You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.

index.html 35 kB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890891892893894895896897898899900901902903904905906907908909910911912913914915916917918919920921922923924925926927928929930931932933934935936937938939940941942943944945946947948949950951952953954955956957958959960961962963964965966967968969970971972973974975976977978979980981982983984985986987988989990991992993994995996997998999100010011002100310041005100610071008100910101011101210131014101510161017101810191020102110221023102410251026102710281029103010311032103310341035103610371038103910401041104210431044104510461047104810491050105110521053105410551056105710581059106010611062106310641065106610671068106910701071107210731074107510761077107810791080108110821083108410851086108710881089109010911092109310941095109610971098109911001101110211031104110511061107110811091110111111121113111411151116111711181119112011211122112311241125112611271128112911301131113211331134113511361137113811391140114111421143114411451146114711481149115011511152115311541155115611571158115911601161116211631164116511661167116811691170117111721173117411751176117711781179118011811182118311841185118611871188118911901191119211931194119511961197119811991200120112021203120412051206120712081209121012111212121312141215121612171218121912201221122212231224122512261227122812291230123112321233123412351236123712381239124012411242124312441245124612471248124912501251125212531254125512561257125812591260126112621263126412651266126712681269127012711272127312741275127612771278127912801281128212831284128512861287128812891290129112921293129412951296129712981299130013011302130313041305130613071308130913101311131213131314131513161317131813191320132113221323132413251326132713281329133013311332133313341335133613371338133913401341134213431344134513461347134813491350135113521353135413551356135713581359136013611362136313641365136613671368136913701371137213731374137513761377137813791380138113821383138413851386138713881389139013911392139313941395139613971398139914001401140214031404140514061407140814091410141114121413141414151416141714181419142014211422142314241425142614271428142914301431143214331434143514361437143814391440144114421443144414451446144714481449145014511452145314541455145614571458145914601461146214631464146514661467146814691470147114721473147414751476147714781479148014811482148314841485148614871488148914901491149214931494149514961497149814991500150115021503150415051506150715081509151015111512151315141515151615171518151915201521152215231524152515261527152815291530153115321533153415351536153715381539154015411542154315441545154615471548154915501551155215531554155515561557155815591560156115621563156415651566156715681569157015711572157315741575157615771578157915801581158215831584158515861587158815891590159115921593159415951596159715981599160016011602160316041605160616071608160916101611161216131614161516161617161816191620162116221623162416251626162716281629163016311632163316341635163616371638163916401641164216431644164516461647164816491650165116521653165416551656165716581659166016611662166316641665166616671668166916701671167216731674167516761677167816791680168116821683168416851686168716881689169016911692169316941695169616971698169917001701170217031704170517061707170817091710171117121713171417151716171717181719172017211722172317241725172617271728172917301731173217331734173517361737173817391740174117421743174417451746
  1. <!doctype html>
  2. <html lang="en" class="no-js">
  3. <head>
  4. <meta charset="utf-8">
  5. <meta name="viewport" content="width=device-width,initial-scale=1">
  6. <link rel="prev" href="../LoadAndSaveState/">
  7. <link rel="next" href="../../xmldocs/">
  8. <link rel="icon" href="../../assets/images/favicon.png">
