llmcmp-distill-llama3-8b-lora-v2-fixed-merged

Overview

Base Model

• unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit

Training Data

• Distilled source: safe_plus_filtered_plus_raw_partial
• Raw Kaggle train mix mode: partial
• Raw train rows are limited to non-distilled ids only
• Teacher hard mix: False

Notes

• Winner labels are trained in A / B / C format.
• C means tie.
• This model is intended for direct inference and submission.