openNemo-9B-Claude-Opus-4.6-distill
Рассуждения — дистиллированная версия openNemo-9B, тонко настроенная на следы рассуждений Клода Опуса 4.6. Обучение с SFT DPO по...
Рассуждения — дистиллированная версия openNemo-9B, тонко настроенная на следы рассуждений Клода Опуса 4.6. Обучение с SFT DPO по...
MLX Studio — the only app that natively supports JANG models with reasoning Nemotron-Cascade-2-30B-A3B — JANG_2L (2.3-bit, 8-bit...
This model mlx-community/Nemotron-Cascade-2-30B-A3B-mlx-6bit was converted to MLX format from nvidia/Nemotron-Cascade-2-30B-A3B using mlx-lm version 0.31.1. Модальности:Генерация текста Области применения:Логика...
> [!TIP] > Support this work → · X · GitHub · REAP paper · Cerebras REAP W4A16...
> Use temperature=1.0 and topp=0.95 across all tasks and serving backends** — reasoning, tool calling, and general chat...
— Model Architecture: NemotronHForCausalLM — Input: Text — Output: Text — Model Optimizations: — Weight quantization: FP8 —...
The post-training data has a cutoff date of May 2026. The pre-training data has a cutoff date of...
> Built with mlx-optiq, the MLX-native toolkit to quantize, fine-tune, and serve LLMs locally on Apple Silicon, no...
The pre-training data has a cutoff date of September 2025. The post-training data has a cutoff date of...
QLoRA fine-tune of NVIDIA Nemotron-3-Super-120B-A12B (120B-total / 12B-active hybrid Mamba-2 + Latent-MoE, nemotronh) on the piagent split of...