CodeSearch-ModernBERT-Finch-Pre / README.md

Shuu12121

Upload ModernBERT model

0b648ba verified 6 months ago

preview code

raw

history blame contribute delete

40.4 kB

metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - dense
  - generated_from_trainer
  - dataset_size:58800
  - loss:MultipleNegativesRankingLoss
base_model: Shuu12121/CodeModernBERT-Finch-Pre
widget:
  - source_sentence: >-
      Returns boolean indicating whether the requestUrl matches against the
      paths configured.


      @param requestedUrl - url requested by user

      @param opts - unless configuration

      @returns {boolean}
    sentences:
      - |-
        def xmoe2_v1_l4k_global_only():
          """"""
          hparams = xmoe2_v1_l4k()
          hparams.decoder_layers = [
              "att" if l == "local_att" else l for l in hparams.decoder_layers]
          return hparams
      - |-
        function matchesPath(requestedUrl, opts) {
          var paths = !opts.path || Array.isArray(opts.path) ?
            opts.path : [opts.path];

          if (paths) {
            return paths.some(function(p) {
              return (typeof p === 'string' && p === requestedUrl.pathname) ||
                (p instanceof RegExp && !! p.exec(requestedUrl.pathname));
            });
          }

          return false;
        }
      - |-
        public static function factory($accessToken, $currentTeam)
            {
                $client = Client::factory($accessToken);

                return new self($client, $currentTeam);
            }
  - source_sentence: >-
      // New creates a new ImageGraphics including an image.RGBA of dimension w
      x h

      // with background bgcol. If font is nil it will use a builtin font.

      // If fontsize is empty useful default are used.
    sentences:
      - "func New(width, height int, bgcol color.RGBA, font *truetype.Font, fontsize map[chart.FontSize]float64) *ImageGraphics {\n\timg := image.NewRGBA(image.Rect(0, 0, width, height))\n\tgc := draw2dimg.NewGraphicContext(img)\n\tgc.SetLineJoin(draw2d.BevelJoin)\n\tgc.SetLineCap(draw2d.SquareCap)\n\tgc.SetStrokeColor(image.Black)\n\tgc.SetFillColor(bgcol)\n\tgc.Translate(0.5, 0.5)\n\tgc.Clear()\n\tif font == nil {\n\t\tfont = defaultFont\n\t}\n\tif len(fontsize) == 0 {\n\t\tfontsize = ConstructFontSizes(13)\n\t}\n\treturn &ImageGraphics{Image: img, x0: 0, y0: 0, w: width, h: height,\n\t\tbg: bgcol, gc: gc, font: font, fs: fontsize}\n}"
      - >-
        public static void requestDataLogsForApp(final Context context, final
        UUID appUuid) {
                final Intent requestIntent = new Intent(INTENT_DL_REQUEST_DATA);
                requestIntent.putExtra(APP_UUID, appUuid);
                context.sendBroadcast(requestIntent);
            }
      - |-
        final protected function setWriteMode($mode)
            {
                if (!in_array($mode, [static::WRITE_MODE_INSERT, static::WRITE_MODE_UPSERT, static::WRITE_MODE_UPDATE])) {
                    throw new \InvalidArgumentException(sprintf('Passed write mode "%s" is invalid!', $mode));
                }
                $this->writeMode = $mode;
            }
  - source_sentence: |-
      Builds the path for a closed arc, returning a PolygonOptions that can be
      further customised before use.

      @param center
      @param start
      @param end
      @param arcType Pass in either ArcType.CHORD or ArcType.ROUND
      @return PolygonOptions with the paths element populated.
    sentences:
      - |-
        function getJavaScriptCallbackParameterListSimple(parameters) {
            var result = []

            parameters.forEach(function(parameter){
                if (!parameter.out) return
                result.push("/*" + getIdlType(parameter.type) + "*/ "+ parameter.name)
            })

            return result.join(", ")
        }
      - "public Color getBackground() {\r\n\t\tpredraw();\r\n\t\tFloatBuffer buffer = BufferUtils.createFloatBuffer(16);\r\n\t\tGL.glGetFloat(SGL.GL_COLOR_CLEAR_VALUE, buffer);\r\n\t\tpostdraw();\r\n\r\n\t\treturn new Color(buffer);\r\n\t}"
      - >-
        public static final PolygonOptions buildClosedArc(LatLong center,
        LatLong start, LatLong end, ArcType arcType) {
                MVCArray res = buildArcPoints(center, start, end);
                if (ArcType.ROUND.equals(arcType)) {
                    res.push(center);
                }
                return new PolygonOptions().paths(res);
            }
  - source_sentence: |-
      Read data from a spread sheet. Return the data in a dict with
          column numbers as keys.

          sheet: xlrd.sheet.Sheet instance
              Ready for use.

          startstops: list
              Four StartStop objects defining the data to read. See
              :func:`~channelpack.pullxl.prepread`.

          usecols: str or seqence of ints or None
              The columns to use, 0-based. 0 is the spread sheet column
              "A". Can be given as a string also - 'C:E, H' for columns C, D,
              E and H.

