llama3-lora-turkish / README.md
Yudum's picture
Update README.md
43cf10e verified
|
raw
history blame
371 Bytes
---
library_name: transformers
tags:
- unsloth
---
# Model Card for Model ID
Fine-tuned Llama3-8b model with Lora (trained with max_steps=300 on colap T4 for experimental purposes)
Base Model: unsloth/llama-3-8b-bnb-4bit
Fine-tuning process https://www.youtube.com/watch?v=pK8u4QfdLx0&ab_channel=DavidOndrej
Fine-tuning data : tolgadev/turkish_73k_instruct_extended