  9. <meta name="generator" content="mkdocs-1.4.3, mkdocs-material-9.1.16">
  10. <title>Quantize model - LLamaSharp Documentation</title>
  11. <link rel="stylesheet" href="../../assets/stylesheets/main.26e3688c.min.css">
  12. <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
  13. <link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Roboto:300,300i,400,400i,700,700i%7CRoboto+Mono:400,400i,700,700i&display=fallback">
  14. <style>:root{--md-text-font:"Roboto";--md-code-font:"Roboto Mono"}</style>
  15. <script>__md_scope=new URL("../..",location),__md_hash=e=>[...e].reduce((e,_)=>(e<<5)-e+_.charCodeAt(0),0),__md_get=(e,_=localStorage,t=__md_scope)=>JSON.parse(_.getItem(t.pathname+"."+e)),__md_set=(e,_,t=localStorage,a=__md_scope)=>{try{t.setItem(a.pathname+"."+e,JSON.stringify(_))}catch(e){}}</script>
  16. </head>
  17. <body dir="ltr">
  18. <script>var palette=__md_get("__palette");if(palette&&"object"==typeof palette.color)for(var key of Object.keys(palette.color))document.body.setAttribute("data-md-color-"+key,palette.color[key])</script>
  19. <input class="md-toggle" data-md-toggle="drawer" type="checkbox" id="__drawer" autocomplete="off">
  20. <input class="md-toggle" data-md-toggle="search" type="checkbox" id="__search" autocomplete="off">
  21. <label class="md-overlay" for="__drawer"></label>
  22. <div data-md-component="skip">
  23. <a href="#quantize-model" class="md-skip">
  24. Skip to content
  25. </a>
  26. </div>
  27. <div data-md-component="announce">
  28. </div>
  29. <div data-md-color-scheme="default" data-md-component="outdated" hidden>
  30. </div>
  31. <header class="md-header md-header--shadow" data-md-component="header">
  32. <nav class="md-header__inner md-grid" aria-label="Header">
  33. <a href="../.." title="LLamaSharp Documentation" class="md-header__button md-logo" aria-label="LLamaSharp Documentation" data-md-component="logo">
  34. <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54Z"/></svg>
  35. </a>
  36. <label class="md-header__button md-icon" for="__drawer">
  37. <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M3 6h18v2H3V6m0 5h18v2H3v-2m0 5h18v2H3v-2Z"/></svg>
  38. </label>
  39. <div class="md-header__title" data-md-component="header-title">
  40. <div class="md-header__ellipsis">
  41. <div class="md-header__topic">
  42. <span class="md-ellipsis">
  43. LLamaSharp Documentation
  44. </span>
  45. </div>
  46. <div class="md-header__topic" data-md-component="header-topic">
  47. <span class="md-ellipsis">
  48. Quantize model
  49. </span>
  50. </div>
  51. </div>
  52. </div>
  53. <label class="md-header__button md-icon" for="__search">
  54. <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.516 6.516 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5Z"/></svg>
  55. </label>
  56. <div class="md-search" data-md-component="search" role="dialog">
  57. <label class="md-search__overlay" for="__search"></label>
  58. <div class="md-search__inner" role="search">
  59. <form class="md-search__form" name="search">
  60. <input type="text" class="md-search__input" name="query" aria-label="Search" placeholder="Search" autocapitalize="off" autocorrect="off" autocomplete="off" spellcheck="false" data-md-component="search-query" required>
  61. <label class="md-search__icon md-icon" for="__search">
  62. <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.516 6.516 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5Z"/></svg>
  63. <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M20 11v2H8l5.5 5.5-1.42 1.42L4.16 12l7.92-7.92L13.5 5.5 8 11h12Z"/></svg>
  64. </label>
  65. <nav class="md-search__options" aria-label="Search">
  66. <button type="reset" class="md-search__icon md-icon" title="Clear" aria-label="Clear" tabindex="-1">
