NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness
AI & ML interests
All Models, One Mind.
Recent Activity
View all activity
Papers
NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness
Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks
Organization Card
Welcome to TokenRhythm Technologies: https://tokenrhythm.ai/
News
- 🐴NeoHorse-1 Models: https://huggingface.co/collections/TokenRhythm/neohorse-1. A Step Towards Recursive Self-Improvement.
- 🎼TokenRhythm MaaS service: https://tokenrhythm.studio/. All Models, One Mind.
- 🦐OpenSquilla is released: https://www.opensquilla.ai/. Token-Efficient AI Agent Intelligence.
models 10
TokenRhythm/NeoHorse-1-9B
Text Generation • 9B • Updated • 7.96k • 649
TokenRhythm/NeoHorse-1-4B
Text Generation • 4B • Updated • 11.9k • 1.94k
TokenRhythm/NeoHorse-1-4B-GGUF
Text Generation • 4B • Updated • 6.51k • 12
TokenRhythm/NeoHorse-1-9B-MLX
Text Generation • 9B • Updated • 390 • 2
TokenRhythm/NeoHorse-1-9B-MLX-8bit
Text Generation • 9B • Updated • 187 • 4
TokenRhythm/NeoHorse-1-9B-MLX-4bit
Text Generation • 9B • Updated • 162 • 3
TokenRhythm/NeoHorse-1-4B-MLX
Text Generation • 4B • Updated • 349 • 2
TokenRhythm/NeoHorse-1-4B-MLX-8bit
Text Generation • 4B • Updated • 98 • 2
TokenRhythm/NeoHorse-1-4B-MLX-4bit
Text Generation • 4B • Updated • 165 • 2
TokenRhythm/NeoHorse-1-9B-GGUF
Text Generation • 9B • Updated • 7.74k • 15