doandune/LexGuard-Mistral-Risk-Merged
TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:4kPublished:Mar 14, 2026License:apache-2.0Architecture:Transformer Open Weights Cold
LexGuard-Mistral-Risk-Merged is a 7 billion parameter Mistral-based causal language model developed by doandune, fine-tuned from unsloth/mistral-7b-instruct-v0.2-bnb-4bit. This model was trained using Unsloth and Huggingface's TRL library, enabling 2x faster fine-tuning. Its primary use case is for applications requiring a Mistral 7B model with efficient training characteristics.
Loading preview...