          Values in the returned dict are numpy arrays. Types are set based on
          the types in the spread sheet.
    sentences:
      - |-
        public function handleScanNotify(callable $callback)
            {
                $notify = $this->getNotify();

                if (!$notify->isValid()) {
                    throw new FaultException('Invalid request payloads.', 400);
                }

                $notify = $notify->getNotify();

                try {
                    $prepayId = call_user_func_array($callback, [$notify->get('product_id'), $notify->get('openid'), $notify]);
                    $response = [
                        'return_code' => 'SUCCESS',
                        'appid'       => $this->merchant->app_id,
                        'mch_id'      => $this->merchant->merchant_id,
                        'nonce_str'   => uniqid(),
                        'prepay_id'   => strval($prepayId),
                        'result_code' => 'SUCCESS',
                    ];
                    $response['sign'] = generate_sign($response, $this->merchant->key);
                } catch (\Exception $e) {
                    $response = [
                        'return_code'  => 'SUCCESS',
                        'return_msg'   => $e->getCode(),
                        'result_code'  => 'FAIL',
                        'err_code_des' => $e->getMessage(),
                    ];
                }

                return new Response(XML::build($response));
            }
      - |-
        def _sheet_asdict(sheet, startstops, usecols=None):
            """
            """

            _, _, start, stop = startstops
            usecols = _sanitize_usecols(usecols)

            if usecols is not None:
                iswithin = start.col <= min(usecols) and stop.col > max(usecols)
                mess = 'Column in usecols outside defined data range, got '
                assert iswithin, mess + str(usecols)
            else:                       # usecols is None.
                usecols = tuple(range(start.col, stop.col))

            # cols = usecols or range(start.col, stop.col)
            D = dict()

            for c in usecols:
                cells = sheet.col(c, start_rowx=start.row, end_rowx=stop.row)
                types = set([cell.ctype for cell in cells])

                # Replace empty values with nan if appropriate:
                if (not types - NANABLE) and xlrd.XL_CELL_NUMBER in types:
                    D[c] = np.array([np.nan if cell.value == '' else cell.value
                                     for cell in cells])
                elif xlrd.XL_CELL_DATE in types:
                    dm = sheet.book.datemode
                    vals = []
                    for cell in cells:
                        if cell.ctype == xlrd.XL_CELL_DATE:
                            dtuple = xlrd.xldate_as_tuple(cell.value, dm)
                            vals.append(datetime.datetime(*dtuple))
                        elif cell.ctype in NONABLES:
                            vals.append(None)
                        else:
                            vals.append(cell.value)
                    D[c] = np.array(vals)
                else:
                    vals = [None if cell.ctype in NONABLES else cell.value
                            for cell in cells]
                    D[c] = np.array(vals)

