Ellora Collection Ellora: Enhancing LLMs with LoRA - Standardized Recipes for Capability Enhancement • 12 items • Updated 5 days ago • 4
100 Coder/Programming - MOE, Reasoning, Reg, Imatrix, Fused. Collection Models (0.8B to 87B) in regular, "reasoning", "Brainstorm", MOE (1x to 8x / 128 experts), and expanded to create better and stronger code, faster. • 62 items • Updated about 9 hours ago • 23
Tool-Star Collection Tool-Star is a reinforcement learning-based framework designed to empower LLMs to autonomously invoke multiple external tools during stepwise reasonin • 7 items • Updated 10 days ago • 5