README.md

metadata

language:
  - en
license: llama2
model-index:
  - name: llama-8b-math
    results: []
tags:
  - llama
  - instruction-tuning

Llama 8B Math

Mathematical reasoning fine-tuned model

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dp66/llama-8b-math")
model = AutoModelForCausalLM.from_pretrained("dp66/llama-8b-math")

Training Details

• Base Model: LLaMA-8B
• Fine-tuning Task: Mathematical