LiquidAI: LFM2.5-2.6B

{"about":"### Model ringkas dengan pelatihan agen\n\nLFM2.5-2.6B adalah model teks Liquid AI untuk tugas yang memerlukan kepatuhan instruksi, pengolahan dokumen, dan pelaksanaan beberapa langkah berurutan. Dalam keluarga LFM2.5, versi ini mendapat pelatihan khusus untuk alur agen: pengembang melatihnya dalam interaksi alat dan lingkungan kerja agen yang umum. Pelatihan ini berkaitan dengan perilaku model; tindakan aplikasi tertentu ditentukan integrasinya.\n\nDasar LFM2.5-2.6B adalah arsitektur hibrida LFM2 dengan 2,69 miliar parameter, menggabungkan blok konvolusi pendek dan perhatian berkelompok. Liquid AI mengembangkan keluarga ini untuk penggunaan pada perangkat, tetapi di Ailoot API model digunakan melalui antarmuka teks: pengguna mengirim pesan dan menerima jawaban teks.\n\n### Penggunaan yang bermanfaat\n\nModel sesuai untuk ekstraksi informasi, pertanyaan atas materi yang diberikan, dan pengolahan instruksi panjang. Misalnya, kirim korespondensi pelanggan, minta persyaratan dihimpun dalam satu daftar, lalu temukan pertentangan dan siapkan surat klarifikasi. Untuk jawaban basis pengetahuan, lampirkan potongan hasil pencarian dan tetapkan aturan: gunakan potongan tersebut, pertahankan nama, dan tandai fakta yang tidak tersedia.\n\nDokumentasi Liquid AI menyebut ekstraksi data, RAG, dan alur konteks panjang. Pengembang juga membatasi penggunaannya: pemrograman agen dan tugas yang memerlukan banyak pengetahuan faktual tanpa sumber yang diberikan bukan tugas yang direkomendasikan untuk versi ini. Untuk istilah bidang khusus, sertakan definisi dan dokumen asal dalam permintaan.\n\n### Konteks dan bahasa\n\nAiloot API menyatakan konteks 128 000 token untuk model ini. Konteks meliputi materi tugas dan riwayat percakapan; ukuran jawaban perlu direncanakan bersama keduanya. Kartu pengembang mencantumkan 16 bahasa, termasuk Rusia, Inggris, Mandarin, Jerman, dan Spanyol. Ini memungkinkan pengolahan dokumen serta korespondensi multibahasa sambil menetapkan bahasa dan format hasil dalam instruksi.","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 ringkas Liquid AI untuk ekstraksi data, jawaban berbasis dokumen, dan tugas berurutan dengan konteks besar."}