Napswoy
/

Legal-Chatbot-Qwen2.5

Model card Files Files and versions

Legal-Chatbot-Qwen2.5

This model is a fine-tuned version of unsloth/Qwen2.5-3B-Instruct for Indonesian Legal tasks. It was trained using Unsloth and TRL.

Training procedure

PEFT / LoRA: 16 r, 16 alpha
Learning rate: 2e-4
Steps: 800
Batch size: 2
Gradient accumulation: 4

Downloads last month: 2

Inference Providers NEW

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

Model tree for Napswoy/Legal-Chatbot-Qwen2.5

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-3B-Instruct

Finetuned

unsloth/Qwen2.5-3B-Instruct

Adapter

(481)

this model