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

Libraries

How to use msimou/Qwen2-7B-Instruct-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="msimou/Qwen2-7B-Instruct-GGUF",
	filename="Qwen2-7B-Instruct-Q3_K_L.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use msimou/Qwen2-7B-Instruct-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf msimou/Qwen2-7B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf msimou/Qwen2-7B-Instruct-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 msimou/Qwen2-7B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf msimou/Qwen2-7B-Instruct-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 msimou/Qwen2-7B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf msimou/Qwen2-7B-Instruct-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 msimou/Qwen2-7B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf msimou/Qwen2-7B-Instruct-GGUF:Q4_K_M

Use Docker

docker model run hf.co/msimou/Qwen2-7B-Instruct-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use msimou/Qwen2-7B-Instruct-GGUF with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/msimou/Qwen2-7B-Instruct-GGUF:Q4_K_M

Ollama
How to use msimou/Qwen2-7B-Instruct-GGUF with Ollama:
```
ollama run hf.co/msimou/Qwen2-7B-Instruct-GGUF:Q4_K_M
```

Unsloth Studio

How to use msimou/Qwen2-7B-Instruct-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 msimou/Qwen2-7B-Instruct-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 msimou/Qwen2-7B-Instruct-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

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

Docker Model Runner
How to use msimou/Qwen2-7B-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/msimou/Qwen2-7B-Instruct-GGUF:Q4_K_M
```

Lemonade

How to use msimou/Qwen2-7B-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull msimou/Qwen2-7B-Instruct-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen2-7B-Instruct-GGUF-Q4_K_M

List all available models

lemonade list

Qwen2-7B-Instruct-GGUF

Introduction

Qwen2 is the new series of Qwen large language models. For Qwen2, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters, including a Mixture-of-Experts model. This repo contains the instruction-tuned 7B Qwen2 model.

Compared with the state-of-the-art opensource language models, including the previous released Qwen1.5, Qwen2 has generally surpassed most opensource models and demonstrated competitiveness against proprietary models across a series of benchmarks targeting for language understanding, language generation, multilingual capability, coding, mathematics, reasoning, etc.

Qwen2-7B-Instruct supports a context length of up to 131,072 tokens, enabling the processing of extensive inputs. Please refer to this section for detailed instructions on how to deploy Qwen2 for handling long texts.

For more details, please refer to our blog, GitHub, and Documentation.

Model Details

Qwen2 is a language model series including decoder language models of different model sizes. For each size, we release the base language model and the aligned chat model. It is based on the Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, etc. Additionally, we have an improved tokenizer adaptive to multiple natural languages and codes.

Training details

We pretrained the models with a large amount of data, and we post-trained the models with both supervised finetuning and direct preference optimization.

Requirements

The code of Qwen2 has been in the latest Hugging face transformers and we advise you to install transformers>=4.37.0, or you might encounter the following error:

KeyError: 'qwen2'

Getting Started

You can manually download the model using the huggingface-cli (pip install huggingface_hub):

huggingface-cli download msimou/Qwen2-7B-Instruct-GGUF Qwen2-7B-Instruct-Q8_0.gguf --local-dir .

To run Qwen2, you can use the llama-cli (the previous main) or llama-server. We recommend using the llama-server as it is simple and compatible with OpenAI API. For example:

./llama-server -m ./models/Qwen2-7B-Instruct-Q8_0.gguf --port 8000 --host 0.0.0.0 -ngl 28 -fa

(Note: -ngl 28 refers to offloading 24 layers to GPUs, and -fa refers to the use of flash attention.)

Then it is easy to access the service with:

curl --location 'http://localhost:8000/v1/chat/completions' \
--header 'Content-Type: application/json' \
--data '{
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant"
    },
    {
      "role": "user",
      "content": "What is your name?"
    }
  ]
}'

The service is compatible with OpenAI API style.

Evaluation

We briefly compare Qwen2-7B-Instruct with similar-sized instruction-tuned LLMs, including Qwen1.5-7B-Chat. The results are shown below:

Datasets	Llama-3-8B-Instruct	Yi-1.5-9B-Chat	GLM-4-9B-Chat	Qwen1.5-7B-Chat	Qwen2-7B-Instruct
English
MMLU	68.4	69.5	72.4	59.5	70.5
MMLU-Pro	41.0	-	-	29.1	44.1
GPQA	34.2	-	-	27.8	25.3
TheroemQA	23.0	-	-	14.1	25.3
MT-Bench	8.05	8.20	8.35	7.60	8.41
Coding
Humaneval	62.2	66.5	71.8	46.3	79.9
MBPP	67.9	-	-	48.9	67.2
MultiPL-E	48.5	-	-	27.2	59.1
Evalplus	60.9	-	-	44.8	70.3
LiveCodeBench	17.3	-	-	6.0	26.6
Mathematics
GSM8K	79.6	84.8	79.6	60.3	82.3
MATH	30.0	47.7	50.6	23.2	49.6
Chinese
C-Eval	45.9	-	75.6	67.3	77.2
AlignBench	6.20	6.90	7.01	6.20	7.21

References

Downloads last month: 2

GGUF

Model size

8B params

Architecture

qwen2

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

8-bit