      -4.986   0.638  -3.442  1.00  0.00           H  \\nHETATM   22  H2  UNL     1      -4.967  -0.526  -2.061  1.00  0.00           H  \\nHETATM   23  H3  UNL     1      -5.301   1.225  -1.757  1.00  0.00           H  \\nHETATM   24  H4  UNL     1      -0.714   0.105  -3.086  1.00  0.00           H  \\nHETATM   25  H5  UNL     1       1.711   0.084  -2.760  1.00  0.00           H  \\nHETATM   26  H6  UNL     1       3.532  -2.137   2.080  1.00  0.00           H  \\nHETATM   27  H7  UNL     1       6.737   0.795   0.227  1.00  0.00           H  \\nHETATM   28  H8  UNL     1       5.672   0.346  -1.155  1.00  0.00           H  \\nHETATM   29  H9  UNL     1       5.163   1.642   0.004  1.00  0.00           H  \\nHETATM   30  H10 UNL     1       6.680  -0.804   1.947  1.00  0.00           H  \\nHETATM   31  H11 UNL     1       1.150  -0.050   1.500  1.00  0.00           H  \\nHETATM   32  H12 UNL     1      -3.405  -0.933   1.139  1.00  0.00           H  \\nHETATM   33  H13 UNL     1      -2.773   2.156   1.490  1.00  0.00           H  \\nHETATM   34  H14 UNL     1      -4.502   1.336   1.110  1.00  0.00           H  \\nHETATM   35  H15 UNL     1      -4.355   0.066   3.181  1.00  0.00           H  \\nHETATM   36  H16 UNL     1      -2.625   0.884   3.562  1.00  0.00           H  \\nCONECT    1    2   21   22   23\\nCONECT    2    3    3    4\\nCONECT    4    5\\nCONECT    5    6    6   16\\nCONECT    6    7   24\\nCONECT    7    8    8   25\\nCONECT    8    9   15\\nCONECT    9   10\\nCONECT   10   11   12   12\\nCONECT   11   26\\nCONECT   12   13   14\\nCONECT   13   27   28   29\\nCONECT   14   30\\nCONECT   15   16   16   31\\nCONECT   16   17\\nCONECT   17   18\\nCONECT   18   19   20   32\\nCONECT   19   20   33   34\\nCONECT   20   35   36\\nEND\\n\",\"pdb\");\n",
+       "\tviewer_1747776614005095.setStyle({\"stick\": {}});\n",
+       "\tviewer_1747776614005095.zoomTo();\n",
+       "viewer_1747776614005095.render();\n",
        "});\n",
        "</script>"
       ]
@@ -246,10 +246,10 @@
     {
      "data": {
       "text/plain": [
-       "<py3Dmol.view at 0x2e38fc790>"
+       "<py3Dmol.view at 0x17615aed0>"
       ]
      },
-     "execution_count": 12,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }

README.md

@@ -15,7 +15,7 @@ from model.utils import MorganFingerprint, morgan_fingerprint_to_text, clean_out
 from model.tokenizer import SmilesTokenizer
 
 # Load the checkpoint and the tokenizer
-checkpoint_path="checkpoint-4120000"
+checkpoint_path="lamthuy/MorganGen"
 model = AutoModelForSeq2SeqLM.from_pretrained(checkpoint_path)
 tokenizer = SmilesTokenizer(vocab_file="data/vocab_morgan.txt")
 

