LiquidAI: LFM2.5-2.6B

{"about":"### Agentlar uchun tayyorlangan ixcham model\n\nLFM2.5-2.6B — ko‘rsatmaga rioya qilish, hujjatlarni qayta ishlash va bir nechta qadamni izchil bajarish muhim bo‘lgan vazifalar uchun Liquid AI matn modeli. LFM2.5 oilasida bu versiya agentli jarayonlarga alohida tayyorlangan: ishlab chiqaruvchi uni vositalar va agentlarning odatiy ish muhitlari bilan muloqotga o‘rgatgan. Bunday o‘qitish model xulqiga taalluqli; ilovadagi aniq harakatlarni integratsiya belgilaydi.\n\nLFM2.5-2.6B asosida 2,69 mlrd parametrli LFM2 gibrid arxitekturasi yotadi. U qisqa konvolyutsiya va guruhlangan diqqat bloklarini birlashtiradi. Liquid AI bu oilani qurilmalarda ishlash uchun rivojlantiradi, ammo Ailootʼda model matnli interfeys orqali ishlatiladi: foydalanuvchi xabar yuborib, matnli javob oladi.\n\n### Qayerda foydali\n\nModel matndan maʼlumot ajratish, berilgan materiallar bo‘yicha savollar va uzun ko‘rsatmalarni qayta ishlashga mos. Masalan, buyurtmachi bilan yozishmalarni berib, talablarni yagona ro‘yxatga yig‘ish, keyin ziddiyatlarni ajratish va aniqlashtiruvchi xat tayyorlashni so‘rash mumkin. Bilimlar bazasi bo‘yicha javob uchun topilgan parchalarni qo‘shib, ularga tayanish, nomlarni saqlash va kerakli fakt yo‘qligini belgilash qoidasini berish foydali.\n\nLiquid AI hujjatlarida ish yo‘nalishlari orasida maʼlumot ajratish, RAG va uzun kontekstli jarayonlar ko‘rsatilgan. Ishlab chiqaruvchi qo‘llanish sohasini alohida chegaralaydi: agentli dasturlash va manbalar berilmasdan katta hajmdagi faktik bilim talab qiladigan topshiriqlar bu versiya uchun tavsiya etilmaydi. Sohaviy atamalar bilan ishlashda so‘rovga taʼriflar va asl hujjatlarni kiritgan maʼqul.\n\n### Kontekst va tillar\n\nAilootʼda bu model uchun 128 000 tokenli kontekst ko‘rsatilgan. Unga vazifa materiallari va suhbat tarixi kiradi; javob hajmini ular bilan birga rejalash kerak. Ishlab chiqaruvchi kartochkasida 16 til, jumladan rus, ingliz, xitoy, nemis va ispan tillari keltirilgan. Bu modelni hujjatlar va yozishmalarni ko‘p tilda qayta ishlashga qo‘llash, ko‘rsatmada esa kerakli til va natija formatini belgilash imkonini beradi.","alias_of":null,"aliases":[],"author":"Liquid","canonical_model":"liquid/lfm-2.5-2.6b","ctx":null,"formats":["chat","gemini","messages","responses"],"id":"liquid/lfm-2.5-2.6b","input":["text"],"kind":"text","max_out":null,"methods":[{"cache_read":0.08,"cache_write":null,"cache_write_1h":null,"cache_write_5m":null,"conditional_meter":null,"ctx":null,"family":"anthropic","fast_multiplier":1,"flex_multiplier":1,"fmt":"messages","http":"POST","img_in":null,"img_out":null,"in":0.7,"input":["text"],"label":"Anthropic Messages","max_out":null,"max_tool_calls":null,"out":1.0,"output":["text"],"path":"/v1/messages","request_model_id":"liquid/lfm-2.5-2.6b","route_label":"Ultra","status_reads":[],"tiers":[],"tool_prices":null,"unit":"token","units":[]},{"cache_read":0.08,"cache_write":null,"cache_write_1h":null,"cache_write_5m":null,"conditional_meter":null,"ctx":null,"family":"openai","fast_multiplier":1,"flex_multiplier":1,"fmt":"responses","http":"POST","img_in":null,"img_out":null,"in":0.7,"input":["text"],"label":"OpenAI Responses","max_out":null,"max_tool_calls":null,"out":1.0,"output":["text"],"path":"/v1/responses","request_model_id":"liquid/lfm-2.5-2.6b","route_label":"Ultra","status_reads":[],"tiers":[],"tool_prices":null,"unit":"token","units":[]},{"cache_read":0.08,"cache_write":null,"cache_write_1h":null,"cache_write_5m":null,"conditional_meter":null,"ctx":null,"family":"openai","fast_multiplier":1,"flex_multiplier":1,"fmt":"chat","http":"POST","img_in":null,"img_out":null,"in":0.7,"input":["text"],"label":"OpenAI Chat","max_out":null,"max_tool_calls":null,"out":1.0,"output":["text"],"path":"/v1/chat/completions","request_model_id":"liquid/lfm-2.5-2.6b","route_label":"Ultra","status_reads":[],"tiers":[],"tool_prices":null,"unit":"token","units":[]},{"cache_read":0.08,"cache_write":null,"cache_write_1h":null,"cache_write_5m":null,"conditional_meter":null,"ctx":null,"family":"gemini","fast_multiplier":1,"flex_multiplier":1,"fmt":"gemini","http":"POST","img_in":null,"img_out":null,"in":0.7,"input":["text"],"label":"Gemini generateContent","max_out":null,"max_tool_calls":null,"out":1.0,"output":["text"],"path":"/v1beta/models/liquid/lfm-2.5-2.6b:generateContent","request_model_id":"liquid/lfm-2.5-2.6b","route_label":"Ultra","status_reads":[],"tiers":[],"tool_prices":null,"unit":"token","units":[]}],"model_aliases":[{"canonical_model_id":"liquid/lfm-2.5-2.6b","request_model_id":"liquid/lfm-2.5-2.6b","route_label":"Ultra"}],"name":"LiquidAI: LFM2.5-2.6B","price":{"in":0.7,"in_label":null,"out":1.0,"out_label":null,"sort_in":0.7,"sort_out":1.0,"varies":false},"public_id":"liquid/lfm-2.5-2.6b","short":"Maʼlumot ajratish, hujjatlar bo‘yicha javob va katta kontekstli izchil vazifalar uchun Liquid AIʼning ixcham matn modeli."}