Upload 11 files

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 768,
+  "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
+}

README.md

@@ -0,0 +1,793 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:5776
+- loss:MultipleNegativesRankingLoss
+base_model: BAAI/bge-base-en
+widget:
+- source_sentence: Explain the importance of specifying VST search locations in Minihost
+    Modular and how it affects the loading of plugins and .gra files.
+  sentences:
+  - 'Document_title: Minihost Modular (DEPRECIATED)
+
+    File_name: plugins/Minihost Modular.htm
+
+    Heading_hierarchy: [Minihost Modular (DEPRECIATED) -> Registering Plugins]
+
+    Anchor_id: [none]
+
+    Before MiniHost can find your plugins you need to specify their location and scan
+    them. The fastest way is to use Scan (no verify), but we recommend Scan & Verify
+    as it will tell you what plugins might cause problems (you will get crash reports
+    in the lis), and give more information such as
+
+    manufacturer, number of I/Os etc. Select File > Preferences > Plugins > Scan &
+    Verify NOTES: • Scanning - Without scanning your plugins, you won''t be able to
+    add any plugins in MiniHost Modular and .gra files from other users won''t load
+    correctly. • Enter up to 4 VST search locations - These
+
+    are in ADDITION to the standard VST locations that will also be scanned. • Bridging
+    - Minihost Modular will only run 32 or 64 Bit plugins equivalent to the version
+    you are using (32 or 64 Bit).'
+  - 'Document_title: FL Keys
+
+    File_name: plugins/FL Keys.htm
+
+    Heading_hierarchy: [FL Keys]
+
+    Anchor_id: [none]
+
+    FL Keys With the help of several additional modules included in FL Studio, FL
+    Keys can also operate as Rhodes & Roto Organ.'
+  - "Document_title: Sawer - Modulation\nFile_name: plugins/Sawer_Modulation.htm\n\
+    Heading_hierarchy: [Sawer - Modulation -> LFO Controls]\nAnchor_id: [none]\nLFO\
+    \ is a 'Low Frequency Oscillator' that creates an oscillating control output,\
+    \ the rate of which can be adjusted between 0 and 10 Hz. This generator is used\
+    \ to control parameters inside Sawer to add motion\n      or variability to sounds\
+    \ in order to make them more interesting. • SPEED - LFO speed, between 0 and 10\
+    \ Hz. • ATTACK - Fade-in for the LFO, ramps up the LFO amount. This is linked\
+    \ to a note-on event. • RELEASE - Fade-out for the LFO, ramps down the LFO amount.\
+    \ This is linked to a\nnote-release event. • AMPLITUDE - A multiplier or amount\
+    \ of LFO to be applied to the Destination control. • RETRIG (Retrigger) - Restarts\
+    \ the LFO cycle at the start of each note. • TMP SYNC (Tempo Sync) - Synchronizes\
+    \ the LFO speed to the host tempo. When selected the SPEED knob now\ncontrols\
+    \ the tempo sync from 1/16th to 32/4. • INV (Invert) - Inverts the phase of the\
+    \ LFO waveform. • SHAPE - Select the LFO shape (TRIANGLE, SAW, SQUARE, RANDOM).\
+    \ • LFO DESTINATION LFO Destination, select from - ➤ CUTOFF - [Filter cutoff\n\
+    frequency](https://www.image-line.com/fl-studio-learning/fl-studio-online-manual/html/Sawer_Filter.htm)\
+    \ . ➤ SYNC FRQ (Frequency) - [Main oscillator synchronization frequency](https://www.image-line.com/fl-studio-learning/fl-studio-online-manual/html/Sawer_Oscillators.htm)\
+    \ . ➤ PHASE - [Sub-o\nscillator phase](https://www.image-line.com/fl-studio-learning/fl-studio-online-manual/html/Sawer_Oscillators.htm)\
+    \ . ➤ FREQ (Frequency) - [Master tuning frequency](https://www.image-line.com/fl-studio-learning/fl-studio-online-manual/html/Sawer_Master.htm)\
+    \ . ➤ NOISE - Controls the [Oscillato\nr noise level](https://www.image-line.com/fl-studio-learning/fl-studio-online-manual/html/Sawer_Oscillators.htm)\
+    \ . ➤ LEVEL - [Master volume](https://www.image-line.com/fl-studio-learning/fl-studio-online-manual/html/Sawer_Master.htm)\
+    \ . ➤ PAN - [Master\npanning](https://www.image-line.com/fl-studio-learning/fl-studio-online-manual/html/Sawer_Master.htm)\
+    \ ."
+- source_sentence: What steps should a user take to change the name on their FL Studio
+    account after a legal name change, and why is it important to have a verifiable
+    user ID in their account?
