Text Generation
PEFT
Safetensors
English
lora
qlora
sft
legal-ai
tax-law
indian-tax
retrieval-augmented-generation
citation-verification
conversational
Instructions to use JayNagose/LLaMa-3.2-tax-basic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use JayNagose/LLaMa-3.2-tax-basic with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/llama-3-8b-Instruct-bnb-4bit") model = PeftModel.from_pretrained(base_model, "JayNagose/LLaMa-3.2-tax-basic") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Update README.md
Verified signatureefcbf85 -
Update README.md
Verified signature4922875 -
my first finetuned model for Tax-logic
Verified signature--- base_model: meta-llama/Llama-3.2-8B-Instruct library_name: peft pipeline_tag: text-generation language: - en tags: - lora - qlora - sft - legal-ai - tax-law - indian-tax - retrieval-augmented-generation - citation-verification license: apache-2.0 datasets: - custom --- # Tax-LLaMA-Ind: Indian Tax Law Expert Model A fine-tuned LLaMA 3.2 8B model specialized in Indian Income Tax Act, 1961. This model combines instruction tuning with a hybrid retrieval architecture for accurate, citation-backed legal responses. ## Model Description Tax-LLaMA-Ind is a domain-specialized language model for Indian tax law, featuring: - **Base Model:** meta-llama/Llama-3.2-8B-Instruct - **Fine-tuning Method:** QLoRA (Quantized Low-Rank Adaptation) - **Domain:** Indian Income Tax Act, 1961 - **Architecture:** Hybrid RAG with Knowledge Graph integration - **Citation Verification:** Built-in hallucination detection ### Key Features ✅ **Accurate Legal Citations** - 94.3% citation accuracy with KG valid…c840982
-
initial commit
Verified signatured5ca9cb