arunmcops/FinanceParam-GGUF

FinanceParam - GGUF

Finance - Indian Financial Services  |  BharatGenAI  |  Hindi + English

FinanceParam is BharatGenAI's Indian finance domain specialist, fine-tuned from Param-1-2.9B-Instruct on banking, insurance, taxation, stock markets, mutual funds, and government financial schemes. Designed for financial advisory and literacy in Hindi and English.

---

Available Quantizations

Quantization	File	Size	Description
F16	FinanceParam-F16.gguf	~5.3 GB	Full float 16, near-lossless, GPU recommended
Q2_K	FinanceParam-Q2_K.gguf	~1.2 GB	2-bit, smallest, significant quality loss
Q3_K_M	FinanceParam-Q3_K_M.gguf	~1.4 GB	3-bit medium, moderate quality
Q4_K_M	FinanceParam-Q4_K_M.gguf	~1.7 GB	4-bit medium - recommended for most users
Q5_K_M	FinanceParam-Q5_K_M.gguf	~1.9 GB	5-bit medium, great quality
Q6_K	FinanceParam-Q6_K.gguf	~2.2 GB	6-bit, excellent quality
Q8_0	FinanceParam-Q8_0.gguf	~2.8 GB	8-bit, best quality/size balance

Not sure which to pick?

• Q4_K_M for everyday use on CPU/GPU
• Q8_0 for best quality on GPU with >= 6 GB VRAM
• F16/BF16 for full precision research use

---

Use Cases

• Banking and insurance queries
• Income tax and GST guidance
• Stock market and mutual fund advisory
• Government financial schemes (PM Jan Dhan, etc.)
• Financial literacy and planning
• Loan and EMI calculations

---

Model Details

Property	Value
Base Model	bharatgenai/Param-1-2.9B-Instruct
Architecture	LLaMA (Decoder-only Transformer)
Parameters	~2.9B
Hidden Size	2048
Intermediate Size	7168
Layers	32
Attention Heads	16 (8 KV heads, GQA)
Context Length	4096 tokens
Activation	SiLU
Positional Encoding	RoPE (theta=10000)
Precision	BF16 (original)
Languages	Hindi, English
License	BharatGen Non-Commercial

Training

Fine-tuned from Param-1-2.9B-Instruct with domain-specific Indian finance data covering:

• Banking & Insurance - RBI regulations, bank products, insurance policies, PMJDY, PMSBY
• Taxation - Income Tax, GST, TDS, tax-saving instruments (80C/80D), filing procedures
• Capital Markets - Stock exchanges (BSE/NSE), mutual funds, SIP, SEBI regulations
• Government Schemes - PM Jan Dhan Yojana, Atal Pension Yojana, Sukanya Samriddhi
• Personal Finance - EMI calculations, loan types, credit scores, budgeting

Original Model

Source: bharatgenai/FinanceParam

---

Quick Start

llama.cpp

# Windows
winget install llama.cpp

# Run directly from Hugging Face
llama-cli -hf arunmcops/FinanceParam-GGUF:FinanceParam-Q4_K_M.gguf

# OpenAI-compatible server
llama-server -hf arunmcops/FinanceParam-GGUF:FinanceParam-Q4_K_M.gguf --port 8080

Ollama

ollama run hf.co/arunmcops/FinanceParam-GGUF:FinanceParam-Q4_K_M.gguf

LM Studio / Jan

Search arunmcops/FinanceParam-GGUF in the model browser - GGUF files appear automatically.

Python (llama-cpp-python)

from llama_cpp import Llama

llm = Llama.from_pretrained(
    repo_id="arunmcops/FinanceParam-GGUF",
    filename="FinanceParam-Q4_K_M.gguf",
)

response = llm.create_chat_completion(
    messages=[{"role": "user", "content": "Namaste! Aap kaun hain?"}]
)
print(response["choices"][0]["message"]["content"])

---

About BharatGenAI

BharatGenAI builds open-source language models for India - bilingual (Hindi + English) and domain-specialized for agriculture, healthcare, legal, and general-purpose use.

• GitHub: BharatGenAI
• HuggingFace: arunmcops

---

License

Apache 2.0 - free for personal, research, and commercial use.