+  sentences:
+  - 'Title: Legal name change
+
+    Answer: If you are looking to hide your name to protect your online privacy when
+    using FL Studio in public, see - [How can I change the name displayed in the Title
+    Bar?](https://support.image-line.com/action/knowledgebase/?ans=524)To change the
+    name on your Account after a legal name change: Please create a [Support Ticket
+    here](https://support.image-line.com/action/ticketing/add-issue), attach your
+    documentation and request a name change for your license or account. NOTE: Always
+    ensure you have a verifiable user ID in your account. With FL Studio''s Lifetime
+    Free Updates,
+
+    it''s crucial for us to identify you as the rightful owner. If you lose access
+    to your account and we cannot verify your identity, we cannot grant access due
+    to [GDPR](https://gdpr-info.eu/) privacy regulations. Image-Line Support Team'
+  - 'Document_title: FLEX
+
+    File_name: plugins/FLEX.htm
+
+    Heading_hierarchy: [FLEX -> Online Packs]
+
+    Anchor_id: [none]
+
+    You can download free, subscribed and purchased Packs from the integrated FLEX
+    Store so there is no need to leave FLEX to install expansion content. There are
+    two categories according to the Tabs: • GET - Free, subscribed and purchased packs
+    that are ready to download. Click the
+
+    Download Icon after the pack name to download and install it. • STORE - Packs
+    that have not been purchased. After purchase they will move to the ''GET'' Tab.'
+  - "Document_title: Installing Plugins    \nFile_name: basics_externalplugins.htm\n\
+    Heading_hierarchy: [Installing Plugins -> Related Links:]\nAnchor_id: [none]\n\
+    ➤ [Installed instruments](https://www.image-line.com/fl-studio-learning/fl-studio-online-manual/html/generator_plugins.htm)\
+    \ - Learn more about instruments (generators) pre-installed in FL Studio. ➤ [Installed\n\
+    effects](https://www.image-line.com/fl-studio-learning/fl-studio-online-manual/html/effects_plugins.htm)\
+    \ - Learn more about the effects pre-installed in FL Studio. ➤ [Plugin standards](https://www.image-line.com/fl-studio-learning/fl-studio-online-manual/html/plugins_supported.htm)\
+    \ - Learn\nmore about the plugin standards supported by FL Studio."
+- source_sentence: Explain the role of the Self Oscillating Filter (SOF) in the Drumpad
+    percussion modeling instrument and describe how it contributes to the creation
+    of kick and snare sounds.
+  sentences:
+  - 'Document_title: Drumpad - Percussion Modeling Instrument
+
+    File_name: plugins/Drumpad.htm
+
+    Heading_hierarchy: [Drumpad - Percussion Modeling Instrument -> Self Oscillating
+    Filter (SOF)]
+
+    Anchor_id: [none]
+
+    The SOF is an ''allpass'' filter with a narrow frequency-peak exhibiting high
+    levels of self-oscillation. When the frequency-peak is swept quickly downwards,
+    it is useful to make kicks and snares. • Freq - Down-sweep starting frequency.
+    The frequency will sweep down to ~20 Hz (fixed). • Decay -
+
+    Down-sweep time. Fast sweeps produce the most realistic ''kick'' sounds. • Level
+    - SOF mix level. The SOF sweep is added before other filters in the modeling engine,
+    immediately after the Membrane sound is generated.'
+  - 'Title: Does iOS version matter?
+
+    Answer: FL Studio Mobile runs on every device with iOS 5.1 and higher. If your
+    iOS device can not run iOS 5.1 or higher, it is not possible to reinstall your
+    FL Studio Mobile app. A hardware update is needed in that case. As soon as you
+    have new hardware, and the iOS can be updated to 5.1 or higher, you regain access
+    to your earlier purchased app in your iTunes account.The soon to be released FL
+    Studio Mobile update (expected in September 2014) will be optimized for iOS 8.'
+  - "Document_title: Audio Myths & DAW Wars       \nFile_name: app_audio.htm\nHeading_hierarchy:\
+    \ [Audio Myths & DAW Wars -> Audio quality, the eternal quest]\nAnchor_id: [none]\n\
+    Spend time on any forum devoted to any Digital Audio Workstation (DAW) software\
+    \ or music production and you are guaranteed to see users making claims about\
+    \ the superior audio quality of this or that DAW application. Protagonists will\
+    \ say a given program is clearly and audibly superior to\nanother. To be frank,\
+    \ that's just nonsense . Any DAW application that uses, at least , 32 Bit floating\
+    \ point calculations (and today, that's all software), will process audio without\
+    \ introducing unwanted distortions, frequency response alterations or any other\
+    \ effect that would be ' clearly audible '\nso as to influence opinion. This ability\
+    \ to process audio without making unintended, audible changes is called ' transparency\
+    \ '. From a transparency perspective all DAW software is created equal ."
+- source_sentence: Explain how the four key parameters—Tension, Phase, Material, and
+    Shape—affect the tonal character of the drum membrane in the Drumaxx Percussion
+    Modeling Instrument. How should these parameters be adjusted to achieve a natural
+    drum sound?