checkpoint-4120000/config.json

@@ -1,75 +0,0 @@
-{
-  "_name_or_path": "facebook/bart-base",
-  "activation_dropout": 0.1,
-  "activation_function": "gelu",
-  "add_bias_logits": false,
-  "add_final_layer_norm": false,
-  "architectures": [
-    "BartForConditionalGeneration"
-  ],
-  "attention_dropout": 0.1,
-  "bos_token_id": 0,
-  "classif_dropout": 0.1,
-  "classifier_dropout": 0.0,
-  "d_model": 768,
-  "decoder_attention_heads": 12,
-  "decoder_ffn_dim": 3072,
-  "decoder_layerdrop": 0.0,
-  "decoder_layers": 6,
-  "decoder_start_token_id": 2,
-  "dropout": 0.1,
-  "early_stopping": true,
-  "encoder_attention_heads": 12,
-  "encoder_ffn_dim": 3072,
-  "encoder_layerdrop": 0.0,
-  "encoder_layers": 6,
-  "eos_token_id": 2,
-  "forced_bos_token_id": 0,
-  "forced_eos_token_id": 2,
-  "gradient_checkpointing": false,
-  "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1",
-    "2": "LABEL_2"
-  },
-  "init_std": 0.02,
-  "is_encoder_decoder": true,
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2
-  },
-  "max_position_embeddings": 1024,
-  "model_type": "bart",
-  "no_repeat_ngram_size": 3,
-  "normalize_before": false,
-  "normalize_embedding": true,
-  "num_beams": 4,
-  "num_hidden_layers": 6,
-  "pad_token_id": 1,
-  "scale_embedding": false,
-  "task_specific_params": {
-    "summarization": {
-      "length_penalty": 1.0,
-      "max_length": 128,
-      "min_length": 12,
-      "num_beams": 4
-    },
-    "summarization_cnn": {
-      "length_penalty": 2.0,
-      "max_length": 142,
-      "min_length": 56,
-      "num_beams": 4
-    },
-    "summarization_xsum": {
-      "length_penalty": 1.0,
-      "max_length": 62,
-      "min_length": 11,
-      "num_beams": 6
-    }
-  },
-  "torch_dtype": "float16",
-  "transformers_version": "4.37.0",
-  "use_cache": true,
-  "vocab_size": 50265
-}

checkpoint-4120000/generation_config.json

@@ -1,13 +0,0 @@
-{
-  "_from_model_config": true,
-  "bos_token_id": 0,
-  "decoder_start_token_id": 2,
-  "early_stopping": true,
-  "eos_token_id": 2,
-  "forced_bos_token_id": 0,
-  "forced_eos_token_id": 2,
-  "no_repeat_ngram_size": 3,
-  "num_beams": 4,
-  "pad_token_id": 1,
-  "transformers_version": "4.37.0"
-}

checkpoint-4120000/global_step4120000/mp_rank_00_model_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:21d1573828b5ea09d93b840a2d0fddc4ff050baed01d8e418d5a108a4ca2abb5
-size 279011960

checkpoint-4120000/global_step4120000/zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4124c72760850e3dfe47ef6271cf52c342902ddf4895ab2af48c1cc85df94b7b
-size 836532205

checkpoint-4120000/global_step4120000/zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b99a8df8657f8304bd84ea3872b48ab441afd17d7dc7a6beb9462944a1769b15
-size 836542061

checkpoint-4120000/latest

@@ -1 +0,0 @@
-global_step4120000

checkpoint-4120000/model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2add04b3d765e6b586d45a138bbdf5938a91d4668e23469c5fc977ec57685eb8
-size 510592834

checkpoint-4120000/rng_state_0.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6cd095dfb9a400482d1cbe7aeb660e1635d4c46839d11b4c9fd38b3d26db3672
-size 14512

checkpoint-4120000/rng_state_1.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:92852906cdd6fb428f8147e3fdaadeb026c6cce1f3a0bf56c0c7593ab725edb5
-size 14512

checkpoint-4120000/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5b2db6ec78a7157dbeee04114a5472abebf66b70394acaffb21a3238de5d390e
-size 6200

