kevin009
/

llama323

Model card Files Files and versions Community

kevin009/llama323

Model Description

This is a LoRA-tuned version of unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit using KTO (Knowledge Transfer Optimization).

Training Parameters

Learning Rate: 2.5e-05
Batch Size: 1
Training Steps: 1300
LoRA Rank: 16
Training Date: 2025-01-02

Usage

from peft import AutoPeftModelForCausalLM
from transformers import AutoTokenizer

model = AutoPeftModelForCausalLM.from_pretrained("kevin009/llama323", token="YOUR_TOKEN")
tokenizer = AutoTokenizer.from_pretrained("kevin009/llama323")

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support