+  sentences:
+  - "Document_title: ZGameEditor Visualizer\nFile_name: plugins/ZGameEditor Visualizer.htm\n\
+    Heading_hierarchy: [ZGameEditor Visualizer -> Add Content]\nAnchor_id: zge_addcontent\n\
+    Custom content you can add here includes Pictures, HTML, Text, Meshes and Video.\
+    \ The content is then available from the Image Src and Mesh selectors at the top\
+    \ of the Effect interface for each layer. NOTE: You can drag and drop video and\
+    \ images directly on the main Layer Window and it\nwill also be listed here. •\
+    \ Images - Most image and video formats are supported. If an effect can use images,\
+    \ select them from the Image Src field at the top of the Effect column.  Click\
+    \ the button and browse to the location of the content. The location will then\
+    \ be listed in the field below. Use\nthe sub-tabs here to load: ➤ Add Pictures\
+    \ - Images in popular formats are supported (.bmp, .gif, .jpg, .png etc). ➤ Add\
+    \ Videos - Any video format, supported by your computer, should work. ➤ Add WebCam\
+    \ - Any webcam/s connected to your computer will appear here. ➤ Add Window - Choose\n\
+    from FL Studio Windows such as the Playlist or Mixer as source video. ➤ Add Preset\
+    \ - Use ZGameEditor presets (projects) as source video. ➤ Add URL - A link to\
+    \ any streamable video file on the web. ➤ Find online media - Browse copyright\
+    \ free, high quality images and videos from [Pexels.com](\nhttps://www.pexels.com/)\
+    \ . ➤ Filtering - Choose how images are blended with the background when the Alpha\
+    \ controls are used. ➤ Video preloading - Options associated with preloading video\
+    \ to RAM. ◆ Enable video preloading -  Preload video to RAM. This will significantly\
+    \ reduce CPU load and\nresponsiveness when using CUE points to jump around or\
+    \ automation to animate the video playback position. ◆ Compress - Reduces the\
+    \ amount of RAM needed with a small increase in CPU load. ◆ With audio - Preload\
+    \ the video's audio and also by extension, include the audio in the video in\n\
+    playback. • Sync video with song position - Will start any video playback with\
+    \ the start of the project. When this is disabled, the video will play continuously\
+    \ as a loop. • Lower controls: ➤ Select all - Selects all content. ➤ Remove -\
+    \ Removes selected content. ➤ Remove all - Removes all content. \n➤ Replace -\
+    \ Replaces selected content so that presets using the original content work with\
+    \ the new content. ➤ Remove unused - Removes any content that is not used in the\
+    \ project. • HTML - HTML code entered here works in conjunction with the Text\
+    \ > TextTrueType effect. The code\ndetermines the appearance of the text in accordance\
+    \ with HTML text formatting. There is some example HTML options on the HTML tab\
+    \ itself (right side) or your can [watch this video](https://www.youtube.com/watch?v=yrm2SAfXav0)\
+    \ . ➤ Example code: [textline] • How to use: Enter the exact\ncode above on the\
+    \ HTML tab. Select the Text > TrueTypeText effect. Switch on SingleLineMode and\
+    \ automate the line shown with the Text Line control. You can use additional HTML\
+    \ formatting (bold, italics, text-size etc) as desired. • Text - Enter the text\
+    \ to be displayed by the Text > TextTrue\nType , MeshText and TextDraw effects.\
+    \ From these effects, use the Text Line control to step through lines entered\
+    \ on the Text tab. • Meshes - Include [.3ds format](https://en.wikipedia.org/wiki/.3ds)\
+    \ 3D meshes that can be loaded and used as objects by some effects. • Video cue\
+    \ points - Set up\nto 70 cue points in the video by entering a list of time-offsets\
+    \ in seconds (including decimals if needed). The simplest way to add a video is\
+    \ by selecting ' Image Effects > Image ' from the list and choosing the Video\
+    \ from the Img Src menu. ➤ Setup - Match the MIDI IN Port on the Settings tab\
+    \ to\na [MIDI Out](https://www.image-line.com/fl-studio-learning/fl-studio-online-manual/html/MIDI%20Out.htm)\
+    \ Port (and Channel). ➤ Trigger cue points - Notes played on the MIDI Out Channel\
+    \ will trigger playback from the set cue points. Cue-points start from note C5\
+    \ (C5 = the first cue-point in the\nlist) and are mapped progressively to each\
+    \ cue-point down the list as you progress up the keyboard. ➤ Special functions\
+    \ - You can put the cue points play and stop anywhere in the list."