            return D
      - "func (o Option) RequiresOption(name string) bool {\n\tfor _, o := range o.Requires {\n\t\tif o == name {\n\t\t\treturn true\n\t\t}\n\t}\n\n\treturn false\n}"
  - source_sentence: |-
      // reBuild partially rebuilds a site given the filesystem events.
      // It returns whetever the content source was changed.
      // TODO(bep) clean up/rewrite this method.
    sentences:
      - "func WebPageImageResolver(doc *goquery.Document) ([]candidate, int) {\n\timgs := doc.Find(\"img\")\n\n\tvar candidates []candidate\n\tsignificantSurface := 320 * 200\n\tsignificantSurfaceCount := 0\n\tsrc := \"\"\n\timgs.Each(func(i int, tag *goquery.Selection) {\n\t\tvar surface int\n\t\tsrc = getImageSrc(tag)\n\t\tif src == \"\" {\n\t\t\treturn\n\t\t}\n\n\t\twidth, _ := tag.Attr(\"width\")\n\t\theight, _ := tag.Attr(\"height\")\n\t\tif width != \"\" {\n\t\t\tw, _ := strconv.Atoi(width)\n\t\t\tif height != \"\" {\n\t\t\t\th, _ := strconv.Atoi(height)\n\t\t\t\tsurface = w * h\n\t\t\t} else {\n\t\t\t\tsurface = w\n\t\t\t}\n\t\t} else {\n\t\t\tif height != \"\" {\n\t\t\t\tsurface, _ = strconv.Atoi(height)\n\t\t\t} else {\n\t\t\t\tsurface = 0\n\t\t\t}\n\t\t}\n\n\t\tif surface > significantSurface {\n\t\t\tsignificantSurfaceCount++\n\t\t}\n\n\t\ttagscore := score(tag)\n\t\tif tagscore >= 0 {\n\t\t\tc := candidate{\n\t\t\t\turl:     src,\n\t\t\t\tsurface: surface,\n\t\t\t\tscore:   score(tag),\n\t\t\t}\n\t\t\tcandidates = append(candidates, c)\n\t\t}\n\t})\n\n\tif len(candidates) == 0 {\n\t\treturn nil, 0\n\t}\n\n\treturn candidates, significantSurfaceCount\n\n}"
      - "@SuppressWarnings(\"rawtypes\")\n\tpublic void open(Map conf, TopologyContext context,\n\t\t\tSpoutOutputCollector collector) {\n\t\tif(this.jmsProvider == null){\n\t\t\tthrow new IllegalStateException(\"JMS provider has not been set.\");\n\t\t}\n\t\tif(this.tupleProducer == null){\n\t\t\tthrow new IllegalStateException(\"JMS Tuple Producer has not been set.\");\n\t\t}\n\t\tInteger topologyTimeout = (Integer)conf.get(\"topology.message.timeout.secs\");\n\t\t// TODO fine a way to get the default timeout from storm, so we're not hard-coding to 30 seconds (it could change)\n\t\ttopologyTimeout = topologyTimeout == null ? 30 : topologyTimeout;\n\t\tif( (topologyTimeout.intValue() * 1000 )> this.recoveryPeriod){\n\t\t    LOG.warn(\"*** WARNING *** : \" +\n\t\t    \t\t\"Recovery period (\"+ this.recoveryPeriod + \" ms.) is less then the configured \" +\n\t\t    \t\t\"'topology.message.timeout.secs' of \" + topologyTimeout + \n\t\t    \t\t\" secs. This could lead to a message replay flood!