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

Libraries

How to use lmstudio-community/WizardLM-2-7B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="lmstudio-community/WizardLM-2-7B-GGUF",
	filename="WizardLM-2-7B-IQ1_M.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use lmstudio-community/WizardLM-2-7B-GGUF with llama.cpp:

Install from brew

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

Use Docker

docker model run hf.co/lmstudio-community/WizardLM-2-7B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use lmstudio-community/WizardLM-2-7B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lmstudio-community/WizardLM-2-7B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lmstudio-community/WizardLM-2-7B-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/lmstudio-community/WizardLM-2-7B-GGUF:Q4_K_M

Ollama
How to use lmstudio-community/WizardLM-2-7B-GGUF with Ollama:
```
ollama run hf.co/lmstudio-community/WizardLM-2-7B-GGUF:Q4_K_M
```

Unsloth Studio new

How to use lmstudio-community/WizardLM-2-7B-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 lmstudio-community/WizardLM-2-7B-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 lmstudio-community/WizardLM-2-7B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

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

Docker Model Runner
How to use lmstudio-community/WizardLM-2-7B-GGUF with Docker Model Runner:
```
docker model run hf.co/lmstudio-community/WizardLM-2-7B-GGUF:Q4_K_M
```

Lemonade

How to use lmstudio-community/WizardLM-2-7B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull lmstudio-community/WizardLM-2-7B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.WizardLM-2-7B-GGUF-Q4_K_M

List all available models

lemonade list

💫 Community Model> WizardLM-2-7B by Microsoft

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord.

Model creator: Microsoft
Original model: WizardLM-2-7B
GGUF quantization: provided by bartowski based on llama.cpp release b2675

Model Summary:

WizardLM 2 7B is a followup model to the original and highly successful WizardLM line of models. This model is trained to excel at multi-turn conversations, and does so very successfully, outclassing models more than twice its size.
This model should be used for general conversation and world knowledge, but as with most models these days will be relatively competent at coding and reasoning as well.

Prompt Template:

For now, you'll need to make your own template. Choose the LM Studio Blank Preset in your LM Studio.

Then, set the system prompt to whatever you'd like (check the recommended one below), and set the following values:
System Message Suffix: ''
User Message Prefix: ' USER: '
User Message Suffix: ' ASSISTANT: '

Under the hood, the model will see a prompt that's formatted like so:

A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT: </s>

Use case and examples

WizardLM 2 was tuned for improved performance on complex chat, multilingual, reasoning and agent tasks. This makes it a great model to use when wanting to chat back and forth and have reasoning based discussions.

World knowledge:

Conversational:

Coding:

Technical Details

WizardLM 2 applies several new methods for training compared to the original iteration, truly showing just how much the Open Source AI world has advanced since their intial offerings.

The first of which is Progress Learning. Rather than applying all training data at once, the team applied stage-by-stage training by partitioning the data into multiple sections and training on each one after the other.

AI Align AI (AAA) is another new process, whereby various state-of-the-art LLMs are allowed to co-teach and improve from each other, using simulated chats, quality judging, and improvement suggestions. They also participate in self-teaching in a similar manor.

The model then underwent Supervised Learning, Stage-DPO, and Evol-Instruct and Instruction&Process Supervised Reinforcement Learning (RLEIF) which uses an instruction quality reward model and a supervision reward model for more precise correctness.

The results are a model that performs exceptionally well on the automatic MT-Bench evaluation.

For more information, check the WizardLM2 blog post here

Special thanks

🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible.

🙏 Special thanks to Kalomaze for his dataset (linked here) that was used for calculating the imatrix for these quants, which improves the overall quality!

Disclaimers

LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

Downloads last month: 768

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

1-bit

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit