GGUF
English
mistral
llama.cpp
ollama
unsloth
indian-law
legal-ai
phi-3
qlora
kanoonu-ai
conversational
Instructions to use tejasgowda05/Kanoonu-AI-Phi3-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use tejasgowda05/Kanoonu-AI-Phi3-GGUF with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf tejasgowda05/Kanoonu-AI-Phi3-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf tejasgowda05/Kanoonu-AI-Phi3-GGUF:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf tejasgowda05/Kanoonu-AI-Phi3-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf tejasgowda05/Kanoonu-AI-Phi3-GGUF:Q4_K_M
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 tejasgowda05/Kanoonu-AI-Phi3-GGUF:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf tejasgowda05/Kanoonu-AI-Phi3-GGUF:Q4_K_M
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 tejasgowda05/Kanoonu-AI-Phi3-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf tejasgowda05/Kanoonu-AI-Phi3-GGUF:Q4_K_M
Use Docker
docker model run hf.co/tejasgowda05/Kanoonu-AI-Phi3-GGUF:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use tejasgowda05/Kanoonu-AI-Phi3-GGUF with Ollama:
ollama run hf.co/tejasgowda05/Kanoonu-AI-Phi3-GGUF:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use tejasgowda05/Kanoonu-AI-Phi3-GGUF with Docker Model Runner:
docker model run hf.co/tejasgowda05/Kanoonu-AI-Phi3-GGUF:Q4_K_M
- Lemonade
How to use tejasgowda05/Kanoonu-AI-Phi3-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull tejasgowda05/Kanoonu-AI-Phi3-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.Kanoonu-AI-Phi3-GGUF-Q4_K_M
List all available models
lemonade list
- Atomic Chat
| FROM KanoonuAi-phi-3-mini-4k-instruct.Q4_K_M.gguf | |
| TEMPLATE """{{ if .System }}<|system|>{{ .System }}<|end|>{{ end }}{{ if .Prompt }}<|user|>{{ .Prompt }}<|end|>{{ end }}<|assistant|>{{ .Response }}<|end|>""" | |
| SYSTEM """You are Kanoonu AI, an intelligent assistant with expertise in Indian law, created by Tejas Gowda. You are highly knowledgeable about the Constitution of India, IPC, CrPC, and other Indian statutes. For legal questions, provide clear and accurate answers based on Indian law. For non-legal questions, answer helpfully as a general assistant. Always clarify that you are not a substitute for professional legal advice.""" | |
| PARAMETER stop "<|end|>" | |
| PARAMETER stop "<|user|>" | |
| PARAMETER stop "<|assistant|>" | |
| PARAMETER temperature 0.3 | |
| PARAMETER top_p 0.85 | |
| PARAMETER top_k 50 | |
| PARAMETER repeat_penalty 1.3 | |
| PARAMETER num_predict 200 |