checkpoint-4120000/zero_to_fp32.py

@@ -1,587 +0,0 @@
-#!/usr/bin/env python
-
-# Copyright (c) Microsoft Corporation.
-# SPDX-License-Identifier: Apache-2.0
-
-# DeepSpeed Team
-
-# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
-# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
-# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
-# application.
-#
-# example: python zero_to_fp32.py . pytorch_model.bin
-
-import argparse
-import torch
-import glob
-import math
-import os
-import re
-from collections import OrderedDict
-from dataclasses import dataclass
-
-# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
-# DeepSpeed data structures it has to be available in the current python environment.
-from deepspeed.utils import logger
-from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
-                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
-                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
-
-
-@dataclass
-class zero_model_state:
-    buffers: dict()
-    param_shapes: dict()
-    shared_params: list
-    ds_version: int
-    frozen_param_shapes: dict()
-    frozen_param_fragments: dict()
-
-
-debug = 0
-
-# load to cpu
-device = torch.device('cpu')
-
-
-def atoi(text):
-    return int(text) if text.isdigit() else text
-
-
-def natural_keys(text):
-    '''
-    alist.sort(key=natural_keys) sorts in human order
-    http://nedbatchelder.com/blog/200712/human_sorting.html
-    (See Toothy's implementation in the comments)
-    '''
-    return [atoi(c) for c in re.split(r'(\d+)', text)]
-
-
-def get_model_state_file(checkpoint_dir, zero_stage):
-    if not os.path.isdir(checkpoint_dir):
-        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
-
-    # there should be only one file
-    if zero_stage <= 2:
-        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
-    elif zero_stage == 3:
-        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
-
-    if not os.path.exists(file):
-        raise FileNotFoundError(f"can't find model states file at '{file}'")
-
-    return file
-
-
-def get_checkpoint_files(checkpoint_dir, glob_pattern):
-    # XXX: need to test that this simple glob rule works for multi-node setup too
-    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
-
-    if len(ckpt_files) == 0:
-        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
-
-    return ckpt_files
-
-
-def get_optim_files(checkpoint_dir):
-    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
-
-
-def get_model_state_files(checkpoint_dir):
-    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
-
-
-def parse_model_states(files):
-    zero_model_states = []
-    for file in files:
-        state_dict = torch.load(file, map_location=device)
-
-        if BUFFER_NAMES not in state_dict:
-            raise ValueError(f"{file} is not a model state checkpoint")
-        buffer_names = state_dict[BUFFER_NAMES]
-        if debug:
-            print("Found buffers:", buffer_names)
-
-        # recover just the buffers while restoring them to fp32 if they were saved in fp16
-        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
-        param_shapes = state_dict[PARAM_SHAPES]
-
-        # collect parameters that are included in param_shapes
-        param_names = []
-        for s in param_shapes:
-            for name in s.keys():
-                param_names.append(name)
-
-        # update with frozen parameters
-        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
-        if frozen_param_shapes is not None:
-            if debug:
-                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
-            param_names += list(frozen_param_shapes.keys())
-
-        # handle shared params
-        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
-
-        ds_version = state_dict.get(DS_VERSION, None)
-
-        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
-
-        z_model_state = zero_model_state(buffers=buffers,
-                                         param_shapes=param_shapes,
-                                         shared_params=shared_params,
-                                         ds_version=ds_version,
-                                         frozen_param_shapes=frozen_param_shapes,
-                                         frozen_param_fragments=frozen_param_fragments)
-        zero_model_states.append(z_model_state)
-
-    return zero_model_states
-
-
-def parse_optim_states(files, ds_checkpoint_dir):
-
-    total_files = len(files)
-    state_dicts = []
-    for f in files:
-        state_dict = torch.load(f, map_location=device)
-        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
-        # and also handle the case where it was already removed by another helper script
-        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
-        state_dicts.append(state_dict)
-
-    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
-        raise ValueError(f"{files[0]} is not a zero checkpoint")
-    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
-    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
-
-    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
-    # parameters can be different from data parallelism for non-expert parameters. So we can just
-    # use the max of the partition_count to get the dp world_size.
-
-    if type(world_size) is list:
-        world_size = max(world_size)
-
-    if world_size != total_files:
-        raise ValueError(
-            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
-            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
-        )
-
-    # the groups are named differently in each stage
-    if zero_stage <= 2:
-        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
-    elif zero_stage == 3:
-        fp32_groups_key = FP32_FLAT_GROUPS
-    else:
-        raise ValueError(f"unknown zero stage {zero_stage}")
-
-    if zero_stage <= 2:
-        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
-    elif zero_stage == 3:
-        # if there is more than one param group, there will be multiple flattened tensors - one
-        # flattened tensor per group - for simplicity merge them into a single tensor
-        #
-        # XXX: could make the script more memory efficient for when there are multiple groups - it
-        # will require matching the sub-lists of param_shapes for each param group flattened tensor
-
-        fp32_flat_groups = [
-            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
-        ]
-
-    return zero_stage, world_size, fp32_flat_groups
-
-
-def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir):
-    """
-    Returns fp32 state_dict reconstructed from ds checkpoint
-
-    Args:
-        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
