159 1 year ago

tools
ollama run rjmalagon/rombos-llm-v2.5-qwen-32b:q8_0

Applications

Claude Code
Claude Code ollama launch claude --model rjmalagon/rombos-llm-v2.5-qwen-32b:q8_0
Codex
Codex ollama launch codex --model rjmalagon/rombos-llm-v2.5-qwen-32b:q8_0
OpenCode
OpenCode ollama launch opencode --model rjmalagon/rombos-llm-v2.5-qwen-32b:q8_0
OpenClaw
OpenClaw ollama launch openclaw --model rjmalagon/rombos-llm-v2.5-qwen-32b:q8_0

Models

View all →

Readme

Rombos-LLM-V2.5-Qwen-32b

image/jpeg

Rombos-LLM-V2.5-Qwen-32b is a continues finetuned version of Qwen2.5-32B. I noticed recently that the Qwen team did not learn from my methods of continuous finetuning, the great benefits, and no downsides of it. So I took it upon myself to merge the instruct model with the base model myself using the Ties merge method

This version of the model shows higher performance than the original instruct and base models. https://huggingface.co/rombodawg/Rombos-LLM-V2.5-Qwen-32b