LLama-3-8b-Maths / README.md
Kukedlc's picture
Update README.md
34a04fd verified
metadata
language:
  - en
license: other
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - llama
  - trl
  - sft
base_model: Kukedlc/LLama-3-8b-Python
datasets:
  - microsoft/orca-math-word-problems-200k

Uploaded model

  • Developed by: Kukedlc
  • License: apache-2.0
  • Finetuned from model : Kukedlc/LLama-3-8b-Maths

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