metadata

base_model: unsloth/llama-3.2-3b-instruct-bnb-4bit
language:
  - en
license: apache-2.0
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - llama
  - trl
datasets:
  - Nitral-AI/Mielikki-Erebus_87k-ShareGPT
  - NewEden/Gryphe-Opus-Sharegpt

Uploaded model

Load datasets

dataset1 = load_dataset("sanjay920/LongWriter-6k-sharegpt", split="train")
dataset2 = load_dataset("NewEden/Gryphe-Opus-Sharegpt", split="train")
dataset3 = load_dataset("AiCloser/sharegpt_cot_dataset", split="train")
dataset4 = load_dataset("Nitral-AI/Mielikki-Erebus_87k-ShareGPT", split="train")

Developed by: bunnycore
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.