+  - "Document_title: Harmor \nFile_name: plugins/Harmor.htm\nHeading_hierarchy: [Harmor\
+    \ -> Filter]\nAnchor_id: [none]\nThe filter functions control the type of filtering\
+    \ and cutoff frequency. • ENV - Envelope modulation amount. The knob is bi-directional\
+    \ from -100 to +100%. ➤ adapt - Adaptive envelope mode. The bandwidth of the filter\
+    \ changes width as a function of the notes frequency, so that the duration of\n\
+    envelopes applied to low vs high notes sound similar in duration. Set by ear.\
+    \ • oct / Hz - Sets the shape of the resonance frequency peak to an Octave or\
+    \ Hertz scale. Set by ear. • kb track - Keyboard tracking. Applies an offset to\
+    \ the filter cutoff value depending on pitch. The offset-value can be\npositive\
+    \ or negative depending on the direction of the knob. For  example, keyboard tracking\
+    \ is useful to make a sound brighter,\n    by raising the cutoff frequency of\
+    \ a low-pass filter, as higher keys are played. • width - Filter bandwidth, equivalent\
+    \ to 'dB/Octave' setting on traditional filters. Narrower widths create a more\
+    \ clearly defined 'center frequency' or 'cut' frequency. • FREQ - Filter cutoff\
+    \ frequency. This is the\ntarget for all controls in green to the left of the\
+    \ knob. • Filter type menu - Choose from cutoff slope variations, Crude & Hill\
+    \ being the steepest: ➤ Low pass - Filters frequencies above the cutoff frequency.\
+    \ ➤ Band pass - Filters frequencies either side of a central band. ➤ Band stop\
+    \ - Filters\nfrequencies inside a central band. ➤ High pass - Filters frequencies\
+    \ below the cutoff frequency. ➤ Phaser - 'Comb filtering', a series of stacked\
+    \ band-stop filers. ➤ Custom shape 1 & 2 - Define your own filter shape with ENV\
+    \ 'Filter shape 1 & 2' envelopes. • Filter 1 & 2 mix - Filter resonance\nsections\
+    \ can operate in parallel or series depending on the position of the knob (see\
+    \ below). Consider the percentage like the mix between Filter 1 and 2. When parallel\
+    \ it's the mix of both filters to the output. When serial its the mix of Filter\
+    \ 1 directly to the output or into Filter 2. ➤ Left of 12\nO'Clock = (1-Mix) *\
+    \ F1 + Mix * F2 ➤ Right of 12 O'Clock = (1-Mix) * F1 + Mix * (F1⇒F2) Where: ◆\
+    \ F1 is the output of Filter 1 ◆ F2 is the output of Filter 2 ◆ F1⇒F2 is the output\
+    \ of F1 processed by F2 ◆ Mix is the value of the Filter 1 & 2 mix knob TIP: If\
+    \ [Units](https://www.image-line.com/fl-studio\n-learning/fl-studio-online-manual/html/Harmor.htm#harmor_adv)\
+    \ are placed after F1, then F1 becomes  F1 + following units. • RES - Filter resonance.\
+    \ This boosts frequencies around the cutoff value (depending on the offset value\
+    \ ). Resonance accentuates the cutoff frequency position making\na familiar 'resonant'\
+    \ sound. • Resonance type menu - Choose from resonance type variations: ➤ Classic\
+    \ - Single narrow resonance peak. ➤ Cuberdon, Pedestal, Sedge hat, Wide bump,\
+    \ Double cone - Various resonance peak shapes, named according to their approximate\
+    \ shape. ➤ Well &\nWormhole - Cut frequencies at the cutoff frequency with resonant\
+    \ peaks either side of the hole. These settings are designed to be used with the\
+    \ self-oscillation,\n        to avoid annoying interferences and overly loud \
+    \ ringing when the resonance peak passes harmonic frequencies. ➤ Noise - Special\
+    \ effect. Harmonics are sounded randomly. Use the RES to control the amount of\
+    \ randomness, width controls the length/duration of changes in harmonics. ➤ C\n\
+    ustom shape 1 & 2 - Define your own resonance filter shape with  'Filter (resonance)\
+    \ shape 1 & 2' envelopes. ➤ Low pass - Provides a resonance peak followed by a\
+    \ dip, this makes it an 'extra lowpass', so that the slope of the lowpass filter\
+    \ effectively becomes steeper as the resonance\nincreases. • width - Resonance\
+    \ peak width, left = narrow, right = wide. ➤ adapt - Adaptive envelope mode. The\
+    \ bandwidth of the filter changes width as a function of the notes frequency,\
+    \ so that the resonance sounds similar regardless of the note pitch. Set by ear."
+  - "Document_title: Drumaxx - Percussion Modeling Instrument \nFile_name: plugins/Drumaxx.htm\n\
+    Heading_hierarchy: [Drumaxx - Percussion Modeling Instrument -> Membrane]\nAnchor_id:\
+    \ [none]\nThe drum membrane (skin) has a significant impact on the tonal character\
+    \ of the final sound. There are 4 key parameters - Tension , Phase , Material\
+    \ and Shape .\n    When the right balance between these four controls is achieved,\
+    \ the sound will be most natural. We recommend adjusting Tension and Phase first,\
+    \ so that the pitch is close to\n    what you need. Then adjust Material and Shape\
+    \ to fine-tune the tonal qualities. If the balance is right, the Drum Pad will\
+    \ sound like a drum, and if not, the Drum Pad can sound 'blurry' and 'loose'.\
+    \ • Decay - Decay time for the membrane response and reflections. • Tension -\
+    \ Membrane\ntension (how tightly stretched the drum is). • Material - This control\
+    \ moves the membrane material through a range of possible characteristics and\
+    \ types. Generally left are heavier slower materials and right are \n      lighter\
+    \ more reflective materials. Set by ear. • Cutoff - High frequency cutoff. • Phase\
+    \ - Relates to the impact-point on the drum-head. Set by ear. • Size - Drum-head\
+    \ size. • Shape - The shape can be varied from square (left) to round (right).\
+    \ Most drum-heads are round, but experimentation\nis always rewarded!"
+- source_sentence: Explain how the "Time mul" and "PAN" controls in the Riff Machine
+    options can affect a musical progression. Provide examples of scenarios where
+    these controls would be particularly useful.
