Show HN: TOD,a universal Decision model based on Task Oriented Design

Parsec AI released TOD, a 12B Gemma-based model and API for decision-making in LLM pipelines, open-sourced on Hugging Face. TOD scores options for tasks such as ticket routing, intent classification, urgency and severity rating, using a 150M retriever to narrow more than 120 labels to a shortlist with recall@16 of 0.9–1.0 on the company's evals. The model supports up to 49k tokens of context and up to 8 images per request, and Parsec AI said it is working on RL environments for custom fine-tuning.

Hi HN, we built TOD, a model and API for jevlike LLM pipelines. we have people using it for, routing a ticket, classifying intent, deciding whether something is urgent, or rating severity. Architecture - 12B Gemma fine-tuned to score options. since it is gemma based it has multimodality built in - When there are 120 labels, we have a 150M retriever that narrows them to a shortlist recall@16 is 0.9–1.0 on our evals , and the 12B model scores that shortlist. - Context goes up to 49k tokens, with up to 8 images per request. we have open sourced it, model: https://huggingface.co/parsecai/tod https://huggingface.co/parsecai/tod API: https://parseclab.ai/tod https://parseclab.ai/tod We are working on getting the RL environments to finetune for custom use cases. would love to hear your opinions on this. Comments URL: https://news.ycombinator.com/item?id=49981275 https://news.ycombinator.com/item?id=49981275 Points: 1 Comments: 0