--- license: apache-2.0 library_name: transformers base_model: - Rombo-Org/Rombo-LLM-V2.5-Qwen-72b datasets: - Rombo-Org/Optimized_Reasoning - NovaSky-AI/Sky-T1_data_17k tags: - unsloth --- # Like my work? Support me on patreon for only $5 a month and get to vote on what model's i make next as well as get access to this org's private repo's Subscribe bellow: - Patreon.com/Rombodawg __________________________________________________ # Rombo-LLM-V3.0-Qwen-72b ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/642cc1c253e76b4c2286c58e/wp9qOi2K2WGzkey0I3SgH.jpeg) Rombos-LLM-V3.0-Qwen-72b is a continues finetuned version of the Rombo-LLM-V2.5-Qwen-72b on a Reasoning and Non-reasoning dataset. The models performs exceptionally well when paired with the system prompt that it was trained on during reasoning training. Nearing SOTA levels even quantized to 4-bit. I highly recommend using a temp of 0.4 when using this model (Especially with the reasoning system prompt) The system prompt is as follows for multi-reasoning, also called optimized reasoning. (Recommended) ``` You are an AI assistant that always begins by assessing whether detailed reasoning is needed before answering; follow these guidelines: 1) Start every response with a single block that evaluates the query's complexity and ends with ; 2) For straightforward queries, state that no detailed reasoning is required and provide a direct answer; 3) For complex queries, indicate that detailed reasoning is needed, then include an additional " (reasoning) (answer)" block with a concise chain-of-thought before delivering the final answer—keeping your reasoning succinct and adding extra steps only when necessary. ``` For single reasoning or traditional reasoning you can use the system prompt bellow: ``` You are an AI assistant that always begins by assessing whether detailed reasoning is needed before answering; follow these guidelines: 1) Start every response with a single " (reasoning) (answer)" block with a concise chain-of-thought before delivering the final answer—keeping your reasoning succinct and adding extra steps only when necessary. ``` For non-reasoning use cases no system prompt is needed (Not recommended) Quantized versions: - https://huggingface.co/bartowski/Rombo-Org_Rombo-LLM-V3.0-Qwen-72b-GGUF - https://huggingface.co/mradermacher/Rombo-LLM-V3.0-Qwen-72b-i1-GGUF Model Evaluation: (Coming soon)