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

Libraries

How to use Ujjansh/Smarttalk with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Ujjansh/Smarttalk",
	filename="Llama-3.2-1B-Instruct.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Ujjansh/Smarttalk 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 Ujjansh/Smarttalk:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Ujjansh/Smarttalk:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Ujjansh/Smarttalk:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Ujjansh/Smarttalk: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 Ujjansh/Smarttalk:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Ujjansh/Smarttalk: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 Ujjansh/Smarttalk:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Ujjansh/Smarttalk:Q4_K_M

Use Docker

docker model run hf.co/Ujjansh/Smarttalk:Q4_K_M

LM Studio
Jan
Ollama
How to use Ujjansh/Smarttalk with Ollama:
```
ollama run hf.co/Ujjansh/Smarttalk:Q4_K_M
```

Unsloth Studio

How to use Ujjansh/Smarttalk 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 Ujjansh/Smarttalk 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 Ujjansh/Smarttalk to start chatting

Using HuggingFace Spaces for Unsloth

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

Atomic Chat new
Docker Model Runner
How to use Ujjansh/Smarttalk with Docker Model Runner:
```
docker model run hf.co/Ujjansh/Smarttalk:Q4_K_M
```

Lemonade

How to use Ujjansh/Smarttalk with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Ujjansh/Smarttalk:Q4_K_M

Run and chat with the model

lemonade run user.Smarttalk-Q4_K_M

List all available models

lemonade list

Smarttalk / README.md

Ujjansh

Update README.md

9150f81 verified 26 days ago

preview code

Raw

History Blame Contribute Delete

511 Bytes

metadata

license: apache-2.0
tags:
  - gguf
  - llama.cpp
  - qwen
  - llama
  - gemma
  - phi
  - smollm
  - quantized
  - edge-ai
  - iot
  - smart-home
  - llm
  - inference

Lightweight GGUF LLM Collection (Edge AI / IoT Ready)

Overview

This repository contains a collection of quantized GGUF models optimized for edge devices, CPU inference, and IoT applications.

These models are designed for:

Smart home assistants
Lightweight chat systems
Offline inference
Jetson / Raspberry Pi / CPU-only environments