全站搜索
AI 模型 85012
- Llama-3-Peach-Instruct-4x8B-MoE-GGUF↗
RDson
- automerger_-_ShadowYamshadow-7B-gguf↗
RichardErkhov
- duoqi_-_Nanbeige2-16B-Chat-gguf↗
RichardErkhov
- LoftQ_-_Mistral-7B-v0.1-4bit-32rank-gguf↗
RichardErkhov
- seyf1elislam_-_WestKunai-Hermes-10.7b-test-gguf↗
RichardErkhov
- rwkv-6-world-3b↗
RWKV
- Qwen3-4B-Thinking-heretic↗
saidutta69
- polish-roberta-base-v2↗
sdadas
- gpt-oss-120b-VISION-GGUF↗
SoAIHQ
- Nori-30M↗
Synthefy
**Nori-30M** is the ~29.2M-parameter variant of Nori, a tabular foundation model for **regression** via in-context learning (ICL). Given a few labeled rows as context, it predicts on new query rows in a **single forward pass**, with no task-specific training or fine-tuning. The model is trained **entirely on synthetic data**. - **Documentation:** https://docs.synthefy.com/nori/ - **Repository:** https://github.com/Synthefy/synthefy-nori - **Library:** `pip install synthefy-nori` - **Checkpoint:** `nori.pt` (this repo) - **Parameters:** ~29.2M - **License:** Apache-2.0 Mean and median R² across 96 regression tasks from three public benchmark suites, on the same protocol as the base Nori:
