NOVA-vision-language/PlanLLM
TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:4kPublished:Feb 1, 2024License:apache-2.0Architecture:Transformer0.0K Open Weights Cold

PlanLLM by NOVA-vision-language is a 7 billion parameter conversational assistant, fine-tuned from Vicuna-7B-v1.1 with a 4096-token context length. It specializes in guiding users through multi-step tasks like recipes and DIY projects, answering related questions throughout the process. The model was trained using a combination of Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) on synthetic dialogue data.

Loading preview...