+  sentences:
+  - "Document_title: Layer Settings\nFile_name: chansettings_layer.htm\nHeading_hierarchy:\
+    \ [Layer Settings -> Options]\nAnchor_id: [none]\n• Levels Adjustment - This section\
+    \ contains controls for the volume (VOL) , panning (PAN) and Pitch of the linked\
+    \ layers. NOTE: The levels you set in the Layer Channel apply ONLY to the notes\
+    \ played through that layer. If you play a child of this Channel through \n  \
+    \      its own [Step Sequencer](https://www.image-line.com/fl-studio-learning/fl-studio-online-manual/html/channelrack.htm)\
+    \ dots or [Piano roll](https://www.image-line.com/fl-studio-learning/fl-studio-online-manual/html/pianoroll.htm)\
+    \ , these settings will not be applied. • Layering section ➤ Set\nchildren - Assigns\
+    \ all selected Channels in the [Step Sequencer](https://www.image-line.com/fl-studio-learning/fl-studio-online-manual/html/channelrack.htm)\
+    \ as children in this Layer Channel. When you\n          play a note on the Layer\
+    \ Channel, all the children play along. To unassign a Channel from the Layer Channel,\
+    \ select all the Channels you want to remain \n          as children and press\
+    \ the Set children button again (all unselected Channels become unassigned for\
+    \ this Layer Channel). ➤ Show children - Selects all Channels that are children\
+    \ of this Layer Channel in the Step Sequencer, and deselects all other Channels.\
+    \ ➤ Random - OFF: All children of\nthe Layer Channel will sound on each note.\
+    \ ON: A single, random, Channel in the Layer will play. Use the 'Random' feature\n\
+    \          to make more interesting percussion sounds, for example, by assigning\
+    \ many similar samples to each Channel in the Layer. This will give subtle variations\
+    \ on\n          each repeated note. ➤ Crossfade - ON: The Fade knob (below) will\
+    \ crossfade between two or more Channels in the Layer. ◆ Fade knob - Used to set\
+    \ the crossfade level in crossfade mode. For example; If you have 3 Layer Channels\
+    \ turning the Fade knob from left to right will \n          sound: Child 1 > Child\
+    \ 1 + Child 2 > Child 2 > Child 2 + Child 3 > Child 3 . Channels are faded from\
+    \ top (knob left) to bottom (knob right) in the Channel Rack. NOTE: Crossfading\
+    \ only works with\n          FL Studio native format plugins, it does not work\
+    \ with VST/AU  plugins. • Sequential - ON: Each Channel will play in turn (round-robbin\
+    \ style) starting with the highest Channel working to the lowest when the ' Set\
+    \ children ' function was used. NOTE: The system remembers the Channel\norder\
+    \ when 'Set children' was used. To re-order the sequence, rearrange your Channels\
+    \ and reapply 'Set children'. • Layering menu - Click on the small arrow at the\
+    \ top left of this panel you can access some additional commands: ➤ Split children\
+    \ - Splits the children of the Layer Channel across\nthe keyboard (starting with\
+    \ the root key of the Layer Channel), assigning each layer to a single key. The\
+    \ root keys of the children are automatically adjusted, so that the correct pitch\
+    \ is played through the Layer Channel. This feature is useful for creating drum\
+    \ kits or instruments where each\nnote has different sample. ➤ Reset children\
+    \ - Resets the range and root notes for all Child Channels of a layer. Basically\
+    \ undoes the ' Split children ' actions. ➤ Group children - Adds all children\
+    \ of the Layer Channel to a group (a popup window will appear to enter the name\
+    \ of the group). For\nmore information see the Channel Filtering section in the\
+    \ [Step Sequencer](https://www.image-line.com/fl-studio-learning/fl-studio-online-manual/html/channelrack.htm)\
+    \ page. ➤ Delete children - Removes selected children from the layer. • Preview\
+    \ Keyboard - The preview keyboard allows you\nto preview the Channel instrument\
+    \ (Left-clicking on the piano-keyboard), set the root key (Right-Click a key),\
+    \ and set key region (Left-click and drag on the ruler). See the [Miscellaneous\
+    \ Channel\nSettings](https://www.image-line.com/fl-studio-learning/fl-studio-online-manual/html/chansettings_misc.htm)\
+    \ page for more information on using the Preview Keyboard."
+  - 'Document_title: Maximus Flow Diagram & Tutorials
+
+    File_name: plugins/Maximus_Tutorials.htm
+
+    Heading_hierarchy: [Maximus Flow Diagram & Tutorials -> Inversion]
+
+    Anchor_id: [none]
+
+    Inversion flips the volume, loud signals become quiet, and quiet signals become
+    loud.'
