metadata

base_model: unsloth/Llama-3.2-3B-Instruct-bnb-4bit
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - llama
  - trl
  - sft
license: apache-2.0
language:
  - en

Uploaded model

Developed by: msthil2
License: apache-2.0
Finetuned from model : unsloth/Llama-3.2-3B-Instruct-bnb-4bit

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

PLEASE NOTE: You may need to do model.config.torch_dtype = torch.float16 when loading from the hub. Related to this github which wasn't fixed when this was trained: https://github.com/unslothai/unsloth/issues/404