Hugging Face's logo

3rd-Degree-Burn
/
Llama-3.1-8B-Squareroot-v0

Safetensors
llama
Merge
mergekit
lazymergekit
NousResearch/Meta-Llama-3.1-8B-Instruct
EpistemeAI/Fireball-Alpaca-Llama3.1.07-8B-Philos-Math-KTO-beta
nvidia/OpenMath2-Llama3.1-8B
Model card Files Community
Llama-3.1-8B-Squareroot-v0 / README.md
3rd-Degree-Burn's picture
3rd-Degree-Burn
Update README.md
7cd5a6a verified
preview code
|
raw
history blame contribute delete
1.4 kB
metadata
license: apache-2.0
tags:
  - merge
  - mergekit
  - lazymergekit
  - NousResearch/Meta-Llama-3.1-8B-Instruct
  - EpistemeAI/Fireball-Alpaca-Llama3.1.07-8B-Philos-Math-KTO-beta
  - nvidia/OpenMath2-Llama3.1-8B
base_model:
  - NousResearch/Meta-Llama-3.1-8B-Instruct
  - EpistemeAI/Fireball-Alpaca-Llama3.1.07-8B-Philos-Math-KTO-beta
  - nvidia/OpenMath2-Llama3.1-8B

Llama-3.1-8B-Squareroot

This is a TIES merge that combines the performance of the following models:

image/png

Disclaimer: This one's a failed attempt. Working on a better version, so check back soon!

Benchmarks

The model ranks in the top 5 for MATH benchmarks but performs severely badly on others (which isn't quite what I was expecting). I’m hoping to improve its general abilities without losing its math skills. Qwen still has the top spot :(

image/png