Hugging Face's logo
Zixi "Oz" Li's picture
Open to Work
7 25 40

Zixi "Oz" Li PRO

OzTianlu
NoesisLab
ljupco's profile picture Fishtiks's profile picture John6666's profile picture
·
https://github.com/lizixi-0x2F

AI & ML interests

My research focuses on deep reasoning with small language models, Transformer architecture innovation, and knowledge distillation for efficient alignment and transfer.

Recent Activity

liked a dataset about 18 hours ago
OpenDataArena/MMFineReason-SFT-123K-Qwen3-VL-235B-Thinking
liked a model about 18 hours ago
Tesslate/OmniCoder-9B
reacted to smirki's post with 👍 about 23 hours ago
Introducing OmniCoder-9B We trained a 9B coding agent on 425K real agentic trajectories from Claude Opus 4.6, GPT-5.4, GPT-5.3-Codex, and Gemini 3.1 Pro across Claude Code, OpenCode, Codex, and Droid scaffolding. Results: - GPQA Diamond: 83.8 pass@1 (166/198), 86.4 pass@3 — above GPT-OSS-120B (80.1), Qwen3.5-9B (81.7), and Claude Haiku 4.5 (73) - AIME 2025: 90 pass@5 (27/30) - Terminal-Bench 2.0: 28.1 (25/89) — +8.1 points over base model The key insight: We trained on what frontier agents actually do, real tool calls, real error recovery, real edit diffs. The model learns read-before-write patterns, responds to LSP diagnostic, and applies minimal diffs instead of full rewrites. Base: Qwen3.5-9B. LoRA SFT, 4x H200, Axolotl, 99.35% packing efficiency. Weights: https://huggingface.co/Tesslate huggingface.co/Tesslate/OmniCoder-9B GGUF: huggingface.co/Tesslate/OmniCoder-9B-GGUF Apache 2.0. Run it locally.
View all activity

Organizations

LocalLLaMA's profile picture Hugging Face Discord Community's profile picture NoesisLab's profile picture Unsloth Jobs Explorers's profile picture