Open to Collab
45.5 TFLOPS 90 followers Β·
124 following - LLM for sales, marketing, promotion
- LLM for Website Revision System
- increasing quality of communication with customers
- helping clients access information faster
- saving people from financial troubles
reacted
to
smirki 's
post with π 1 day 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 β 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) β +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 JLouisBiz 's activityAll Models Datasets Spaces Papers Collections Community Posts Upvotes Likes Articles view article Website links that automatically improve its accuracy by using assistance from a Large Language Model (LLM) view article Balancing Large Language Model (LLM) Convenience with Control in the Age of Free Software ππ€ 
