Instructions to use MBASE/Qwen2.5-7B-Instruct-1M-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MBASE/Qwen2.5-7B-Instruct-1M-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="MBASE/Qwen2.5-7B-Instruct-1M-GGUF",
	filename="Qwen2.5-7B-Instruct-1M-q4_0.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 MBASE/Qwen2.5-7B-Instruct-1M-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf MBASE/Qwen2.5-7B-Instruct-1M-GGUF:Q4_0
# Run inference directly in the terminal:
llama-cli -hf MBASE/Qwen2.5-7B-Instruct-1M-GGUF:Q4_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf MBASE/Qwen2.5-7B-Instruct-1M-GGUF:Q4_0
# Run inference directly in the terminal:
llama-cli -hf MBASE/Qwen2.5-7B-Instruct-1M-GGUF:Q4_0

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 MBASE/Qwen2.5-7B-Instruct-1M-GGUF:Q4_0
# Run inference directly in the terminal:
./llama-cli -hf MBASE/Qwen2.5-7B-Instruct-1M-GGUF:Q4_0

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 MBASE/Qwen2.5-7B-Instruct-1M-GGUF:Q4_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf MBASE/Qwen2.5-7B-Instruct-1M-GGUF:Q4_0

Use Docker

docker model run hf.co/MBASE/Qwen2.5-7B-Instruct-1M-GGUF:Q4_0

LM Studio
Jan

vLLM

How to use MBASE/Qwen2.5-7B-Instruct-1M-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MBASE/Qwen2.5-7B-Instruct-1M-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": "MBASE/Qwen2.5-7B-Instruct-1M-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MBASE/Qwen2.5-7B-Instruct-1M-GGUF:Q4_0

Ollama
How to use MBASE/Qwen2.5-7B-Instruct-1M-GGUF with Ollama:
```
ollama run hf.co/MBASE/Qwen2.5-7B-Instruct-1M-GGUF:Q4_0
```

Unsloth Studio new

How to use MBASE/Qwen2.5-7B-Instruct-1M-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 MBASE/Qwen2.5-7B-Instruct-1M-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 MBASE/Qwen2.5-7B-Instruct-1M-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for MBASE/Qwen2.5-7B-Instruct-1M-GGUF to start chatting

Pi new

How to use MBASE/Qwen2.5-7B-Instruct-1M-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf MBASE/Qwen2.5-7B-Instruct-1M-GGUF:Q4_0

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "MBASE/Qwen2.5-7B-Instruct-1M-GGUF:Q4_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use MBASE/Qwen2.5-7B-Instruct-1M-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf MBASE/Qwen2.5-7B-Instruct-1M-GGUF:Q4_0

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default MBASE/Qwen2.5-7B-Instruct-1M-GGUF:Q4_0

Run Hermes

hermes

Docker Model Runner
How to use MBASE/Qwen2.5-7B-Instruct-1M-GGUF with Docker Model Runner:
```
docker model run hf.co/MBASE/Qwen2.5-7B-Instruct-1M-GGUF:Q4_0
```

Lemonade

How to use MBASE/Qwen2.5-7B-Instruct-1M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull MBASE/Qwen2.5-7B-Instruct-1M-GGUF:Q4_0

Run and chat with the model

lemonade run user.Qwen2.5-7B-Instruct-1M-GGUF-Q4_0

List all available models

lemonade list

Qwen 2.5 7B Instruct 1M

Original Author : Qwen.
Model Owner: Qwen.
Original Repository: Qwen/Qwen2.5-7B-Instruct-1M.
Conversion Tool: llama.cpp.

Description

This repo contains Qwen2.5-7B-Instruct-1M model in gguf format to be leveraged by LLM inference engines that can process GGUF file.

Conversion Process

Original model Qwen safetensors are converted using the llama.cpp model conversion script.

The default configuration applied during the conversion process. In other words, neither the imatrix applied or the GGUF parameters altered.

For detailed information about the conversion process: Converting to GGUF

MBASE GGUF Documentation

For general information about GGUF files: About GGUF Files

Chat Template

<|im_start|>{system_prompt}
<|im_end|>
<|im_start|>{user_prompt}
<|im_end|>
<|im_start|>{assistant_response}
<|im_end|>

Disclaimer

MBASE Software Corporation is a software company officially registered as (MBASE Yazılım A.Ş.) in Turkey (https://www.mbasesoftware.com). Throughout this document, references to MBASE Software Corporation or MBASE refer to the (MBASE Yazılım A.Ş.)

MBASE is not the creator, originator, or owner of the model featured in this repository. This model is created and provided by third parties. MBASE does not endorse, support, or guarantee the completeness, accuracy, or reliability of the model or its outputs.

You understand that the model can generate content that may be offensive, harmful, inaccurate, inappropriate, or deceptive. Responsibility for the model and its outputs lies solely with the entity or individual who created and provided the model. MBASE does not monitor or control the model's outputs and disclaims any liability arising from its use.

MBASE provides no warranties regarding the accuracy, reliability, or fitness of the model for any particular purpose. Additionally, MBASE disclaims any guarantees that the model will operate without errors, interruptions, viruses, or other issues. You are solely responsible for any consequences resulting from the use or access of this model, including any damage caused by downloading or utilizing it.

Downloads last month: 43

GGUF

Model size

8B params

Architecture

qwen2

Hardware compatibility

4-bit

8-bit