Instructions to use mgonzs13/Mistroll-7B-v2.2-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mgonzs13/Mistroll-7B-v2.2-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mgonzs13/Mistroll-7B-v2.2-GGUF",
	filename="Mistroll-7B-v2.2.IQ4_XS.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 mgonzs13/Mistroll-7B-v2.2-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mgonzs13/Mistroll-7B-v2.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mgonzs13/Mistroll-7B-v2.2-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 mgonzs13/Mistroll-7B-v2.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mgonzs13/Mistroll-7B-v2.2-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 mgonzs13/Mistroll-7B-v2.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mgonzs13/Mistroll-7B-v2.2-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 mgonzs13/Mistroll-7B-v2.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mgonzs13/Mistroll-7B-v2.2-GGUF:Q4_K_M

Use Docker

docker model run hf.co/mgonzs13/Mistroll-7B-v2.2-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use mgonzs13/Mistroll-7B-v2.2-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mgonzs13/Mistroll-7B-v2.2-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": "mgonzs13/Mistroll-7B-v2.2-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mgonzs13/Mistroll-7B-v2.2-GGUF:Q4_K_M

Ollama
How to use mgonzs13/Mistroll-7B-v2.2-GGUF with Ollama:
```
ollama run hf.co/mgonzs13/Mistroll-7B-v2.2-GGUF:Q4_K_M
```

Unsloth Studio new

How to use mgonzs13/Mistroll-7B-v2.2-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 mgonzs13/Mistroll-7B-v2.2-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 mgonzs13/Mistroll-7B-v2.2-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mgonzs13/Mistroll-7B-v2.2-GGUF to start chatting

Docker Model Runner
How to use mgonzs13/Mistroll-7B-v2.2-GGUF with Docker Model Runner:
```
docker model run hf.co/mgonzs13/Mistroll-7B-v2.2-GGUF:Q4_K_M
```

Lemonade

How to use mgonzs13/Mistroll-7B-v2.2-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mgonzs13/Mistroll-7B-v2.2-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Mistroll-7B-v2.2-GGUF-Q4_K_M

List all available models

lemonade list

Mistroll-7B-v2.2-GGUF

Model creator: BarraHome
Original model: Mistroll-7B-v2.2
GGUF quantization: llama.cpp commit 6e472f58e40cd4acf6023e15c75a2700535c5f0b

Description

This model was trained 2x faster with Unsloth and Huggingface's TRL library.

This experiment serves to test and refine a specific training and evaluation pipeline research framework. Its primary objective is to identify potential optimizations, with a focus on data engineering, architectural efficiency, and evaluation performance.

The goal of this experiment is to evaluate the effectiveness of a new training and evaluation pipeline for Large Language Models (LLMs). To achieve this, we will explore adjustments in data preprocessing, model training algorithms, and evaluation metrics to test methods for improvement.

Prompt Template

Following the Mistroll chat template, the prompt template is ChatML.

<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Downloads last month: 50

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

32-bit

Model tree for mgonzs13/Mistroll-7B-v2.2-GGUF

Base model

yam-peleg/Experiment26-7B

Quantized

BarraHome/Mistroll-7B-v2.2

Quantized

(5)

this model