  67. <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M19 6.41 17.59 5 12 10.59 6.41 5 5 6.41 10.59 12 5 17.59 6.41 19 12 13.41 17.59 19 19 17.59 13.41 12 19 6.41Z"/></svg>
  68. </button>
  69. </nav>
  70. </form>
  71. <div class="md-search__output">
  72. <div class="md-search__scrollwrap" data-md-scrollfix>
  73. <div class="md-search-result" data-md-component="search-result">
  74. <div class="md-search-result__meta">
  75. Initializing search
  76. </div>
  77. <ol class="md-search-result__list" role="presentation"></ol>
  78. </div>
  79. </div>
  80. </div>
  81. </div>
  82. </div>
  83. </nav>
  84. </header>
  85. <div class="md-container" data-md-component="container">
  86. <main class="md-main" data-md-component="main">
  87. <div class="md-main__inner md-grid">
  88. <div class="md-sidebar md-sidebar--primary" data-md-component="sidebar" data-md-type="navigation" >
  89. <div class="md-sidebar__scrollwrap">
  90. <div class="md-sidebar__inner">
  91. <nav class="md-nav md-nav--primary" aria-label="Navigation" data-md-level="0">
  92. <label class="md-nav__title" for="__drawer">
  93. <a href="../.." title="LLamaSharp Documentation" class="md-nav__button md-logo" aria-label="LLamaSharp Documentation" data-md-component="logo">
  94. <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54Z"/></svg>
  95. </a>
  96. LLamaSharp Documentation
  97. </label>
  98. <ul class="md-nav__list" data-md-scrollfix>
  99. <li class="md-nav__item">
  100. <a href="../.." class="md-nav__link">
  101. Overview
  102. </a>
  103. </li>
  104. <li class="md-nav__item">
  105. <a href="../../GetStarted/" class="md-nav__link">
  106. Get Started
  107. </a>
  108. </li>
  109. <li class="md-nav__item">
  110. <a href="../../Architecture/" class="md-nav__link">
  111. Architecture
  112. </a>
  113. </li>
  114. <li class="md-nav__item">
  115. <a href="../../Tricks/" class="md-nav__link">
  116. Tricks for FAQ
  117. </a>
  118. </li>
  119. <li class="md-nav__item">
  120. <a href="../../ContributingGuide/" class="md-nav__link">
  121. Contributing Guide
  122. </a>
  123. </li>
  124. <li class="md-nav__item md-nav__item--nested">
  125. <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_6" >
  126. <label class="md-nav__link" for="__nav_6" id="__nav_6_label" tabindex="0">
  127. LLamaModel
  128. <span class="md-nav__icon md-icon"></span>
  129. </label>
  130. <nav class="md-nav" data-md-level="1" aria-labelledby="__nav_6_label" aria-expanded="false">
  131. <label class="md-nav__title" for="__nav_6">
  132. <span class="md-nav__icon md-icon"></span>
  133. LLamaModel
  134. </label>
  135. <ul class="md-nav__list" data-md-scrollfix>
  136. <li class="md-nav__item">
  137. <a href="../../LLamaModel/parameters/" class="md-nav__link">
  138. Model Parameters
  139. </a>
  140. </li>
  141. <li class="md-nav__item">
  142. <a href="../../LLamaModel/tokenization/" class="md-nav__link">
  143. Tokenization
  144. </a>
  145. </li>
  146. <li class="md-nav__item">
  147. <a href="../../LLamaModel/embeddings/" class="md-nav__link">
  148. Get Embeddings
  149. </a>
  150. </li>
  151. <li class="md-nav__item">
  152. <a href="../../LLamaModel/quantization/" class="md-nav__link">
  153. Quantization
  154. </a>
  155. </li>
  156. <li class="md-nav__item">
  157. <a href="../../LLamaModel/save-load-state/" class="md-nav__link">
  158. Save/Load State
  159. </a>
  160. </li>
  161. </ul>
  162. </nav>
  163. </li>
  164. <li class="md-nav__item md-nav__item--nested">
  165. <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_7" >
  166. <label class="md-nav__link" for="__nav_7" id="__nav_7_label" tabindex="0">
  167. LLamaExecutors
  168. <span class="md-nav__icon md-icon"></span>
  169. </label>
  170. <nav class="md-nav" data-md-level="1" aria-labelledby="__nav_7_label" aria-expanded="false">
