Quantization made by Richard Erkhov.
-
Developed by: 1024m
-
License: apache-2.0
-
Finetuned from model : unsloth/llama-3-8b-bnb-4bit
-
Part of EXALT shared task submission : fine-tuned on train data - v001
This llama model was trained 2x faster with
Unsloth and Huggingface's TRL library.
