Instructions to use Digiedze/BFSI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Digiedze/BFSI with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Digiedze/BFSI",
	filename="astra-llm.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Digiedze/BFSI with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Digiedze/BFSI
# Run inference directly in the terminal:
llama-cli -hf Digiedze/BFSI

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Digiedze/BFSI
# Run inference directly in the terminal:
llama-cli -hf Digiedze/BFSI

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Digiedze/BFSI
# Run inference directly in the terminal:
./llama-cli -hf Digiedze/BFSI

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Digiedze/BFSI
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Digiedze/BFSI

Use Docker

docker model run hf.co/Digiedze/BFSI

LM Studio
Jan
Ollama
How to use Digiedze/BFSI with Ollama:
```
ollama run hf.co/Digiedze/BFSI
```

Unsloth Studio new

How to use Digiedze/BFSI with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Digiedze/BFSI to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Digiedze/BFSI to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Digiedze/BFSI to start chatting

Docker Model Runner
How to use Digiedze/BFSI with Docker Model Runner:
```
docker model run hf.co/Digiedze/BFSI
```

Lemonade

How to use Digiedze/BFSI with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Digiedze/BFSI

Run and chat with the model

lemonade run user.BFSI-{{QUANT_TAG}}

List all available models

lemonade list

BFSI

File size: 563 Bytes

f671bb7

# Astra LLM (BFSI Domain)

## Overview
A domain-adapted Large Language Model built on Mistral 7B, fine-tuned using LoRA for financial intelligence tasks.

## Capabilities
- Credit card optimization
- Financial insights & recommendations
- Fraud/scam reasoning
- Insurance claim understanding

## Architecture
- Base Model: Mistral 7B
- Fine-tuning: LoRA
- Deployment: Ollama
- Format: GGUF

## Integration
- RAG with Qdrant
- Multi-agent orchestration (LangGraph)
- Used in Astra 360 Digital Brain

## Usage (Ollama)
ollama run astra-llm

## Author
Pramod Seeram