llama-aica

Llama-3.1-8B-Instruct LoRA Fine-tuned on Indian Accounting Standards (Ind AS)

This model is a LoRA (Low-Rank Adaptation) fine-tuned version of meta-llama/Llama-3.1-8B-Instruct, specifically trained on Indian Accounting Standards (Ind AS) data.

Model Details

• Base Model: meta-llama/Llama-3.1-8B-Instruct (latest Meta model)
• Fine-tuning Method: LoRA (Low-Rank Adaptation)
• Training Data: 269 high-quality examples covering Indian Accounting Standards
• Domain: Finance and Accounting (India-specific)
• Language: English

Training Details

• Training Epochs: 3
• LoRA Rank: 64
• LoRA Alpha: 16
• Learning Rate: 2e-4
• Batch Size: 8 (effective)
• Max Sequence Length: 2048
• Quantization: 4-bit (nf4)

Use Cases

This model is designed to answer questions about:

• Indian Accounting Standards (Ind AS)
• Financial statement presentation
• Balance sheet preparation
• Profit and loss statements
• Cash flow statements
• Accounting policies and disclosures
• Going concern assessments
• Asset and liability classification

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

# Load base model (requires Meta approval)
base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.1-8B-Instruct")
tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.1-8B-Instruct")

# Load LoRA weights
model = PeftModel.from_pretrained(base_model, "your-username/llama-3.1-8b-indas-lora")

# Use the model for inference
prompt = "Define the objective of Ind AS 1."
inputs = tokenizer.encode(prompt, return_tensors="pt")
outputs = model.generate(inputs, max_new_tokens=512)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)

Base Model Notes

• Uses official meta-llama/Llama-3.1-8B-Instruct
• Latest generation with improved instruction following
• Better performance on complex reasoning tasks
• Requires Meta approval but usually granted quickly
• Enhanced capabilities compared to Llama 2

Limitations

• This model is specifically trained on Indian Accounting Standards and may not perform well on other accounting standards (IFRS, US GAAP, etc.)
• The training data focuses on Ind AS 1 and related standards
• Responses should be verified with official accounting standards documents
• Not suitable for providing legal or investment advice

Training Infrastructure

• Platform: Google Colab Pro+
• GPU: T4/A100 (depending on availability)
• Memory Optimization: 4-bit quantization with LoRA

Citation

If you use this model, please cite:

@misc{llama3.1-indas-lora,
  title={Llama-3.1-8B-Instruct LoRA Fine-tuned on Indian Accounting Standards},
  author={Your Name},
  year={2024},
  url={https://huggingface.co/your-username/llama-3.1-8b-indas-lora}
}