🦙 LLaMA 3.2 1B — Financial Agent (Fine-tuned with Unsloth)

This model is a fine-tuned version of LLaMA 3.2 1B Instruct on a financial transaction recording dataset. It can understand and generate structured actions for expense logging and income tracking.

Training details

Base model: meta-llama/Llama-3.2-1B-Instruct
Fine-tuning: PEFT (LoRA) via Unsloth
Dataset: finbot_augmented_fixed.jsonl
Parameters: r=32, alpha=64, dropout=0.05

Usage

from unsloth import FastLanguageModel
model, tokenizer = FastLanguageModel.from_pretrained("raditioah/llama-3.2-1B-financial-agent")
FastLanguageModel.for_inference(model)
print(model.chat(tokenizer, "Catat pengeluaran makan siang 25000"))

Downloads last month: 1

Safetensors

Model size

1B params

Tensor type

F32

BF16

Inference Providers NEW

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

Model tree for raditioah/financial-llama-1b-instruct-merged

Base model

meta-llama/Llama-3.2-1B-Instruct

Quantized

(353)

this model