Downloads · 30 days
43
41% of all-time downloads
dennisonb/qwen25-tax-3b-GGUF
qwen25-tax-3b-GGUF is a text generation model from dennisonb. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
A fine-tuned version of Qwen/Qwen2.5-3B-Instruct trained on the IRS tax code using a 3-stage training pipeline. This repository contains the quantized GGUF model for local inference via llama.cpp, Ollama, or compatibl…
Downloads · 30 days
43
41% of all-time downloads
All-time downloads
106
Public
Repo size
3.3 GB
Likes
0
Public
Click a slice to open those files.
.gguf3.3 GB · 100%
From the Hugging Face model README
A fine-tuned version of Qwen/Qwen2.5-3B-Instruct trained on the IRS tax code using a 3-stage training pipeline. This repository contains the quantized GGUF model for local inference via llama.cpp, Ollama, or compatible runtimes.
| Property | Value |
|---|---|
| Base Model | Qwen/Qwen2.5-3B-Instruct |
| Parameters | ~3 Billion |
| Quantization | q8_0 (8-bit, high quality) |
| Format | GGUF |
| License | Apache 2.0 |
| Training Domain | IRS Tax Code / US Federal Tax Law |
This model was produced by a 3-stage fine-tuning pipeline applied to Qwen 2.5 3B Instruct:
The base instruct model was fine-tuned with LoRA adapters on a curated dataset of IRS tax code passages, definitions, and question-answer pairs. This stage establishes domain knowledge and instills the correct response format for tax-related queries.
Using pairs of preferred and rejected responses to tax questions, DPO training aligned the model to produce accurate, well-structured answers that reflect correct tax law interpretation over hallucinated or misleading responses.
GRPO reinforcement learning was applied to further optimize response quality using a reward model that evaluated accuracy, completeness, and citation of relevant tax code sections. This stage improves the model's ability to reason through multi-step tax scenarios.
| File | Description |
|---|---|
qwen25-tax-3b-q8_0.gguf | q8_0 quantized GGUF for local inference |
The raw LoRA adapter weights for all three training stages are available in the companion repository: dennisonb/qwen25-tax-3b-adapters
ollama create qwen25-tax-3b -f Modelfile
ollama run qwen25-tax-3b "What is the standard deduction for a single filer in 2024?"
./llama-cli -m qwen25-tax-3b-q8_0.gguf -p "What are the income limits for contributing to a Roth IRA?" -n 512
This model is intended as a research and educational tool for exploring IRS tax code information. It is not a substitute for professional tax advice. Always consult a qualified tax professional for your specific situation.
Apache 2.0 — see LICENSE