Ling-3.0-flash-Sante-fp8
🤗 Hugging Face | 🤖 ModelScope | 🐙 Vercel Ling-3.0-flash-Sante-fp8 is the FP8-quantized release of Ling-3.0-flash-Sante,...
🤗 Hugging Face | 🤖 ModelScope | 🐙 Vercel Ling-3.0-flash-Sante-fp8 is the FP8-quantized release of Ling-3.0-flash-Sante,...
inclusionAI/Ling-3.1-flash の公式FP8を出発点に、SGLang専用のNVFP4保存版を作り、そこへweights-only abliteration (T24) を焼き込み、さらにNEXTN 3-stepのMTP draftを同梱した保存版です。 通常のHugging Face量子化モデルではありません。vLLM/Transformers/GGUFでそのまま動く形式でもありません。 固定SGLang image・TP4/EP4・同梱patch・記載のGPU世代を維持した場合のみ再現できます。 draft/ は本体の model.wordembeddings / lmhead を共有する前提で、model.layers.72. だけを持ちます。量子化configは取り除いてあります(unquant...
Base Model | OpenRouter | Announcement Ling-3.0-flash-Fin is the first finance-enhanced model in the...
Base Model | OpenRouter | Announcement Ling-3.0-flash-Fin is the first finance-enhanced model in the...
NVFP4 (4-bit) quantization of inclusionAI/Ling-3.0-flash (BailingMoeV3, 42-layer hybrid MoE + MTP) produced with NVIDIA ModelOpt using the DeepSeek-V4...
> Important: This model uses the JANGTQ (JANG TurboQuant) quantization format — an extreme-compression variant of JANG for...
This model mlx-community/Ling-2.6-flash-mlx-4bit-gs32 was converted to MLX format from inclusionAI/Ling-2.6-flash using mlx-lm version 0.31.3. Модальности:Генерация текста Области применения:Диалог...
A second quantization of inclusionAI/Ling-3.0-flash, alongside Ling-3.0-flash-HybridQuant-NVFP4-W4A16. Identical bit placement and identical serving contract; it differs in how...
Эта модель mlx-community/Ling-2.6-flash-mlx-4bit-DWQ была преобразована в формат MLX из includeAI/Ling-2.6-flash с использованием mlx-lm версии 0.31.3. Модальности:Генерация текста Области...
🤗 Обнимающее лицо | 🤖 ModelScope | Технический отчет Ling-2.6-flash-base — это базовая контрольная точка модели...