AI NEWS.ccAIが動く、未来が変わる
♡ 保存済み 0
AIモデルライブラリ/kakaocorp/kanana-2-3b-instruct
モデル情報

kanana-2-3b-instruct

kakaocorp · kanana-2-3b-instruct

We present Kanana-2 SLM, **Kakao's second series of Small Language Models (SLMs)**, designed to deliver strong language capabilities while remaining compact and efficient for practical deployment. The series includes 3B, 1.3B, and 0.9B models. This release publicly includes the 3B model and the compressed 1.3B model, providing a balance between capability and efficiency for a wide range of applications. Kanana-2-3B was **pretrained from scratch on TPU clusters** and further improved through post-training with **supervised fine-tuning and reinforcement learning**, resulting in strong instruction-following and reasoning capabilities. Kanana-2-1.3B models are derived from Kanana-2-3B through a **cascade pruning and distillation pipeline**. To further improve deployment efficiency, they adopt **Sliding Window Attention (SWA)**, enabling memory-efficient long-context inference with support for context lengths of up to **32K tokens** while substantially reducing KV-cache memory requirements. General Tasks MMLU acc 5 62.77 56.49 62.32 MMLU-Pro acc 5 36.54 29.87 37.08 BBH acc 3 54.23 45.58 53.60 SimpleQA † acc 5 27.39 23.76 16.83 Mathematics Tasks MATH em 4 35.08 30.82 41.74 GSM8K em 8 61.03 51.93 75.74 Coding Tasks HumanEval pass@1 0 55.96 51.33 45.31 MBPP pass@1 3 50.95 44.86 53.85 Korean Tasks KMMLU acc 5 47.92 44.17 43.08 KoSimpleQA † acc 5 32.50 28.50 13.40 HAE-RAE Bench (v1.0) acc 5 80.66 75.34 55.54 MATH-Ko ‡ em 4 31.54 24.75 31.92 MBPP-Ko § pass@1 3 44.55 39.38 47.97 Long Context Tasks RULER-32K acc 0 67.50 55.72 69.01 Instruction-following, chat, tool-calling, code, math, and knowledge benchmarks for the Kanana-2 SLM series. Scores use greedy decoding (temperature 0.0, top-p 1.0, max 4096 tokens); the metric for each benchmark is listed in the Metric column.

翻訳待ちのため原文を表示しています。

テキスト生成license:other
コンテキスト長非公開
入力 → 出力テキスト → テキスト
モデルウェイト未確認
情報更新日時2026/11/2 19:16:19
OVERVIEW

モデル紹介

We present Kanana-2 SLM, **Kakao's second series of Small Language Models (SLMs)**, designed to deliver strong language capabilities while remaining compact and efficient for practical deployment. The series includes 3B, 1.3B, and 0.9B models. This release publicly includes the 3B model and the compressed 1.3B model, providing a balance between capability and efficiency for a wide range of applications. Kanana-2-3B was **pretrained from scratch on TPU clusters** and further improved through post-training with **supervised fine-tuning and reinforcement learning**, resulting in strong instruction-following and reasoning capabilities. Kanana-2-1.3B models are derived from Kanana-2-3B through a **cascade pruning and distillation pipeline**. To further improve deployment efficiency, they adopt **Sliding Window Attention (SWA)**, enabling memory-efficient long-context inference with support for context lengths of up to **32K tokens** while substantially reducing KV-cache memory requirements. General Tasks MMLU acc 5 62.77 56.49 62.32 MMLU-Pro acc 5 36.54 29.87 37.08 BBH acc 3 54.23 45.58 53.60 SimpleQA † acc 5 27.39 23.76 16.83 Mathematics Tasks MATH em 4 35.08 30.82 41.74 GSM8K em 8 61.03 51.93 75.74 Coding Tasks HumanEval pass@1 0 55.96 51.33 45.31 MBPP pass@1 3 50.95 44.86 53.85 Korean Tasks KMMLU acc 5 47.92 44.17 43.08 KoSimpleQA † acc 5 32.50 28.50 13.40 HAE-RAE Bench (v1.0) acc 5 80.66 75.34 55.54 MATH-Ko ‡ em 4 31.54 24.75 31.92 MBPP-Ko § pass@1 3 44.55 39.38 47.97 Long Context Tasks RULER-32K acc 0 67.50 55.72 69.01 Instruction-following, chat, tool-calling, code, math, and knowledge benchmarks for the Kanana-2 SLM series. Scores use greedy decoding (temperature 0.0, top-p 1.0, max 4096 tokens); the metric for each benchmark is listed in the Metric column.

主な特徴

特点摘要待依据来源补齐，不凭模型名称推断能力。

制約と注意点

具体的な制約を判断する出典が不足しています。実際の性能、遅延、データ方針、ライセンス、提供期間を確認してください。

PRICING & COST

出典別料金と費用分析

料金はチャネル・地域・設定によって異なります。各チャネルの料金は個別に表示し、提供元の統一公式料金とは見なしません。

出典・チャネル入力出力課金単位収集日時
確認可能な料金がありません。出典を確認してください。

月額の基本トークン費用を試算

—

試算はキャッシュ割引、段階料金、マルチモーダル追加料金、検索、税金、追加推論出力を含みません。

INDEPENDENT BENCHMARKS

公開評価と実行設定

暂无已采集的可核验公开评分。模型未上榜不代表能力较低。

収録済みの全ランキング →

よくある質問

オープンウェイトなら無料で商用利用できますか？

必ずしもそうではありません。バージョン別のライセンス、商用条件、利用方針を確認してください。自前運用には計算資源と保守費用も必要です。

これはリアルタイムの請求料金ですか？

収集日時付きの料金スナップショットです。最新のバージョン、地域、割引、課金方式は各チャネルで確認してください。

出典と追跡記録

huggingface · kakaocorp/kanana-2-3b-instruct ↗2026/10/29 17:01:56
huggingface · enrich:ec826434-786f-4407-85cf-433e7e06c073 ↗2026/10/30 04:34:35

许可证：other。模型介绍与第三方评测均以原来源的具体版本和方法为准。