LiquidAI: LFM2.5-2.6B

{"about":"### Model padat dengan latihan ejen\n\nLFM2.5-2.6B ialah model teks Liquid AI untuk tugas yang memerlukan pematuhan arahan, pengolahan dokumen dan pelaksanaan beberapa langkah berturutan. Dalam keluarga LFM2.5, versi ini mendapat latihan khusus untuk aliran ejen: pembangun melatihnya melalui interaksi alat dan persekitaran kerja ejen yang lazim. Latihan ini berkaitan dengan tingkah laku model; tindakan aplikasi tertentu ditetapkan oleh integrasi.\n\nAsas LFM2.5-2.6B ialah seni bina hibrid LFM2 dengan 2,69 bilion parameter, menggabungkan blok konvolusi pendek dan perhatian berkumpulan. Liquid AI membangunkan keluarga ini untuk penggunaan pada peranti, namun dalam Ailoot API model digunakan melalui antara muka teks: pengguna menghantar mesej dan menerima jawapan teks.\n\n### Kegunaan yang sesuai\n\nModel sesuai untuk pengekstrakan maklumat, soalan berdasarkan bahan yang diberikan dan pengolahan arahan panjang. Contohnya, hantar surat-menyurat pelanggan, minta keperluan dikumpulkan dalam satu senarai, kemudian kenal pasti percanggahan dan sediakan surat penjelasan. Untuk jawapan pangkalan pengetahuan, lampirkan petikan carian dan tetapkan peraturan: bergantung padanya, kekalkan nama dan tandakan fakta yang tiada.\n\nDokumentasi Liquid AI menyatakan pengekstrakan data, RAG dan aliran konteks panjang. Pembangun turut mengehadkan kegunaan: pengaturcaraan ejen dan tugas yang memerlukan banyak pengetahuan fakta tanpa sumber yang diberikan bukan tugas disyorkan untuk versi ini. Untuk istilah bidang khusus, sertakan takrif dan dokumen asal dalam permintaan.\n\n### Konteks dan bahasa\n\nAiloot API menyatakan konteks 128 000 token bagi model ini. Konteks merangkumi bahan tugas dan sejarah perbualan; saiz jawapan perlu dirancang bersama kedua-duanya. Kad pembangun menyenaraikan 16 bahasa, termasuk Rusia, Inggeris, Cina, Jerman dan Sepanyol. Ini membolehkan pengolahan dokumen serta surat-menyurat berbilang bahasa sambil menetapkan bahasa dan format hasil dalam arahan.","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":"Model teks padat Liquid AI untuk pengekstrakan data, jawapan berasaskan dokumen dan tugas berturutan dengan konteks besar."}