Instructions to use prithivMLmods/Minitron-8B-Instruct-200K-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/Minitron-8B-Instruct-200K-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="prithivMLmods/Minitron-8B-Instruct-200K-GGUF",
	filename="Minitron-8B-Instruct-200K-GGUF.F16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use prithivMLmods/Minitron-8B-Instruct-200K-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf prithivMLmods/Minitron-8B-Instruct-200K-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf prithivMLmods/Minitron-8B-Instruct-200K-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf prithivMLmods/Minitron-8B-Instruct-200K-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf prithivMLmods/Minitron-8B-Instruct-200K-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 prithivMLmods/Minitron-8B-Instruct-200K-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf prithivMLmods/Minitron-8B-Instruct-200K-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 prithivMLmods/Minitron-8B-Instruct-200K-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf prithivMLmods/Minitron-8B-Instruct-200K-GGUF:Q4_K_M

Use Docker

docker model run hf.co/prithivMLmods/Minitron-8B-Instruct-200K-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use prithivMLmods/Minitron-8B-Instruct-200K-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/Minitron-8B-Instruct-200K-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/Minitron-8B-Instruct-200K-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/prithivMLmods/Minitron-8B-Instruct-200K-GGUF:Q4_K_M

Ollama
How to use prithivMLmods/Minitron-8B-Instruct-200K-GGUF with Ollama:
```
ollama run hf.co/prithivMLmods/Minitron-8B-Instruct-200K-GGUF:Q4_K_M
```

Unsloth Studio new

How to use prithivMLmods/Minitron-8B-Instruct-200K-GGUF 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 prithivMLmods/Minitron-8B-Instruct-200K-GGUF 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 prithivMLmods/Minitron-8B-Instruct-200K-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for prithivMLmods/Minitron-8B-Instruct-200K-GGUF to start chatting

Docker Model Runner
How to use prithivMLmods/Minitron-8B-Instruct-200K-GGUF with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/Minitron-8B-Instruct-200K-GGUF:Q4_K_M
```

Lemonade

How to use prithivMLmods/Minitron-8B-Instruct-200K-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull prithivMLmods/Minitron-8B-Instruct-200K-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Minitron-8B-Instruct-200K-GGUF-Q4_K_M

List all available models

lemonade list

Minitron-8B-Instruct-200K-GGUF

Attribute	Description
Developed by	prithivMLmods
License	creativeml-openrail-m
Finetuned from model	nvidia/Mistral-NeMo-Minitron-8B-Instruct

Model File

File Name	Size	Description
`.gitattributes`	1.83kB	Git configuration file specifying attributes and LFS rules.
`Minitron-8B-Instruct-200K-GGUF.F16.gguf`	16.8GB	Full precision 16-bit float model file for Minitron 8B with 200K steps.
`Minitron-8B-Instruct-200K-GGUF.Q4_K_M.gguf`	5.15GB	Quantized 4-bit model file, optimized for memory usage.
`Minitron-8B-Instruct-200K-GGUF.Q5_K_M.gguf`	6GB	Quantized 5-bit model file, balanced for performance and accuracy.
`Minitron-8B-Instruct-200K-GGUF.Q8_0.gguf`	8.95GB	Quantized 8-bit model file, moderate accuracy and memory optimization.
`README.md`	76B	Markdown file with project information and instructions.
`config.json`	33B	JSON configuration file for setting model parameters.

Run with Ollama 🦙

Download and Install Ollama

To get started, download Ollama from https://ollama.com/download and install it on your Windows or Mac system.

Run Your Own Model in Minutes

Steps to Run GGUF Models:

1. Create the Model File

Name your model file appropriately, for example, metallama200.

2. Add the Template Command

Include a FROM line with the base model file. For instance:
```
FROM Llama-3.2-8B-GGUF-200K
```
Make sure the model file is in the same directory as your script.

3. Create and Patch the Model

Use the following command in your terminal to create and patch your model:
```
ollama create metallama200 -f ./metallama200
```
Upon success, a confirmation message will appear.
To verify that the model was created successfully, run:
```
ollama list
```
Ensure that metallama200 appears in the list of models.

Running the Model

To run the model, use:

ollama run metallama200

Sample Usage

In the command prompt, run:

D:\>ollama run metallama200

Example interaction:

>>> write a mini passage about space x
Space X, the private aerospace company founded by Elon Musk, is revolutionizing the field of space exploration.
With its ambitious goals to make humanity a multi-planetary species and establish a sustainable human presence in
the cosmos, Space X has become a leading player in the industry. The company's spacecraft, like the Falcon 9, have
demonstrated remarkable capabilities, allowing for the transport of crews and cargo into space with unprecedented
efficiency. As technology continues to advance, the possibility of establishing permanent colonies on Mars becomes
increasingly feasible, thanks in part to the success of reusable rockets that can launch multiple times without
sustaining significant damage. The journey towards becoming a multi-planetary species is underway, and Space X
plays a pivotal role in pushing the boundaries of human exploration and settlement.

Downloads last month: 42

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

4-bit

5-bit

8-bit

16-bit

Model tree for prithivMLmods/Minitron-8B-Instruct-200K-GGUF

Base model

nvidia/Mistral-NeMo-Minitron-8B-Base

Finetuned

nvidia/Mistral-NeMo-Minitron-8B-Instruct

Quantized

(13)

this model

prithivMLmods
/

Minitron-8B-Instruct-200K-GGUF