Instructions to use yuvarajakkole/finance-slm-qwen3-router-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use yuvarajakkole/finance-slm-qwen3-router-lora with PEFT:
Task type is invalid.
- MLX
How to use yuvarajakkole/finance-slm-qwen3-router-lora with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # if on a CUDA device, also pip install mlx[cuda] # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("yuvarajakkole/finance-slm-qwen3-router-lora") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use yuvarajakkole/finance-slm-qwen3-router-lora with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "yuvarajakkole/finance-slm-qwen3-router-lora" --prompt "Once upon a time"
Finance SLM Router (QLoRA)
Overview
Finance SLM Router is a QLoRA adapter built on top of Qwen3-8B for finance intent routing and structured argument extraction.
The model is designed to classify finance requests and prepare structured arguments for downstream deterministic finance tools rather than directly executing financial operations.
Features
- Finance intent routing
- Structured JSON argument extraction
- Journal validation
- Variance analysis
- Policy-aware execution
- Human approval for high-risk operations
- MLX compatible deployment
Base Model
Qwen/Qwen3-8B
Training
- Method: QLoRA
- Framework: MLX-LM
- Fine-tuning Type: LoRA
Supported Tasks
- Journal Validation
- Variance Analysis
- Accounts Payable
- Accounts Receivable
- Treasury
- Payroll
- Finance Routing
Intended Use
This adapter is intended for research, education, and AI engineering demonstrations.
It is not intended to autonomously execute financial transactions or provide financial advice.
Author
Yuvaraj Akkole
- Downloads last month
- 13
Hardware compatibility
Log In to add your hardware
Quantized