haritzpuerto/unsloth-Qwen3-1.7B-IF-FA
Text Generation • Updated
• 21
⚙️🧠🔒 Controllable Reasoning Models - Checkpoints
Training dataset and LoRA checkpoints for the arXiv 2026 preprint Controllable Reasoning Models are Private Thinkers
-
-
haritzpuerto/unsloth-Qwen3-1.7B-IF-RT
Text Generation • Updated • 15 -
haritzpuerto/unsloth-Qwen3-4B-IF-FA
Text Generation • Updated • 17 -
haritzpuerto/unsloth-Qwen3-4B-IF-RT
Text Generation • Updated • 13 -
haritzpuerto/unsloth-Qwen3-8B-IF-FA
Text Generation • Updated • 17 -
haritzpuerto/unsloth-Qwen3-8B-IF-RT
Text Generation • Updated • 19 -
haritzpuerto/unsloth-Qwen3-14B-IF-Avg
Text Generation • Updated • 14 -
haritzpuerto/unsloth-Qwen3-14B-IF-FA
Text Generation • Updated • 15 -
haritzpuerto/unsloth-Qwen3-14B-IF-RT
Text Generation • Updated • 19 -
haritzpuerto/unsloth-Phi-4-3.8B-IF-FA
Text Generation • Updated • 12 -
haritzpuerto/unsloth-Phi-4-3.8B-IF-RT
Text Generation • Updated • 16 -
haritzpuerto/microsoft-Phi-4-14B-IF-Avg
Text Generation • Updated • 18 -
haritzpuerto/microsoft-Phi-4-14B-IF-FA
Text Generation • Updated • 16 -
haritzpuerto/microsoft-Phi-4-14B-IF-RT
Text Generation • Updated • 20