  171. <label class="md-nav__title" for="__nav_7">
  172. <span class="md-nav__icon md-icon"></span>
  173. LLamaExecutors
  174. </label>
  175. <ul class="md-nav__list" data-md-scrollfix>
  176. <li class="md-nav__item">
  177. <a href="../../LLamaExecutors/parameters/" class="md-nav__link">
  178. Inference Parameters
  179. </a>
  180. </li>
  181. <li class="md-nav__item">
  182. <a href="../../LLamaExecutors/text-to-text-apis/" class="md-nav__link">
  183. Text-to-Text APIs
  184. </a>
  185. </li>
  186. <li class="md-nav__item">
  187. <a href="../../LLamaExecutors/save-load-state/" class="md-nav__link">
  188. Save/Load State
  189. </a>
  190. </li>
  191. <li class="md-nav__item">
  192. <a href="../../LLamaExecutors/differences/" class="md-nav__link">
  193. Differences of Executors
  194. </a>
  195. </li>
  196. </ul>
  197. </nav>
  198. </li>
  199. <li class="md-nav__item md-nav__item--nested">
  200. <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_8" >
  201. <label class="md-nav__link" for="__nav_8" id="__nav_8_label" tabindex="0">
  202. ChatSession
  203. <span class="md-nav__icon md-icon"></span>
  204. </label>
  205. <nav class="md-nav" data-md-level="1" aria-labelledby="__nav_8_label" aria-expanded="false">
  206. <label class="md-nav__title" for="__nav_8">
  207. <span class="md-nav__icon md-icon"></span>
  208. ChatSession
  209. </label>
  210. <ul class="md-nav__list" data-md-scrollfix>
  211. <li class="md-nav__item">
  212. <a href="../../ChatSession/basic-usages/" class="md-nav__link">
  213. Basic Usages
  214. </a>
  215. </li>
  216. <li class="md-nav__item">
  217. <a href="../../ChatSession/transforms/" class="md-nav__link">
  218. Transoforms
  219. </a>
  220. </li>
  221. <li class="md-nav__item">
  222. <a href="../../ChatSession/save-load-session/" class="md-nav__link">
  223. Save/Load Session
  224. </a>
  225. </li>
  226. </ul>
  227. </nav>
  228. </li>
  229. <li class="md-nav__item md-nav__item--nested">
  230. <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_9" >
  231. <label class="md-nav__link" for="__nav_9" id="__nav_9_label" tabindex="0">
  232. Non-English Usages
  233. <span class="md-nav__icon md-icon"></span>
  234. </label>
  235. <nav class="md-nav" data-md-level="1" aria-labelledby="__nav_9_label" aria-expanded="false">
  236. <label class="md-nav__title" for="__nav_9">
  237. <span class="md-nav__icon md-icon"></span>
  238. Non-English Usages
  239. </label>
  240. <ul class="md-nav__list" data-md-scrollfix>
  241. <li class="md-nav__item">
  242. <a href="../../NonEnglishUsage/Chinese/" class="md-nav__link">
  243. Chinese
  244. </a>
  245. </li>
  246. </ul>
  247. </nav>
  248. </li>
  249. <li class="md-nav__item md-nav__item--nested">
  250. <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_10" >
  251. <label class="md-nav__link" for="__nav_10" id="__nav_10_label" tabindex="0">
  252. High-level Applications
  253. <span class="md-nav__icon md-icon"></span>
  254. </label>
  255. <nav class="md-nav" data-md-level="1" aria-labelledby="__nav_10_label" aria-expanded="false">
  256. <label class="md-nav__title" for="__nav_10">
  257. <span class="md-nav__icon md-icon"></span>
  258. High-level Applications
  259. </label>
  260. <ul class="md-nav__list" data-md-scrollfix>
  261. <li class="md-nav__item">
  262. <a href="../../HighLevelApps/bot-sharp/" class="md-nav__link">
  263. BotSharp
  264. </a>
  265. </li>
  266. </ul>
  267. </nav>
  268. </li>
  269. <li class="md-nav__item md-nav__item--nested">
  270. <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_11" >
  271. <label class="md-nav__link" for="__nav_11" id="__nav_11_label" tabindex="0">
  272. More
  273. <span class="md-nav__icon md-icon"></span>
  274. </label>
  275. <nav class="md-nav" data-md-level="1" aria-labelledby="__nav_11_label" aria-expanded="false">
  276. <label class="md-nav__title" for="__nav_11">
  277. <span class="md-nav__icon md-icon"></span>
  278. More
  279. </label>
  280. <ul class="md-nav__list" data-md-scrollfix>
  281. <li class="md-nav__item">
  282. <a href="../../More/log/" class="md-nav__link">
  283. Logger
  284. </a>
  285. </li>
  286. </ul>
  287. </nav>
  288. </li>
  289. <li class="md-nav__item md-nav__item--active md-nav__item--nested">
  290. <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_12" checked>
  291. <label class="md-nav__link" for="__nav_12" id="__nav_12_label" tabindex="0">
  292. Examples
  293. <span class="md-nav__icon md-icon"></span>
  294. </label>
  295. <nav class="md-nav" data-md-level="1" aria-labelledby="__nav_12_label" aria-expanded="true">
  296. <label class="md-nav__title" for="__nav_12">
  297. <span class="md-nav__icon md-icon"></span>
  298. Examples
  299. </label>
  300. <ul class="md-nav__list" data-md-scrollfix>
  301. <li class="md-nav__item">
  302. <a href="../ChatSessionStripRoleName/" class="md-nav__link">
  303. Chat session 1
  304. </a>
  305. </li>
  306. <li class="md-nav__item">
  307. <a href="../ChatSessionWithRoleName/" class="md-nav__link">
  308. Chat session 2
  309. </a>
  310. </li>
  311. <li class="md-nav__item">
  312. <a href="../GetEmbeddings/" class="md-nav__link">
  313. Get embeddings
  314. </a>
  315. </li>
  316. <li class="md-nav__item">
  317. <a href="../InstructModeExecute/" class="md-nav__link">
  318. Instruct executor
  319. </a>
  320. </li>
  321. <li class="md-nav__item">
  322. <a href="../InteractiveModeExecute/" class="md-nav__link">
  323. Interactive executor
  324. </a>
  325. </li>
  326. <li class="md-nav__item">
  327. <a href="../StatelessModeExecute/" class="md-nav__link">
  328. Stateless exeutor
  329. </a>
  330. </li>
  331. <li class="md-nav__item">
  332. <a href="../LoadAndSaveSession/" class="md-nav__link">
  333. Load/Save session
  334. </a>
  335. </li>
  336. <li class="md-nav__item">
  337. <a href="../LoadAndSaveState/" class="md-nav__link">
  338. Load/Save state
  339. </a>
  340. </li>
  341. <li class="md-nav__item md-nav__item--active">
  342. <input class="md-nav__toggle md-toggle" type="checkbox" id="__toc">
  343. <a href="./" class="md-nav__link md-nav__link--active">
  344. Quantize model
  345. </a>
  346. </li>
  347. </ul>
  348. </nav>
  349. </li>
  350. <li class="md-nav__item md-nav__item--nested">
  351. <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_13" >
  352. <label class="md-nav__link" for="__nav_13" id="__nav_13_label" tabindex="0">
  353. API Reference
  354. <span class="md-nav__icon md-icon"></span>
  355. </label>
  356. <nav class="md-nav" data-md-level="1" aria-labelledby="__nav_13_label" aria-expanded="false">
  357. <label class="md-nav__title" for="__nav_13">
  358. <span class="md-nav__icon md-icon"></span>
  359. API Reference
  360. </label>
  361. <ul class="md-nav__list" data-md-scrollfix>
  362. <li class="md-nav__item">
  363. <a href="../../xmldocs/" class="md-nav__link">
  364. index
  365. </a>
  366. </li>
  367. <li class="md-nav__item">
  368. <a href="../../xmldocs/llama.abstractions.ihistorytransform/" class="md-nav__link">
  369. llama.abstractions.ihistorytransform
  370. </a>
  371. </li>
  372. <li class="md-nav__item">
  373. <a href="../../xmldocs/llama.abstractions.illamaexecutor/" class="md-nav__link">
  374. llama.abstractions.illamaexecutor
  375. </a>
  376. </li>
  377. <li class="md-nav__item">
  378. <a href="../../xmldocs/llama.abstractions.itextstreamtransform/" class="md-nav__link">
  379. llama.abstractions.itextstreamtransform
  380. </a>
  381. </li>
  382. <li class="md-nav__item">