\");\n\t\t}\n\t\tthis.queue = new LinkedBlockingQueue<Message>();\n\t\tthis.toCommit = new TreeSet<JmsMessageID>();\n        this.pendingMessages = new HashMap<JmsMessageID, Message>();\n\t\tthis.collector = collector;\n\t\ttry {\n\t\t\tConnectionFactory cf = this.jmsProvider.connectionFactory();\n\t\t\tDestination dest = this.jmsProvider.destination();\n\t\t\tthis.connection = cf.createConnection();\n\t\t\tthis.session = connection.createSession(false,\n\t\t\t\t\tthis.jmsAcknowledgeMode);\n\t\t\tMessageConsumer consumer = session.createConsumer(dest);\n\t\t\tconsumer.setMessageListener(this);\n\t\t\tthis.connection.start();\n\t\t\tif (this.isDurableSubscription() && this.recoveryPeriod > 0){\n\t\t\t    this.recoveryTimer = new Timer();\n\t\t\t    this.recoveryTimer.scheduleAtFixedRate(new RecoveryTask(), 10, this.recoveryPeriod);\n\t\t\t}\n\t\t\t\n\t\t} catch (Exception e) {\n\t\t\tLOG.warn(\"Error creating JMS connection.\", e);\n\t\t}\n\n\t}"
      - "func (s *Site) processPartial(events []fsnotify.Event) (whatChanged, error) {\n\n\tevents = s.filterFileEvents(events)\n\tevents = s.translateFileEvents(events)\n\n\ts.Log.DEBUG.Printf(\"Rebuild for events %q\", events)\n\n\th := s.h\n\n\t// First we need to determine what changed\n\n\tvar (\n\t\tsourceChanged       = []fsnotify.Event{}\n\t\tsourceReallyChanged = []fsnotify.Event{}\n\t\tcontentFilesChanged []string\n\t\ttmplChanged         = []fsnotify.Event{}\n\t\tdataChanged         = []fsnotify.Event{}\n\t\ti18nChanged         = []fsnotify.Event{}\n\t\tshortcodesChanged   = make(map[string]bool)\n\t\tsourceFilesChanged  = make(map[string]bool)\n\n\t\t// prevent spamming the log on changes\n\t\tlogger = helpers.NewDistinctFeedbackLogger()\n\t)\n\n\tcachePartitions := make([]string, len(events))\n\n\tfor i, ev := range events {\n\t\tcachePartitions[i] = resources.ResourceKeyPartition(ev.Name)\n\n\t\tif s.isContentDirEvent(ev) {\n\t\t\tlogger.Println(\"Source changed\", ev)\n\t\t\tsourceChanged = append(sourceChanged, ev)\n\t\t}\n\t\tif s.isLayoutDirEvent(ev) {\n\t\t\tlogger.Println(\"Template changed\", ev)\n\t\t\ttmplChanged = append(tmplChanged, ev)\n\n\t\t\tif strings.Contains(ev.Name, \"shortcodes\") {\n\t\t\t\tshortcode := filepath.Base(ev.Name)\n\t\t\t\tshortcode = strings.TrimSuffix(shortcode, filepath.Ext(shortcode))\n\t\t\t\tshortcodesChanged[shortcode] = true\n\t\t\t}\n\t\t}\n\t\tif s.isDataDirEvent(ev) {\n\t\t\tlogger.Println(\"Data changed\", ev)\n\t\t\tdataChanged = append(dataChanged, ev)\n\t\t}\n\t\tif s.isI18nEvent(ev) {\n\t\t\tlogger.Println(\"i18n changed\", ev)\n\t\t\ti18nChanged = append(dataChanged, ev)\n\t\t}\n\t}\n\n\t// These in memory resource caches will be rebuilt on demand.\n\tfor _, s := range s.h.Sites {\n\t\ts.ResourceSpec.ResourceCache.DeletePartitions(cachePartitions...)