CelesteImperia/Llama-3-8B-Indian-Finance-Quant-v2.0-RELEASE

Llama-3-8B Indian Finance Quant (v2.0 Gold)

The specialized reasoning engine for the Indian Equity Ecosystem. This is a high-precision LoRA adapter for Llama-3-8B, fine-tuned specifically to decode the complexities of Indian corporate actions, SEBI/RBI regulatory shifts, and Nifty 50 equity analysis.

---

⚠️ IMPORTANT UPDATE (April 2026): > A significantly upgraded version of this model is now available. Indian Finance Quant v2.1 - DeepSeek Reasoning Edition has been released, featuring a "Dual-Brain" architecture capable of synthesizing technical indicators, live market sentiment, and complex regulatory/legal constraints using native <think> reasoning chains. Please migrate to v2.1 for all "Indian Finance Quant" deployments.

---

🐍 For Python Users (Transformers/PEFT)

To get the best results, use the 4-bit quantization provided by bitsandbytes.

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "unsloth/llama-3-8b-Instruct-bnb-4bit"
model = AutoModelForCausalLM.from_pretrained(
    model_id, 
    load_in_4bit=True, 
    torch_dtype=torch.float16, 
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_id)

# Loading the Indian Finance Gold Adapter
model = PeftModel.from_pretrained(model, "CelesteImperia/Llama-3-8B-Indian-Finance-Quant-v2.0-RELEASE")

prompt = "Analyze HDFC Bank's guidance for lower deposit growth in Q3 and its impact on NIM."
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")

with torch.no_grad():
    outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.2, top_p=0.9)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))

---

💻 For C# / .NET Users (LLamaSharp Implementation)

As a Senior .NET developer, I have validated this model for local C# integration using LLamaSharp. This is ideal for building local Indian Finance desktop tools.

using LLama.Common;
using LLama;

// 1. Load the Base GGUF Model (Llama-3-8B)
var parameters = new ModelParams("path/to/llama-3-8b-instruct.gguf") {
    ContextSize = 4096,
    GpuLayerCount = 32 // Optimized for RTX 3090/A4000
};

using var weights = LLamaWeights.LoadFromFile(parameters);

// 2. Apply the Indian Finance LoRA Adapter
weights.ApplyLoraFromFile("path/to/Indian-Finance-Quant-v2.0-F16.gguf");

using var context = weights.CreateContext(parameters);
var executor = new InteractiveExecutor(context);

// 3. Run Financial Reasoning
var chatSession = new ChatSession(executor);
var query = "What is the impact of a 25bps RBI Repo Rate hike on Indian NBFC borrowing costs?";

await foreach (var text in chatSession.ChatAsync(new ChatHistory.Message(AuthorRole.User, query))) {
    Console.Write(text);
}

---

📜 v2.0 Gold Release: Change Log

The v2.0 Gold edition represents a significant architectural shift from the initial v1.1 release, moving from general fine-tuning to specialized financial reasoning.

🛠️ Key Technical Upgrades:

• Logic Engine: Transitioned from Standard Prompting to Chain of Thought (CoT) Reasoning, allowing the model to "think through" banking ratios before providing a final verdict.
• Dataset Curation: Replaced raw transcripts with Expert-Labelled Financial Pairs, focusing on Nifty 50 quarterly guidance and SEBI 2025/2026 regulatory shifts.
• Optimization: Fully integrated with the Unsloth Engine, resulting in 2.3x faster inference and 70% less VRAM usage compared to v1.0.
• Banking Vertical: Specialized training on Net Interest Margin (NIM), CASA ratios, and Loan-to-Deposit (LDR) dynamics unique to the Indian private and PSU banking sectors.
• Context Stability: Rock-solid performance up to 8k tokens, enabling the analysis of full "Management Discussion & Analysis" sections.

---

🎯 Sample Prompting Guide (Gold Standard Tests)

To see the v2.0 Gold difference, try these complex "Institutional-Grade" queries. These are designed to test the model's ability to reason, not just retrieve facts.

Test Case 1: Banking NIM Pressure

Prompt: "A private sector bank reports a 10% increase in credit growth but a 20% spike in bulk deposit reliance. How will this impact their NIM in the next two quarters?"

Expected Reasoning: The model should identify that a reliance on high-cost bulk deposits, despite credit growth, will lead to a "cost of funds" spike that outpaces "yield on advances," resulting in compressed Net Interest Margins.

Test Case 2: Regulatory Impact (SEBI/RBI)

Prompt: "Analyze the impact of the latest RBI circular on 'Unsecured Lending' risk weights for a mid-sized Indian NBFC."

Expected Reasoning: The model should reason that higher risk weights lead to a lower Capital Adequacy Ratio (CAR), forcing the NBFC to either raise fresh equity capital or slow down its high-yield personal loan book.

Test Case 3: Corporate Actions & Sentiment

Prompt: "A Nifty 50 company announces a 1:10 stock split alongside a surprise 50% dividend hike. What is the likely short-term impact on retail liquidity and institutional sentiment?"

Expected Reasoning: It should differentiate between the "psychological liquidity" boost for retail investors (due to the split) and the "strong cash-flow signal" for institutions (due to the dividend), likely leading to an accumulation phase.

---

🏗️ Technical Forge & Infrastructure

• Model Type: LoRA Adapter (PEFT / Unsloth)
• Architecture: Llama-3-8B (v2.0 Gold Release)
• Training Workstation: Dual-GPU (NVIDIA RTX 3090 24GB + RTX A4000 16GB)
• Memory: 64GB DDR4
• Engine: Unsloth (Optimized for zero-latency financial reasoning)

---

📜 License & Disclaimer

License: This project is licensed under the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0).

What this means:

• Attribution: You must give appropriate credit to Celeste Imperia (Abhishek Jaiswal).
• Non-Commercial: You may not use this model or its outputs for commercial purposes.
• ShareAlike: If you remix or build upon this work, you must distribute your contributions under the same license.

Disclaimer: This model is provided as an educational and research tool only. It does not constitute financial advice. Financial markets involve significant risk. Always consult a SEBI-registered professional before making any investment decisions. Celeste Imperia and its architects are not liable for any financial losses incurred through the use of this AI.

---

☕ Support the Forge

Maintaining a dual-GPU AI workstation and hosting high-bandwidth models requires significant resources. If our open-source tools power your projects, consider supporting our development:

Platform	Support Link
Global & India	Support via Razorpay

Scan to support via UPI (India Only):

---

Connect with the architect: Abhishek Jaiswal on LinkedIn