  383. <a href="../../xmldocs/llama.abstractions.itexttransform/" class="md-nav__link">
  384. llama.abstractions.itexttransform
  385. </a>
  386. </li>
  387. <li class="md-nav__item">
  388. <a href="../../xmldocs/llama.chatsession/" class="md-nav__link">
  389. llama.chatsession
  390. </a>
  391. </li>
  392. <li class="md-nav__item">
  393. <a href="../../xmldocs/llama.common.authorrole/" class="md-nav__link">
  394. llama.common.authorrole
  395. </a>
  396. </li>
  397. <li class="md-nav__item">
  398. <a href="../../xmldocs/llama.common.chathistory/" class="md-nav__link">
  399. llama.common.chathistory
  400. </a>
  401. </li>
  402. <li class="md-nav__item">
  403. <a href="../../xmldocs/llama.common.fixedsizequeue-1/" class="md-nav__link">
  404. llama.common.fixedsizequeue-1
  405. </a>
  406. </li>
  407. <li class="md-nav__item">
  408. <a href="../../xmldocs/llama.common.illamalogger/" class="md-nav__link">
  409. llama.common.illamalogger
  410. </a>
  411. </li>
  412. <li class="md-nav__item">
  413. <a href="../../xmldocs/llama.common.inferenceparams/" class="md-nav__link">
  414. llama.common.inferenceparams
  415. </a>
  416. </li>
  417. <li class="md-nav__item">
  418. <a href="../../xmldocs/llama.common.llamadefaultlogger/" class="md-nav__link">
  419. llama.common.llamadefaultlogger
  420. </a>
  421. </li>
  422. <li class="md-nav__item">
  423. <a href="../../xmldocs/llama.common.mirostatetype/" class="md-nav__link">
  424. llama.common.mirostatetype
  425. </a>
  426. </li>
  427. <li class="md-nav__item">
  428. <a href="../../xmldocs/llama.common.modelparams/" class="md-nav__link">
  429. llama.common.modelparams
  430. </a>
  431. </li>
  432. <li class="md-nav__item">
  433. <a href="../../xmldocs/llama.exceptions.runtimeerror/" class="md-nav__link">
  434. llama.exceptions.runtimeerror
  435. </a>
  436. </li>
  437. <li class="md-nav__item">
  438. <a href="../../xmldocs/llama.extensions.dictionaryextension/" class="md-nav__link">
  439. llama.extensions.dictionaryextension
  440. </a>
  441. </li>
  442. <li class="md-nav__item">
  443. <a href="../../xmldocs/llama.instructexecutor/" class="md-nav__link">
  444. llama.instructexecutor
  445. </a>
  446. </li>
  447. <li class="md-nav__item">
  448. <a href="../../xmldocs/llama.interactiveexecutor/" class="md-nav__link">
  449. llama.interactiveexecutor
  450. </a>
  451. </li>
  452. <li class="md-nav__item">
  453. <a href="../../xmldocs/llama.llamaembedder/" class="md-nav__link">
  454. llama.llamaembedder
  455. </a>
  456. </li>
  457. <li class="md-nav__item">
  458. <a href="../../xmldocs/llama.llamamodel/" class="md-nav__link">
  459. llama.llamamodel
  460. </a>
  461. </li>
  462. <li class="md-nav__item">
  463. <a href="../../xmldocs/llama.llamaquantizer/" class="md-nav__link">
  464. llama.llamaquantizer
  465. </a>
  466. </li>
  467. <li class="md-nav__item">
  468. <a href="../../xmldocs/llama.llamatransforms/" class="md-nav__link">
  469. llama.llamatransforms
  470. </a>
  471. </li>
  472. <li class="md-nav__item">
  473. <a href="../../xmldocs/llama.native.llamacontextparams/" class="md-nav__link">
  474. llama.native.llamacontextparams
  475. </a>
  476. </li>
  477. <li class="md-nav__item">
  478. <a href="../../xmldocs/llama.native.llamaftype/" class="md-nav__link">
  479. llama.native.llamaftype
  480. </a>
  481. </li>
  482. <li class="md-nav__item">
  483. <a href="../../xmldocs/llama.native.llamatokendata/" class="md-nav__link">
  484. llama.native.llamatokendata
  485. </a>
  486. </li>
  487. <li class="md-nav__item">
  488. <a href="../../xmldocs/llama.native.llamatokendataarray/" class="md-nav__link">
  489. llama.native.llamatokendataarray
  490. </a>
  491. </li>
  492. <li class="md-nav__item">