+  - "Document_title: Riff Machine  \nFile_name: pianoroll_riff_prog.htm\nHeading_hierarchy:\
+    \ [Riff Machine -> Options]\nAnchor_id: [none]\nThese controls augment/modify\
+    \ the selected progression. Note that some controls will only have an effect if\
+    \ the original progression includes some variation in that parameter (PAN for\
+    \ example). • Time mul - Time multiplier, change the length of the notes. • PAN\
+    \ - Note panning multiplier. • VO\nL (Volume) - Note velocity multiplier. • MODX\
+    \ - Modulation X multiplier. • MODY - Modulation Y multiplier. • PITCH - Note\
+    \ pitch multiplier. • Absolute Pattern - On: any note slicing is based on the\
+    \ Piano roll grid. Off: Each note is sliced relative to its own start time. •\
+    \ Group notes - Groups any\nchopped-up notes, use the [grouping](https://www.image-line.com/fl-studio-learning/fl-studio-online-manual/html/toolbar_panels.htm#panel_shortcuticons_group)\
+    \ function on the [Toobar shortcut\nicons](https://www.image-line.com/fl-studio-learning/fl-studio-online-manual/html/toolbar_panels.htm#panel_shortcuticons)\
+    \ to activate note grouping. [Step 2. Chord Progression](https://www.image-line.com/fl-studio-learning/fl-studio-online-manual/html/pianoroll_riff_chord.htm#Riff_Chord)\
+    \ [St\nep 3. Arpeggiation](https://www.image-line.com/fl-studio-learning/fl-studio-online-manual/html/pianoroll_riff_arp.htm#Riff_Arp)\
+    \ [Step 4. Mirroring Notes](https://www.image-line.com/fl-studio-learning/fl-studio-online-manual/html/pianoroll_riff_mirror.htm#Riff_Mirror)\
+    \ [Step 5. Levels &\nPanning](https://www.image-line.com/fl-studio-learning/fl-studio-online-manual/html/pianoroll_riff_levels.htm#Riff_Levels)\
+    \ [Step 6. Articulation (note length)](https://www.image-line.com/fl-studio-learning/fl-studio-online-manual/html/pianoroll_riff_art.htm#Riff_Art)\
+    \ [Step 7. Groove (note\ntiming)](https://www.image-line.com/fl-studio-learning/fl-studio-online-manual/html/pianoroll_riff_groove.htm#Riff_Groove)\
+    \ [Step 8. Fit (note range)](https://www.image-line.com/fl-studio-learning/fl-studio-online-manual/html/pianoroll_riff_fit.htm#Riff_Fit)"
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy@1
+- cosine_accuracy@3
+- cosine_accuracy@5
+- cosine_accuracy@10
+- cosine_precision@1
+- cosine_precision@3
+- cosine_precision@5
+- cosine_precision@10
+- cosine_recall@1
+- cosine_recall@3
+- cosine_recall@5
+- cosine_recall@10
+- cosine_ndcg@10
+- cosine_mrr@10
+- cosine_map@100
+model-index:
+- name: SentenceTransformer based on BAAI/bge-base-en
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: Unknown
+      type: unknown
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.8474930362116991
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.9498607242339833
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9707520891364902
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9832869080779945
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.8474930362116991
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.3166202414113278
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.19415041782729803
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09832869080779943
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.8474930362116991
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.9498607242339833
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.9707520891364902
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9832869080779945
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.9211483862525699
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.9005573794048727
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.9013471154221424
+      name: Cosine Map@100
+---
+
+# SentenceTransformer based on BAAI/bge-base-en
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-base-en](https://huggingface.co/BAAI/bge-base-en). It maps sentences & paragraphs to a 768-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:** [BAAI/bge-base-en](https://huggingface.co/BAAI/bge-base-en) <!-- at revision b737bf5dcc6ee8bdc530531266b4804a5d77b5d8 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 dimensions
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 768, '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})
+  (2): Normalize()
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'Explain how the "Time mul" and "PAN" controls in the Riff Machine options can affect a musical progression. Provide examples of scenarios where these controls would be particularly useful.',
+    'Document_title: Riff Machine  \nFile_name: pianoroll_riff_prog.htm\nHeading_hierarchy: [Riff Machine -> Options]\nAnchor_id: [none]\nThese controls augment/modify the selected progression. Note that some controls will only have an effect if the original progression includes some variation in that parameter (PAN for example). • Time mul - Time multiplier, change the length of the notes. • PAN - Note panning multiplier. • VO\nL (Volume) - Note velocity multiplier. • MODX - Modulation X multiplier. • MODY - Modulation Y multiplier. • PITCH - Note pitch multiplier. • Absolute Pattern - On: any note slicing is based on the Piano roll grid. Off: Each note is sliced relative to its own start time. • Group notes - Groups any\nchopped-up notes, use the [grouping](https://www.image-line.com/fl-studio-learning/fl-studio-online-manual/html/toolbar_panels.htm#panel_shortcuticons_group) function on the [Toobar shortcut\nicons](https://www.image-line.com/fl-studio-learning/fl-studio-online-manual/html/toolbar_panels.htm#panel_shortcuticons) to activate note grouping. [Step 2. Chord Progression](https://www.image-line.com/fl-studio-learning/fl-studio-online-manual/html/pianoroll_riff_chord.htm#Riff_Chord) [St\nep 3. Arpeggiation](https://www.image-line.com/fl-studio-learning/fl-studio-online-manual/html/pianoroll_riff_arp.htm#Riff_Arp) [Step 4. Mirroring Notes](https://www.image-line.com/fl-studio-learning/fl-studio-online-manual/html/pianoroll_riff_mirror.htm#Riff_Mirror) [Step 5. Levels &\nPanning](https://www.image-line.com/fl-studio-learning/fl-studio-online-manual/html/pianoroll_riff_levels.htm#Riff_Levels) [Step 6. Articulation (note length)](https://www.image-line.com/fl-studio-learning/fl-studio-online-manual/html/pianoroll_riff_art.htm#Riff_Art) [Step 7. Groove (note\ntiming)](https://www.image-line.com/fl-studio-learning/fl-studio-online-manual/html/pianoroll_riff_groove.htm#Riff_Groove) [Step 8. Fit (note range)](https://www.image-line.com/fl-studio-learning/fl-studio-online-manual/html/pianoroll_riff_fit.htm#Riff_Fit)',
