ProjectX Economic Brain — Phase 1 (SFT)

Supervised fine-tuning of Qwen/Qwen2.5-7B-Instruct on financial domain data.

Training Details

Method: LoRA (r=16, alpha=32)
Dataset: gbharti/finance-alpaca
Epochs: 2
Learning rate: 2e-4 (cosine)
Format: ChatML

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-7B-Instruct")
model = PeftModel.from_pretrained(base, "automationkasey/projectx-economic-brain-sft")
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-7B-Instruct")

Downloads last month: 1

Model tree for automationkasey/projectx-economic-brain-sft

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct

Adapter

(2363)

this model