-
-    """
-    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
-
-    optim_files = get_optim_files(ds_checkpoint_dir)
-    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
-    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
-
-    model_files = get_model_state_files(ds_checkpoint_dir)
-
-    zero_model_states = parse_model_states(model_files)
-    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
-
-    if zero_stage <= 2:
-        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states)
-    elif zero_stage == 3:
-        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states)
-
-
-def _zero2_merge_frozen_params(state_dict, zero_model_states):
-    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
-        return
-
-    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
-    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
-
-    if debug:
-        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
-        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
-
-        wanted_params = len(frozen_param_shapes)
-        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
-        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
-        print(f'Frozen params: Have {avail_numel} numels to process.')
-        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
-
-    total_params = 0
-    total_numel = 0
-    for name, shape in frozen_param_shapes.items():
-        total_params += 1
-        unpartitioned_numel = shape.numel()
-        total_numel += unpartitioned_numel
-
-        state_dict[name] = frozen_param_fragments[name]
-
-        if debug:
-            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
-
-    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
-
-
-def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
-    param_shapes = zero_model_states[0].param_shapes
-
-    # Reconstruction protocol:
-    #
-    # XXX: document this
-
-    if debug:
-        for i in range(world_size):
-            for j in range(len(fp32_flat_groups[0])):
-                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
-
-    # XXX: memory usage doubles here (zero2)
-    num_param_groups = len(fp32_flat_groups[0])
-    merged_single_partition_of_fp32_groups = []
-    for i in range(num_param_groups):
-        merged_partitions = [sd[i] for sd in fp32_flat_groups]
-        full_single_fp32_vector = torch.cat(merged_partitions, 0)
-        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
-    avail_numel = sum(
-        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
-
-    if debug:
-        wanted_params = sum([len(shapes) for shapes in param_shapes])
-        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
-        # not asserting if there is a mismatch due to possible padding
-        print(f"Have {avail_numel} numels to process.")
-        print(f"Need {wanted_numel} numels in {wanted_params} params.")
-
-    # params
-    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
-    # out-of-core computing solution
-    total_numel = 0
-    total_params = 0
-    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
-        offset = 0
-        avail_numel = full_single_fp32_vector.numel()
-        for name, shape in shapes.items():
-
-            unpartitioned_numel = shape.numel()
-            total_numel += unpartitioned_numel
-            total_params += 1
-
-            if debug:
-                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
-            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
-            offset += unpartitioned_numel
-
-        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
-        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
-        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
-        # live optimizer object, so we are checking that the numbers are within the right range
-        align_to = 2 * world_size
-
-        def zero2_align(x):
-            return align_to * math.ceil(x / align_to)
-
-        if debug:
-            print(f"original offset={offset}, avail_numel={avail_numel}")
-
-        offset = zero2_align(offset)
-        avail_numel = zero2_align(avail_numel)
-
-        if debug:
-            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
-
-        # Sanity check
-        if offset != avail_numel:
-            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
-
-    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
-
-
-def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states):
-    state_dict = OrderedDict()
-
-    # buffers
-    buffers = zero_model_states[0].buffers
-    state_dict.update(buffers)
-    if debug:
-        print(f"added {len(buffers)} buffers")
-
-    _zero2_merge_frozen_params(state_dict, zero_model_states)
-
-    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
-
-    # recover shared parameters
-    for pair in zero_model_states[0].shared_params:
-        if pair[1] in state_dict:
-            state_dict[pair[0]] = state_dict[pair[1]]
-
-    return state_dict
-
-
-def zero3_partitioned_param_info(unpartitioned_numel, world_size):
-    remainder = unpartitioned_numel % world_size
-    padding_numel = (world_size - remainder) if remainder else 0
-    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
-    return partitioned_numel, padding_numel
-
-
-def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
-    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
-        return
-
-    if debug:
-        for i in range(world_size):
-            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
-            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
-
-        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
-        wanted_params = len(frozen_param_shapes)
-        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
-        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
-        print(f'Frozen params: Have {avail_numel} numels to process.')
-        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
-
-    total_params = 0
-    total_numel = 0
-    for name, shape in zero_model_states[0].frozen_param_shapes.items():
-        total_params += 1
-        unpartitioned_numel = shape.numel()
-        total_numel += unpartitioned_numel
-
-        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
-        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
-
-        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
-
-        if debug:
-            print(
-                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
-            )
-
-    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
-
-
-def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
-    param_shapes = zero_model_states[0].param_shapes