+    "Document_title: Layer Settings\nFile_name: chansettings_layer.htm\nHeading_hierarchy: [Layer Settings -> Options]\nAnchor_id: [none]\n• Levels Adjustment - This section contains controls for the volume (VOL) , panning (PAN) and Pitch of the linked layers. NOTE: The levels you set in the Layer Channel apply ONLY to the notes played through that layer. If you play a child of this Channel through \n        its own [Step Sequencer](https://www.image-line.com/fl-studio-learning/fl-studio-online-manual/html/channelrack.htm) dots or [Piano roll](https://www.image-line.com/fl-studio-learning/fl-studio-online-manual/html/pianoroll.htm) , these settings will not be applied. • Layering section ➤ Set\nchildren - Assigns all selected Channels in the [Step Sequencer](https://www.image-line.com/fl-studio-learning/fl-studio-online-manual/html/channelrack.htm) as children in this Layer Channel. When you\n          play a note on the Layer Channel, all the children play along. To unassign a Channel from the Layer Channel, select all the Channels you want to remain \n          as children and press the Set children button again (all unselected Channels become unassigned for this Layer Channel). ➤ Show children - Selects all Channels that are children of this Layer Channel in the Step Sequencer, and deselects all other Channels. ➤ Random - OFF: All children of\nthe Layer Channel will sound on each note. ON: A single, random, Channel in the Layer will play. Use the 'Random' feature\n          to make more interesting percussion sounds, for example, by assigning many similar samples to each Channel in the Layer. This will give subtle variations on\n          each repeated note. ➤ Crossfade - ON: The Fade knob (below) will crossfade between two or more Channels in the Layer. ◆ Fade knob - Used to set the crossfade level in crossfade mode. For example; If you have 3 Layer Channels turning the Fade knob from left to right will \n          sound: Child 1 > Child 1 + Child 2 > Child 2 > Child 2 + Child 3 > Child 3 . Channels are faded from top (knob left) to bottom (knob right) in the Channel Rack. NOTE: Crossfading only works with\n          FL Studio native format plugins, it does not work with VST/AU  plugins. • Sequential - ON: Each Channel will play in turn (round-robbin style) starting with the highest Channel working to the lowest when the ' Set children ' function was used. NOTE: The system remembers the Channel\norder when 'Set children' was used. To re-order the sequence, rearrange your Channels and reapply 'Set children'. • Layering menu - Click on the small arrow at the top left of this panel you can access some additional commands: ➤ Split children - Splits the children of the Layer Channel across\nthe keyboard (starting with the root key of the Layer Channel), assigning each layer to a single key. The root keys of the children are automatically adjusted, so that the correct pitch is played through the Layer Channel. This feature is useful for creating drum kits or instruments where each\nnote has different sample. ➤ Reset children - Resets the range and root notes for all Child Channels of a layer. Basically undoes the ' Split children ' actions. ➤ Group children - Adds all children of the Layer Channel to a group (a popup window will appear to enter the name of the group). For\nmore information see the Channel Filtering section in the [Step Sequencer](https://www.image-line.com/fl-studio-learning/fl-studio-online-manual/html/channelrack.htm) page. ➤ Delete children - Removes selected children from the layer. • Preview Keyboard - The preview keyboard allows you\nto preview the Channel instrument (Left-clicking on the piano-keyboard), set the root key (Right-Click a key), and set key region (Left-click and drag on the ruler). See the [Miscellaneous Channel\nSettings](https://www.image-line.com/fl-studio-learning/fl-studio-online-manual/html/chansettings_misc.htm) page for more information on using the Preview Keyboard.",
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Information Retrieval
+
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.8475     |
+| cosine_accuracy@3   | 0.9499     |
+| cosine_accuracy@5   | 0.9708     |
+| cosine_accuracy@10  | 0.9833     |
+| cosine_precision@1  | 0.8475     |
+| cosine_precision@3  | 0.3166     |
+| cosine_precision@5  | 0.1942     |
+| cosine_precision@10 | 0.0983     |
+| cosine_recall@1     | 0.8475     |
+| cosine_recall@3     | 0.9499     |
+| cosine_recall@5     | 0.9708     |
+| cosine_recall@10    | 0.9833     |
+| **cosine_ndcg@10**  | **0.9211** |
+| cosine_mrr@10       | 0.9006     |
+| cosine_map@100      | 0.9013     |
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Dataset
+
+#### Unnamed Dataset
+
+
+* Size: 5,776 training samples
+* Columns: <code>sentence_0</code> and <code>sentence_1</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence_0                                                                         | sentence_1                                                                           |
+  |:--------|:-----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                               |
+  | details | <ul><li>min: 12 tokens</li><li>mean: 33.33 tokens</li><li>max: 66 tokens</li></ul> | <ul><li>min: 37 tokens</li><li>mean: 278.56 tokens</li><li>max: 512 tokens</li></ul> |
+* Samples:
+  | sentence_0                                                                                                                                                                                                    | sentence_1                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     |
