xensive/llama3.2-noinstructv1.3-redo

Uploaded model

• Developed by: xensive
• License: apache-2.0
• Finetuned from model : unsloth/llama-3.2-3b-unsloth-bnb-4bit

Datasets Used

• 1. https://huggingface.co/datasets/mlabonne/FineTome-100k

Changelogs

• Started from scratch since previous versions would print the tokenizer shit, so far the model doesn't reply to itself and understands some form of speech, as well as even forming some coherent sentences related to the topic (sometimes).

• model does not refuse to anything yet.