-    avail_numel = fp32_flat_groups[0].numel() * world_size
-    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
-    # param, re-consolidating each param, while dealing with padding if any
-
-    # merge list of dicts, preserving order
-    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
-
-    if debug:
-        for i in range(world_size):
-            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
-
-        wanted_params = len(param_shapes)
-        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
-        # not asserting if there is a mismatch due to possible padding
-        avail_numel = fp32_flat_groups[0].numel() * world_size
-        print(f"Trainable params: Have {avail_numel} numels to process.")
-        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
-
-    # params
-    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
-    # out-of-core computing solution
-    offset = 0
-    total_numel = 0
-    total_params = 0
-    for name, shape in param_shapes.items():
-
-        unpartitioned_numel = shape.numel()
-        total_numel += unpartitioned_numel
-        total_params += 1
-
-        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
-
-        if debug:
-            print(
-                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
-            )
-
-        # XXX: memory usage doubles here
-        state_dict[name] = torch.cat(
-            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
-            0).narrow(0, 0, unpartitioned_numel).view(shape)
-        offset += partitioned_numel
-
-    offset *= world_size
-
-    # Sanity check
-    if offset != avail_numel:
-        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
-
-    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
-
-
-def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states):
-    state_dict = OrderedDict()
-
-    # buffers
-    buffers = zero_model_states[0].buffers
-    state_dict.update(buffers)
-    if debug:
-        print(f"added {len(buffers)} buffers")
-
-    _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
-
-    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
-
-    # recover shared parameters
-    for pair in zero_model_states[0].shared_params:
-        if pair[1] in state_dict:
-            state_dict[pair[0]] = state_dict[pair[1]]
-
-    return state_dict
-
-
-def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None):
-    """
-    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
-    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
-    via a model hub.
-
-    Args:
-        - ``checkpoint_dir``: path to the desired checkpoint folder
-        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
-
-    Returns:
-        - pytorch ``state_dict``
-
-    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
-    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
-    the checkpoint.
-
-    A typical usage might be ::
-
-        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
-        # do the training and checkpoint saving
-        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
-        model = model.cpu() # move to cpu
-        model.load_state_dict(state_dict)
-        # submit to model hub or save the model to share with others
-
-    In this example the ``model`` will no longer be usable in the deepspeed context of the same
-    application. i.e. you will need to re-initialize the deepspeed engine, since
-    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
-
-    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
-
-    """
-    if tag is None:
-        latest_path = os.path.join(checkpoint_dir, 'latest')
-        if os.path.isfile(latest_path):
-            with open(latest_path, 'r') as fd:
-                tag = fd.read().strip()
-        else:
-            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
-
-    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
-
-    if not os.path.isdir(ds_checkpoint_dir):
-        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
-
-    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir)
-
-
-def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None):
-    """
-    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
-    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
-
-    Args:
-        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
-        - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
-        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
-    """
-
-    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
-    print(f"Saving fp32 state dict to {output_file}")
-    torch.save(state_dict, output_file)
-
-
-def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
-    """
-    1. Put the provided model to cpu
-    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
-    3. Load it into the provided model
-
-    Args:
-        - ``model``: the model object to update
-        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
-        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
-
-    Returns:
-        - ``model`: modified model
-
-    Make sure you have plenty of CPU memory available before you call this function. If you don't
-    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
-    conveniently placed for you in the checkpoint folder.
-
-    A typical usage might be ::
-
-        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
-        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
-        # submit to model hub or save the model to share with others
-
-    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
-    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
-    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
-
-    """
-    logger.info(f"Extracting fp32 weights")
-    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
-
-    logger.info(f"Overwriting model with fp32 weights")
-    model = model.cpu()
-    model.load_state_dict(state_dict, strict=False)
-
-    return model
-
-
-if __name__ == "__main__":
-
-    parser = argparse.ArgumentParser()
-    parser.add_argument("checkpoint_dir",
-                        type=str,
-                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
-    parser.add_argument(
-        "output_file",
-        type=str,
-        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
-    parser.add_argument("-t",
-                        "--tag",
-                        type=str,
-                        default=None,
-                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
-    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
-    args = parser.parse_args()
-
-    debug = args.debug
-
-    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir, args.output_file, tag=args.tag)