README.md · Cseti/PULI-LlumiX-Llama-3.1-Instruct-SZM-merge-gguf at main

metadata

base_model: NYTK/PULI-LlumiX-Llama-3.1
library_name: peft
datasets:
  - boapps/szurkemarha
tags:
  - llm
  - lora
  - hungarian
  - llama
  - instruct
  - gguf

Model Details

These models are the GGUF versions of this LoRA: Cseti/PULI-LlumiX-Llama-3.1-Instruct-LoRA.

I created them by merging the base model with the qlora, then converted them to GGUF format.

Please note that this model is experimental, and I trained it quickly for testing purposes. I'm still testing it. I'll finetune it further if I feel it is worth it.