+  |:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>Explain the issue that arises with project names in FL Studio 20 when using non-English characters, and describe the steps needed to resolve this issue on a Windows 10 system.</code>                  | <code>Title: Projects names are not showing correctly. Names in non-english characters (Cyrillic Korean, Japanese, Chinese, Hindi, Thai, etc.).<br>Answer: FL Studio 20 works in unicode and displays in Windows 10 automatically your local character set. However, for projects moved from older FL Studio program versions, FL Studio does not know the character set it needs to display. Language not set up correctly: Your FL Studio 20 program will look like this: Solution: correct language set up instructions: A. Please check this [Windows support article](https://answers.microsoft.com/en-us/surface/forum/surfbook-surfaccess/how-to-change-system-locale-in-windows-10-the/d7826ef0-13cd-43ea-8e01-2846d813dfed): Follow the steps<br>below to set up non-unicode language in windows 10 1. In search tab type "Region" and press enter. 2. In new window select "Administrative" 3. then click on "change system locale" 4. Select the language. B. Import your old projects again into FL Studio 20. The names will now show u...</code> |
+  | <code>Discuss the importance of setting the correct language settings in FL Studio 20 for displaying project names accurately, especially when importing projects from older versions of the software.</code> | <code>Title: Projects names are not showing correctly. Names in non-english characters (Cyrillic Korean, Japanese, Chinese, Hindi, Thai, etc.).<br>Answer: FL Studio 20 works in unicode and displays in Windows 10 automatically your local character set. However, for projects moved from older FL Studio program versions, FL Studio does not know the character set it needs to display. Language not set up correctly: Your FL Studio 20 program will look like this: Solution: correct language set up instructions: A. Please check this [Windows support article](https://answers.microsoft.com/en-us/surface/forum/surfbook-surfaccess/how-to-change-system-locale-in-windows-10-the/d7826ef0-13cd-43ea-8e01-2846d813dfed): Follow the steps<br>below to set up non-unicode language in windows 10 1. In search tab type "Region" and press enter. 2. In new window select "Administrative" 3. then click on "change system locale" 4. Select the language. B. Import your old projects again into FL Studio 20. The names will now show u...</code> |
+  | <code>How can you toggle the visibility of the FL Studio window when using it as a ReWire client within Cubase SX™?</code>                                                                                    | <code>Document_title: Using FL Studio ReWire with Cubase SX™ <br>File_name: rewire_client_cubase.htm<br>Heading_hierarchy: [Using FL Studio ReWire with Cubase SX™ -> 5. Toggle the FL Studio window visibility]<br>Anchor_id: [none]<br>Clicking the FL Studio icon toggles the visibility of the FL Studio window inside Cubase™. If you need to hide the FL Studio window, use the close button in the FL Studio window (this will not terminate the current session) or click the icon button<br>  on the FL Studio ReWire panel. To display the window later, click the icon button again.</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                         |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 10
+- `per_device_eval_batch_size`: 10
+- `num_train_epochs`: 2
+- `multi_dataset_batch_sampler`: round_robin
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 10
+- `per_device_eval_batch_size`: 10
+- `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`: 2
+- `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`: False
+- `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
+- `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
+- `dispatch_batches`: None
+- `split_batches`: 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
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: round_robin
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | cosine_ndcg@10 |
+|:------:|:----:|:-------------:|:--------------:|
+| 0.0865 | 50   | -             | 0.9006         |
+| 0.1730 | 100  | -             | 0.8944         |
+| 0.2595 | 150  | -             | 0.8924         |
+| 0.3460 | 200  | -             | 0.8996         |
+| 0.4325 | 250  | -             | 0.9016         |
+| 0.5190 | 300  | -             | 0.9021         |
+| 0.6055 | 350  | -             | 0.9071         |
+| 0.6920 | 400  | -             | 0.9112         |
+| 0.7785 | 450  | -             | 0.9132         |
+| 0.8651 | 500  | 0.1068        | 0.9139         |
+| 0.9516 | 550  | -             | 0.9181         |
+| 1.0    | 578  | -             | 0.9153         |
+| 1.0381 | 600  | -             | 0.9126         |
+| 1.1246 | 650  | -             | 0.9156         |
+| 1.2111 | 700  | -             | 0.9150         |
+| 1.2976 | 750  | -             | 0.9161         |
+| 1.3841 | 800  | -             | 0.9159         |
+| 1.4706 | 850  | -             | 0.9189         |
+| 1.5571 | 900  | -             | 0.9174         |
+| 1.6436 | 950  | -             | 0.9206         |
+| 1.7301 | 1000 | 0.0144        | 0.9185         |
+| 1.8166 | 1050 | -             | 0.9197         |
+| 1.9031 | 1100 | -             | 0.9211         |
+
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.3.1
+- Transformers: 4.47.1
+- PyTorch: 2.5.1+cu121
+- Accelerate: 1.2.1
+- Datasets: 3.2.0
+- Tokenizers: 0.21.0
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@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
+```bibtex
+@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}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "BAAI/bge-base-en",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.3.1",
+    "transformers": "4.47.1",
+    "pytorch": "2.5.1+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a28d13f7778810fe9ab069f5388ca421cf0695856695429ea6fc5020c1def9a7
+size 437951328

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": true
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}