mrgrtv1-grpo-merged-eos-fix/README.md

base_model, tags, license, language

base_model	tags	license	language
N-Bot-Int/mrgrtv1-8b-merged	text-generation-inference transformers unsloth llama	agpl-3.0	en

EXPERIMENTAL FIX... THE MODEL DOESNT HAVE ANY ISSUE... THOUGH IT DOES SEPPOKU... one of the issue we find... not really a massive issue! just follow our recommended setting... this is just a remnant

Uploaded finetuned model

• Developed by: N-Bot-Int
• License: agpl-3.0
• Finetuned from model : N-Bot-Int/mrgrtv1-8b-merged

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.