\n\t}\n\n\tif len(tmplChanged) > 0 || len(i18nChanged) > 0 {\n\t\tsites := s.h.Sites\n\t\tfirst := sites[0]\n\n\t\ts.h.init.Reset()\n\n\t\t// TOD(bep) globals clean\n\t\tif err := first.Deps.LoadResources(); err != nil {\n\t\t\treturn whatChanged{}, err\n\t\t}\n\n\t\tfor i := 1; i < len(sites); i++ {\n\t\t\tsite := sites[i]\n\t\t\tvar err error\n\t\t\tdepsCfg := deps.DepsCfg{\n\t\t\t\tLanguage:      site.language,\n\t\t\t\tMediaTypes:    site.mediaTypesConfig,\n\t\t\t\tOutputFormats: site.outputFormatsConfig,\n\t\t\t}\n\t\t\tsite.Deps, err = first.Deps.ForLanguage(depsCfg, func(d *deps.Deps) error {\n\t\t\t\td.Site = &site.Info\n\t\t\t\treturn nil\n\t\t\t})\n\t\t\tif err != nil {\n\t\t\t\treturn whatChanged{}, err\n\t\t\t}\n\t\t}\n\t}\n\n\tif len(dataChanged) > 0 {\n\t\ts.h.init.data.Reset()\n\t}\n\n\tfor _, ev := range sourceChanged {\n\t\tremoved := false\n\n\t\tif ev.Op&fsnotify.Remove == fsnotify.Remove {\n\t\t\tremoved = true\n\t\t}\n\n\t\t// Some editors (Vim) sometimes issue only a Rename operation when writing an existing file\n\t\t// Sometimes a rename operation means that file has been renamed other times it means\n\t\t// it's been updated\n\t\tif ev.Op&fsnotify.Rename == fsnotify.Rename {\n\t\t\t// If the file is still on disk, it's only been updated, if it's not, it's been moved\n\t\t\tif ex, err := afero.Exists(s.Fs.Source, ev.Name); !ex || err != nil {\n\t\t\t\tremoved = true\n\t\t\t}\n\t\t}\n\t\tif removed && IsContentFile(ev.Name) {\n\t\t\th.removePageByFilename(ev.Name)\n\t\t}\n\n\t\tsourceReallyChanged = append(sourceReallyChanged, ev)\n\t\tsourceFilesChanged[ev.Name] = true\n\t}\n\n\tfor shortcode := range shortcodesChanged {\n\t\t// There are certain scenarios that, when a shortcode changes,\n\t\t// it isn't sufficient to just rerender the already parsed shortcode.\n\t\t// One example is if the user adds a new shortcode to the content file first,\n\t\t// and then creates the shortcode on the file system.\n\t\t// To handle these scenarios, we must do a full reprocessing of the\n\t\t// pages that keeps a reference to the changed shortcode.\n\t\tpagesWithShortcode := h.findPagesByShortcode(shortcode)\n\t\tfor _, p := range pagesWithShortcode {\n\t\t\tcontentFilesChanged = append(contentFilesChanged, p.File().Filename())\n\t\t}\n\t}\n\n\tif len(sourceReallyChanged) > 0 || len(contentFilesChanged) > 0 {\n\t\tvar filenamesChanged []string\n\t\tfor _, e := range sourceReallyChanged {\n\t\t\tfilenamesChanged = append(filenamesChanged, e.Name)\n\t\t}\n\t\tif len(contentFilesChanged) > 0 {\n\t\t\tfilenamesChanged = append(filenamesChanged, contentFilesChanged...)\n\t\t}\n\n\t\tfilenamesChanged = helpers.UniqueStrings(filenamesChanged)\n\n\t\tif err := s.readAndProcessContent(filenamesChanged...); err != nil {\n\t\t\treturn whatChanged{}, err\n\t\t}\n\n\t}\n\n\tchanged := whatChanged{\n\t\tsource: len(sourceChanged) > 0 || len(shortcodesChanged) > 0,\n\t\tother:  len(tmplChanged) > 0 || len(i18nChanged) > 0 || len(dataChanged) > 0,\n\t\tfiles:  sourceFilesChanged,\n\t}\n\n\treturn changed, nil\n\n}"
pipeline_tag: sentence-similarity
library_name: sentence-transformers

