Instructions to use mradermacher/wizardllama-7b-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mradermacher/wizardllama-7b-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mradermacher/wizardllama-7b-GGUF", dtype="auto")

llama-cpp-python

How to use mradermacher/wizardllama-7b-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mradermacher/wizardllama-7b-GGUF",
	filename="wizardllama-7b.IQ3_M.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use mradermacher/wizardllama-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 mradermacher/wizardllama-7b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mradermacher/wizardllama-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 mradermacher/wizardllama-7b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mradermacher/wizardllama-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 mradermacher/wizardllama-7b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mradermacher/wizardllama-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 mradermacher/wizardllama-7b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mradermacher/wizardllama-7b-GGUF:Q4_K_M

Use Docker

docker model run hf.co/mradermacher/wizardllama-7b-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use mradermacher/wizardllama-7b-GGUF with Ollama:
```
ollama run hf.co/mradermacher/wizardllama-7b-GGUF:Q4_K_M
```

Unsloth Studio

How to use mradermacher/wizardllama-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 mradermacher/wizardllama-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 mradermacher/wizardllama-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 mradermacher/wizardllama-7b-GGUF to start chatting

Docker Model Runner
How to use mradermacher/wizardllama-7b-GGUF with Docker Model Runner:
```
docker model run hf.co/mradermacher/wizardllama-7b-GGUF:Q4_K_M
```

Lemonade

How to use mradermacher/wizardllama-7b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mradermacher/wizardllama-7b-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.wizardllama-7b-GGUF-Q4_K_M

List all available models

lemonade list

mradermacher commited on May 6, 2024

Commit

6121ec4

verified ·

1 Parent(s): f54e971

auto-patch README.md

Browse files

Files changed (1) hide show

README.md +1 -2

README.md CHANGED Viewed

@@ -37,7 +37,7 @@ more details, including on how to concatenate multi-part files.
 | [GGUF](https://huggingface.co/mradermacher/wizardllama-7b-GGUF/resolve/main/wizardllama-7b.Q3_K_L.gguf) | Q3_K_L | 3.9 |  |
 | [GGUF](https://huggingface.co/mradermacher/wizardllama-7b-GGUF/resolve/main/wizardllama-7b.IQ4_XS.gguf) | IQ4_XS | 3.9 |  |
 | [GGUF](https://huggingface.co/mradermacher/wizardllama-7b-GGUF/resolve/main/wizardllama-7b.Q4_0.gguf) | Q4_0 | 4.1 | fast, low quality |
-| [GGUF](https://huggingface.co/mradermacher/wizardllama-7b-GGUF/resolve/main/wizardllama-7b.IQ4_NL.gguf) | IQ4_NL | 4.1 | slightly worse than Q4_K_S |
 | [GGUF](https://huggingface.co/mradermacher/wizardllama-7b-GGUF/resolve/main/wizardllama-7b.Q4_K_S.gguf) | Q4_K_S | 4.1 | fast, recommended |
 | [GGUF](https://huggingface.co/mradermacher/wizardllama-7b-GGUF/resolve/main/wizardllama-7b.Q4_K_M.gguf) | Q4_K_M | 4.3 | fast, recommended |
 | [GGUF](https://huggingface.co/mradermacher/wizardllama-7b-GGUF/resolve/main/wizardllama-7b.Q5_K_S.gguf) | Q5_K_S | 4.9 |  |
@@ -45,7 +45,6 @@ more details, including on how to concatenate multi-part files.
 | [GGUF](https://huggingface.co/mradermacher/wizardllama-7b-GGUF/resolve/main/wizardllama-7b.Q6_K.gguf) | Q6_K | 5.8 | very good quality |
 | [GGUF](https://huggingface.co/mradermacher/wizardllama-7b-GGUF/resolve/main/wizardllama-7b.Q8_0.gguf) | Q8_0 | 7.4 | fast, best quality |
 Here is a handy graph by ikawrakow comparing some lower-quality quant
 types (lower is better):

 | [GGUF](https://huggingface.co/mradermacher/wizardllama-7b-GGUF/resolve/main/wizardllama-7b.Q3_K_L.gguf) | Q3_K_L | 3.9 |  |
 | [GGUF](https://huggingface.co/mradermacher/wizardllama-7b-GGUF/resolve/main/wizardllama-7b.IQ4_XS.gguf) | IQ4_XS | 3.9 |  |
 | [GGUF](https://huggingface.co/mradermacher/wizardllama-7b-GGUF/resolve/main/wizardllama-7b.Q4_0.gguf) | Q4_0 | 4.1 | fast, low quality |
+| [GGUF](https://huggingface.co/mradermacher/wizardllama-7b-GGUF/resolve/main/wizardllama-7b.IQ4_NL.gguf) | IQ4_NL | 4.1 | prefer IQ4_XS |
 | [GGUF](https://huggingface.co/mradermacher/wizardllama-7b-GGUF/resolve/main/wizardllama-7b.Q4_K_S.gguf) | Q4_K_S | 4.1 | fast, recommended |
 | [GGUF](https://huggingface.co/mradermacher/wizardllama-7b-GGUF/resolve/main/wizardllama-7b.Q4_K_M.gguf) | Q4_K_M | 4.3 | fast, recommended |
 | [GGUF](https://huggingface.co/mradermacher/wizardllama-7b-GGUF/resolve/main/wizardllama-7b.Q5_K_S.gguf) | Q5_K_S | 4.9 |  |
 | [GGUF](https://huggingface.co/mradermacher/wizardllama-7b-GGUF/resolve/main/wizardllama-7b.Q6_K.gguf) | Q6_K | 5.8 | very good quality |
 | [GGUF](https://huggingface.co/mradermacher/wizardllama-7b-GGUF/resolve/main/wizardllama-7b.Q8_0.gguf) | Q8_0 | 7.4 | fast, best quality |
 Here is a handy graph by ikawrakow comparing some lower-quality quant
 types (lower is better):