  493. <a href="../../xmldocs/llama.native.llamatokendataarraynative/" class="md-nav__link">
  494. llama.native.llamatokendataarraynative
  495. </a>
  496. </li>
  497. <li class="md-nav__item">
  498. <a href="../../xmldocs/llama.native.nativeapi/" class="md-nav__link">
  499. llama.native.nativeapi
  500. </a>
  501. </li>
  502. <li class="md-nav__item">
  503. <a href="../../xmldocs/llama.native.safellamacontexthandle/" class="md-nav__link">
  504. llama.native.safellamacontexthandle
  505. </a>
  506. </li>
  507. <li class="md-nav__item">
  508. <a href="../../xmldocs/llama.native.safellamahandlebase/" class="md-nav__link">
  509. llama.native.safellamahandlebase
  510. </a>
  511. </li>
  512. <li class="md-nav__item">
  513. <a href="../../xmldocs/llama.oldversion.chatcompletion/" class="md-nav__link">
  514. llama.oldversion.chatcompletion
  515. </a>
  516. </li>
  517. <li class="md-nav__item">
  518. <a href="../../xmldocs/llama.oldversion.chatcompletionchoice/" class="md-nav__link">
  519. llama.oldversion.chatcompletionchoice
  520. </a>
  521. </li>
  522. <li class="md-nav__item">
  523. <a href="../../xmldocs/llama.oldversion.chatcompletionchunk/" class="md-nav__link">
  524. llama.oldversion.chatcompletionchunk
  525. </a>
  526. </li>
  527. <li class="md-nav__item">
  528. <a href="../../xmldocs/llama.oldversion.chatcompletionchunkchoice/" class="md-nav__link">
  529. llama.oldversion.chatcompletionchunkchoice
  530. </a>
  531. </li>
  532. <li class="md-nav__item">
  533. <a href="../../xmldocs/llama.oldversion.chatcompletionchunkdelta/" class="md-nav__link">
  534. llama.oldversion.chatcompletionchunkdelta
  535. </a>
  536. </li>
  537. <li class="md-nav__item">
  538. <a href="../../xmldocs/llama.oldversion.chatcompletionmessage/" class="md-nav__link">
  539. llama.oldversion.chatcompletionmessage
  540. </a>
  541. </li>
  542. <li class="md-nav__item">
  543. <a href="../../xmldocs/llama.oldversion.chatmessagerecord/" class="md-nav__link">
  544. llama.oldversion.chatmessagerecord
  545. </a>
  546. </li>
  547. <li class="md-nav__item">
  548. <a href="../../xmldocs/llama.oldversion.chatrole/" class="md-nav__link">
  549. llama.oldversion.chatrole
  550. </a>
  551. </li>
  552. <li class="md-nav__item">
  553. <a href="../../xmldocs/llama.oldversion.chatsession-1/" class="md-nav__link">
  554. llama.oldversion.chatsession-1
  555. </a>
  556. </li>
  557. <li class="md-nav__item">
  558. <a href="../../xmldocs/llama.oldversion.completion/" class="md-nav__link">
  559. llama.oldversion.completion
  560. </a>
  561. </li>
  562. <li class="md-nav__item">
  563. <a href="../../xmldocs/llama.oldversion.completionchoice/" class="md-nav__link">
  564. llama.oldversion.completionchoice
  565. </a>
  566. </li>
  567. <li class="md-nav__item">
  568. <a href="../../xmldocs/llama.oldversion.completionchunk/" class="md-nav__link">
  569. llama.oldversion.completionchunk
  570. </a>
  571. </li>
  572. <li class="md-nav__item">
  573. <a href="../../xmldocs/llama.oldversion.completionlogprobs/" class="md-nav__link">
  574. llama.oldversion.completionlogprobs
  575. </a>
  576. </li>
  577. <li class="md-nav__item">
  578. <a href="../../xmldocs/llama.oldversion.completionusage/" class="md-nav__link">
  579. llama.oldversion.completionusage
  580. </a>
  581. </li>
  582. <li class="md-nav__item">
  583. <a href="../../xmldocs/llama.oldversion.embedding/" class="md-nav__link">
  584. llama.oldversion.embedding
  585. </a>
  586. </li>
  587. <li class="md-nav__item">
  588. <a href="../../xmldocs/llama.oldversion.embeddingdata/" class="md-nav__link">
  589. llama.oldversion.embeddingdata
  590. </a>
  591. </li>
  592. <li class="md-nav__item">
  593. <a href="../../xmldocs/llama.oldversion.embeddingusage/" class="md-nav__link">
  594. llama.oldversion.embeddingusage