SentenceTransformer based on Shuu12121/CodeModernBERT-Finch-Pre

This is a sentence-transformers model finetuned from Shuu12121/CodeModernBERT-Finch-Pre. It maps sentences & paragraphs to a 512-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: Shuu12121/CodeModernBERT-Finch-Pre
Maximum Sequence Length: 1024 tokens
Output Dimensionality: 512 dimensions
Similarity Function: Cosine Similarity

Model Sources

Documentation: Sentence Transformers Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 1024, 'do_lower_case': False, 'architecture': 'ModernBertModel'})
  (1): Pooling({'word_embedding_dimension': 512, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("sentence_transformers_model_id")
# Run inference
sentences = [
    '// reBuild partially rebuilds a site given the filesystem events.\n// It returns whetever the content source was changed.\n// TODO(bep) clean up/rewrite this method.',
    'func (s *Site) processPartial(events []fsnotify.Event) (whatChanged, error) {\n\n\tevents = s.filterFileEvents(events)\n\tevents = s.translateFileEvents(events)\n\n\ts.Log.DEBUG.Printf("Rebuild for events %q", events)\n\n\th := s.h\n\n\t// First we need to determine what changed\n\n\tvar (\n\t\tsourceChanged       = []fsnotify.Event{}\n\t\tsourceReallyChanged = []fsnotify.Event{}\n\t\tcontentFilesChanged []string\n\t\ttmplChanged         = []fsnotify.Event{}\n\t\tdataChanged         = []fsnotify.Event{}\n\t\ti18nChanged         = []fsnotify.Event{}\n\t\tshortcodesChanged   = make(map[string]bool)\n\t\tsourceFilesChanged  = make(map[string]bool)\n\n\t\t// prevent spamming the log on changes\n\t\tlogger = helpers.NewDistinctFeedbackLogger()\n\t)\n\n\tcachePartitions := make([]string, len(events))\n\n\tfor i, ev := range events {\n\t\tcachePartitions[i] = resources.ResourceKeyPartition(ev.Name)\n\n\t\tif s.isContentDirEvent(ev) {\n\t\t\tlogger.Println("Source changed", ev)\n\t\t\tsourceChanged = append(sourceChanged, ev)\n\t\t}\n\t\tif s.isLayoutDirEvent(ev) {\n\t\t\tlogger.Println("Template changed", ev)\n\t\t\ttmplChanged = append(tmplChanged, ev)\n\n\t\t\tif strings.Contains(ev.Name, "shortcodes") {\n\t\t\t\tshortcode := filepath.Base(ev.Name)\n\t\t\t\tshortcode = strings.TrimSuffix(shortcode, filepath.Ext(shortcode))\n\t\t\t\tshortcodesChanged[shortcode] = true\n\t\t\t}\n\t\t}\n\t\tif s.isDataDirEvent(ev) {\n\t\t\tlogger.Println("Data changed", ev)\n\t\t\tdataChanged = append(dataChanged, ev)\n\t\t}\n\t\tif s.isI18nEvent(ev) {\n\t\t\tlogger.Println("i18n changed", ev)\n\t\t\ti18nChanged = append(dataChanged, ev)\n\t\t}\n\t}\n\n\t// These in memory resource caches will be rebuilt on demand.\n\tfor _, s := range s.h.Sites {\n\t\ts.ResourceSpec.ResourceCache.DeletePartitions(cachePartitions...)\n\t}\n\n\tif len(tmplChanged) > 0 || len(i18nChanged) > 0 {\n\t\tsites := s.h.Sites\n\t\tfirst := sites[0]\n\n\t\ts.h.init.Reset()\n\n\t\t// TOD(bep) globals clean\n\t\tif err := first.Deps.LoadResources(); err != nil {\n\t\t\treturn whatChanged{}, err\n\t\t}\n\n\t\tfor i := 1; i < len(sites); i++ {\n\t\t\tsite := sites[i]\n\t\t\tvar err error\n\t\t\tdepsCfg := deps.DepsCfg{\n\t\t\t\tLanguage:      site.language,\n\t\t\t\tMediaTypes:    site.mediaTypesConfig,\n\t\t\t\tOutputFormats: site.outputFormatsConfig,\n\t\t\t}\n\t\t\tsite.Deps, err = first.Deps.ForLanguage(depsCfg, func(d *deps.Deps) error {\n\t\t\t\td.Site = &site.Info\n\t\t\t\treturn nil\n\t\t\t})\n\t\t\tif err != nil {\n\t\t\t\treturn whatChanged{}, err\n\t\t\t}\n\t\t}\n\t}\n\n\tif len(dataChanged) > 0 {\n\t\ts.h.init.data.Reset()\n\t}\n\n\tfor _, ev := range sourceChanged {\n\t\tremoved := false\n\n\t\tif ev.Op&fsnotify.Remove == fsnotify.Remove {\n\t\t\tremoved = true\n\t\t}\n\n\t\t// Some editors (Vim) sometimes issue only a Rename operation when writing an existing file\n\t\t// Sometimes a rename operation means that file has been renamed other times it means\n\t\t// it\'s been updated\n\t\tif ev.Op&fsnotify.Rename == fsnotify.Rename {\n\t\t\t// If the file is still on disk, it\'s only been updated, if it\'s not, it\'s been moved\n\t\t\tif ex, err := afero.Exists(s.Fs.Source, ev.Name); !ex || err != nil {\n\t\t\t\tremoved = true\n\t\t\t}\n\t\t}\n\t\tif removed && IsContentFile(ev.Name) {\n\t\t\th.removePageByFilename(ev.Name)\n\t\t}\n\n\t\tsourceReallyChanged = append(sourceReallyChanged, ev)\n\t\tsourceFilesChanged[ev.Name] = true\n\t}\n\n\tfor shortcode := range shortcodesChanged {\n\t\t// There are certain scenarios that, when a shortcode changes,\n\t\t// it isn\'t sufficient to just rerender the already parsed shortcode.\n\t\t// One example is if the user adds a new shortcode to the content file first,\n\t\t// and then creates the shortcode on the file system.\n\t\t// To handle these scenarios, we must do a full reprocessing of the\n\t\t// pages that keeps a reference to the changed shortcode.\n\t\tpagesWithShortcode := h.findPagesByShortcode(shortcode)\n\t\tfor _, p := range pagesWithShortcode {\n\t\t\tcontentFilesChanged = append(contentFilesChanged, p.File().Filename())\n\t\t}\n\t}\n\n\tif len(sourceReallyChanged) > 0 || len(contentFilesChanged) > 0 {\n\t\tvar filenamesChanged []string\n\t\tfor _, e := range sourceReallyChanged {\n\t\t\tfilenamesChanged = append(filenamesChanged, e.Name)\n\t\t}\n\t\tif len(contentFilesChanged) > 0 {\n\t\t\tfilenamesChanged = append(filenamesChanged, contentFilesChanged...)\n\t\t}\n\n\t\tfilenamesChanged = helpers.UniqueStrings(filenamesChanged)\n\n\t\tif err := s.readAndProcessContent(filenamesChanged...); err != nil {\n\t\t\treturn whatChanged{}, err\n\t\t}\n\n\t}\n\n\tchanged := whatChanged{\n\t\tsource: len(sourceChanged) > 0 || len(shortcodesChanged) > 0,\n\t\tother:  len(tmplChanged) > 0 || len(i18nChanged) > 0 || len(dataChanged) > 0,\n\t\tfiles:  sourceFilesChanged,\n\t}\n\n\treturn changed, nil\n\n}',
    'func WebPageImageResolver(doc *goquery.Document) ([]candidate, int) {\n\timgs := doc.Find("img")\n\n\tvar candidates []candidate\n\tsignificantSurface := 320 * 200\n\tsignificantSurfaceCount := 0\n\tsrc := ""\n\timgs.Each(func(i int, tag *goquery.Selection) {\n\t\tvar surface int\n\t\tsrc = getImageSrc(tag)\n\t\tif src == "" {\n\t\t\treturn\n\t\t}\n\n\t\twidth, _ := tag.Attr("width")\n\t\theight, _ := tag.Attr("height")\n\t\tif width != "" {\n\t\t\tw, _ := strconv.Atoi(width)\n\t\t\tif height != "" {\n\t\t\t\th, _ := strconv.Atoi(height)\n\t\t\t\tsurface = w * h\n\t\t\t} else {\n\t\t\t\tsurface = w\n\t\t\t}\n\t\t} else {\n\t\t\tif height != "" {\n\t\t\t\tsurface, _ = strconv.Atoi(height)\n\t\t\t} else {\n\t\t\t\tsurface = 0\n\t\t\t}\n\t\t}\n\n\t\tif surface > significantSurface {\n\t\t\tsignificantSurfaceCount++\n\t\t}\n\n\t\ttagscore := score(tag)\n\t\tif tagscore >= 0 {\n\t\t\tc := candidate{\n\t\t\t\turl:     src,\n\t\t\t\tsurface: surface,\n\t\t\t\tscore:   score(tag),\n\t\t\t}\n\t\t\tcandidates = append(candidates, c)\n\t\t}\n\t})\n\n\tif len(candidates) == 0 {\n\t\treturn nil, 0\n\t}\n\n\treturn candidates, significantSurfaceCount\n\n}',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 512]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.5930, 0.3537],
#         [0.5930, 1.0000, 0.3285],
#         [0.3537, 0.3285, 1.0000]])

Training Details

Training Dataset

Unnamed Dataset

Size: 58,800 training samples
Columns: sentence_0, sentence_1, and label
Approximate statistics based on the first 1000 samples:
sentence_0 sentence_1 label
type string string float
details
min: 3 tokens
mean: 55.73 tokens
max: 1024 tokens

min: 28 tokens
mean: 179.65 tokens
max: 1024 tokens

min: 1.0
mean: 1.0
max: 1.0

	sentence_0	sentence_1	label
type	string	string	float
details	min: 3 tokens mean: 55.73 tokens max: 1024 tokens	min: 28 tokens mean: 179.65 tokens max: 1024 tokens	min: 1.0 mean: 1.0 max: 1.0

Samples:

sentence_0	sentence_1	label
`// CASNext is a non-callback, loop-based version of CAS method. // // Usage is like this: // // var state memcached.CASState // for client.CASNext(vb, key, exp, &state) { // state.Value = some_mutation(state.Value) // } // if state.Err != nil { ... }`	func (c Client) CASNext(vb uint16, k string, exp int, state CASState) bool { if state.initialized { if !state.Exists { // Adding a new key: if state.Value == nil { state.Cas = 0 return false // no-op (delete of non-existent value) } state.resp, state.Err = c.Add(vb, k, 0, exp, state.Value) } else { // Updating / deleting a key: req := &gomemcached.MCRequest{ Opcode: gomemcached.DELETE, VBucket: vb, Key: []byte(k), Cas: state.Cas} if state.Value != nil { req.Opcode = gomemcached.SET req.Opaque = 0 req.Extras = []byte{0, 0, 0, 0, 0, 0, 0, 0} req.Body = state.Value flags := 0 exp := 0 // ??? Should we use initialexp here instead? binary.BigEndian.PutUint64(req.Extras, uint64(flags)<<32	uint64(exp)) } state.resp, state.Err = c.Send(req) } // If the response status is KEY_EEXISTS or NOT_STORED there's a conflict and we'll need to // get the new value (below). Otherwise, we're done (either ...
`// RestoreResourcePools restores a bulk of resource pools, usually from a backup.`	func (f *Facade) RestoreResourcePools(ctx datastore.Context, pools []pool.ResourcePool) error { defer ctx.Metrics().Stop(ctx.Metrics().Start("Facade.RestoreResourcePools")) // Do not DFSLock here, ControlPlaneDao does that var alog audit.Logger for _, pool := range pools { alog = f.auditLogger.Message(ctx, "Adding ResourcePool").Action(audit.Add).Entity(&pool) pool.DatabaseVersion = 0 if err := f.addResourcePool(ctx, &pool); err != nil { if err == ErrPoolExists { if err := f.updateResourcePool(ctx, &pool); err != nil { glog.Errorf("Could not restore resource pool %s via update: %s", pool.ID, err) return alog.Error(err) } } else { glog.Errorf("Could not restore resource pool %s via add: %s", pool.ID, err) return alog.Error(err) } } alog.Succeeded() } return nil }	`1.0`
`// run starts a goroutine to handle client connects and broadcast events.`	`func (s *Streamer) run() { go func() { for { select { case cl := <-s.connecting: s.clients[cl] = true case cl := <-s.disconnecting: delete(s.clients, cl) case event := <-s.event: for cl := range s.clients { // TODO: non-blocking broadcast //select { //case cl <- event: // Try to send event to client //default: // fmt.Println("Channel full. Discarding value") //} cl <- event } } } }() }`	`1.0`

Loss: MultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim"
}

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 200
per_device_eval_batch_size: 200
fp16: True
multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: no
prediction_loss_only: True
per_device_train_batch_size: 200
per_device_eval_batch_size: 200
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 1
eval_accumulation_steps: None
torch_empty_cache_steps: None
learning_rate: 5e-05
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1
num_train_epochs: 3
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.0
warmup_steps: 0
log_level: passive
log_level_replica: warning
log_on_each_node: True
logging_nan_inf_filter: True
save_safetensors: True
save_on_each_node: False
save_only_model: False
restore_callback_states_from_checkpoint: False
no_cuda: False
use_cpu: False
use_mps_device: False
seed: 42
data_seed: None
jit_mode_eval: False
use_ipex: False
bf16: False
fp16: True
fp16_opt_level: O1
half_precision_backend: auto
bf16_full_eval: False
fp16_full_eval: False
tf32: None
local_rank: 0
ddp_backend: None
tpu_num_cores: None
tpu_metrics_debug: False
debug: []
dataloader_drop_last: False
dataloader_num_workers: 0
dataloader_prefetch_factor: None
past_index: -1
disable_tqdm: False
remove_unused_columns: True
label_names: None
load_best_model_at_end: False
ignore_data_skip: False
fsdp: []
fsdp_min_num_params: 0
fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
fsdp_transformer_layer_cls_to_wrap: None
accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
deepspeed: None
label_smoothing_factor: 0.0
optim: adamw_torch
optim_args: None
adafactor: False
group_by_length: False
length_column_name: length
ddp_find_unused_parameters: None
ddp_bucket_cap_mb: None
ddp_broadcast_buffers: False
dataloader_pin_memory: True
dataloader_persistent_workers: False
skip_memory_metrics: True
use_legacy_prediction_loop: False
push_to_hub: False
resume_from_checkpoint: None
hub_model_id: None
hub_strategy: every_save
hub_private_repo: None
hub_always_push: False
hub_revision: None
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_inputs_for_metrics: False
include_for_metrics: []
eval_do_concat_batches: True
fp16_backend: auto
push_to_hub_model_id: None
push_to_hub_organization: None
mp_parameters:
auto_find_batch_size: False
full_determinism: False
torchdynamo: None
ray_scope: last
ddp_timeout: 1800
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
include_tokens_per_second: False
include_num_input_tokens_seen: False
neftune_noise_alpha: None
optim_target_modules: None
batch_eval_metrics: False
eval_on_start: False
use_liger_kernel: False
liger_kernel_config: None
eval_use_gather_object: False
average_tokens_across_devices: False
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: round_robin
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss
1.7007	500	0.3417

Framework Versions

Python: 3.10.12
Sentence Transformers: 5.0.0
Transformers: 4.53.1
PyTorch: 2.7.0+cu128
Accelerate: 1.7.0
Datasets: 3.6.0
Tokenizers: 0.21.2

Citation

BibTeX

Sentence Transformers

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

MultipleNegativesRankingLoss

@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply},
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}