  595. </a>
  596. </li>
  597. <li class="md-nav__item">
  598. <a href="../../xmldocs/llama.oldversion.ichatmodel/" class="md-nav__link">
  599. llama.oldversion.ichatmodel
  600. </a>
  601. </li>
  602. <li class="md-nav__item">
  603. <a href="../../xmldocs/llama.oldversion.llamaembedder/" class="md-nav__link">
  604. llama.oldversion.llamaembedder
  605. </a>
  606. </li>
  607. <li class="md-nav__item">
  608. <a href="../../xmldocs/llama.oldversion.llamamodel/" class="md-nav__link">
  609. llama.oldversion.llamamodel
  610. </a>
  611. </li>
  612. <li class="md-nav__item">
  613. <a href="../../xmldocs/llama.oldversion.llamaparams/" class="md-nav__link">
  614. llama.oldversion.llamaparams
  615. </a>
  616. </li>
  617. <li class="md-nav__item">
  618. <a href="../../xmldocs/llama.resettablellamamodel/" class="md-nav__link">
  619. llama.resettablellamamodel
  620. </a>
  621. </li>
  622. <li class="md-nav__item">
  623. <a href="../../xmldocs/llama.statefulexecutorbase/" class="md-nav__link">
  624. llama.statefulexecutorbase
  625. </a>
  626. </li>
  627. <li class="md-nav__item">
  628. <a href="../../xmldocs/llama.statelessexecutor/" class="md-nav__link">
  629. llama.statelessexecutor
  630. </a>
  631. </li>
  632. </ul>
  633. </nav>
  634. </li>
  635. </ul>
  636. </nav>
  637. </div>
  638. </div>
  639. </div>
  640. <div class="md-sidebar md-sidebar--secondary" data-md-component="sidebar" data-md-type="toc" >
  641. <div class="md-sidebar__scrollwrap">
  642. <div class="md-sidebar__inner">
  643. <nav class="md-nav md-nav--secondary" aria-label="Table of contents">
  644. </nav>
  645. </div>
  646. </div>
  647. </div>
  648. <div class="md-content" data-md-component="content">
  649. <article class="md-content__inner md-typeset">
  650. <h1 id="quantize-model">Quantize model</h1>
  651. <pre><code class="language-cs">using System;
  652. using System.Collections.Generic;
  653. using System.Linq;
  654. using System.Text;
  655. using System.Threading;
  656. using System.Threading.Tasks;
  657. public class QuantizeModel
  658. {
  659. public static void Run()
  660. {
  661. Console.Write(&quot;Please input your original model path: &quot;);
  662. var inputPath = Console.ReadLine();
  663. Console.Write(&quot;Please input your output model path: &quot;);
  664. var outputPath = Console.ReadLine();
  665. Console.Write(&quot;Please input the quantize type (one of q4_0, q4_1, q5_0, q5_1, q8_0): &quot;);
  666. var quantizeType = Console.ReadLine();
  667. if (LLamaQuantizer.Quantize(inputPath, outputPath, quantizeType))
  668. {
  669. Console.WriteLine(&quot;Quantization succeed!&quot;);
  670. }
  671. else
  672. {
  673. Console.WriteLine(&quot;Quantization failed!&quot;);
  674. }
  675. }
  676. }
  677. </code></pre>
  678. </article>
  679. </div>
  680. </div>
  681. </main>
  682. <footer class="md-footer">
  683. <div class="md-footer-meta md-typeset">
  684. <div class="md-footer-meta__inner md-grid">
  685. <div class="md-copyright">
  686. Made with
  687. <a href="https://squidfunk.github.io/mkdocs-material/" target="_blank" rel="noopener">
  688. Material for MkDocs
  689. </a>
  690. </div>
  691. </div>
  692. </div>
  693. </footer>
  694. </div>
  695. <div class="md-dialog" data-md-component="dialog">
  696. <div class="md-dialog__inner md-typeset"></div>
  697. </div>
  698. <script id="__config" type="application/json">{"base": "../..", "features": [], "search": "../../assets/javascripts/workers/search.208ed371.min.js", "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": {"provider": "mike"}}</script>
  699. <script src="../../assets/javascripts/bundle.a51614de.min.js"></script>
  700. </body>
  701. </html>

C#/.NET上易用的LLM高性能推理框架,支持LLaMA和LLaVA系列模型。

Contributors (1)