Instructions to use gghfez/WizardLM-2-22b-RP-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gghfez/WizardLM-2-22b-RP-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="gghfez/WizardLM-2-22b-RP-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("gghfez/WizardLM-2-22b-RP-GGUF", dtype="auto")

llama-cpp-python

How to use gghfez/WizardLM-2-22b-RP-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="gghfez/WizardLM-2-22b-RP-GGUF",
	filename="wizardlm-2-22b-rp-q4_k_m.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 gghfez/WizardLM-2-22b-RP-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf gghfez/WizardLM-2-22b-RP-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf gghfez/WizardLM-2-22b-RP-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 gghfez/WizardLM-2-22b-RP-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf gghfez/WizardLM-2-22b-RP-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 gghfez/WizardLM-2-22b-RP-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf gghfez/WizardLM-2-22b-RP-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 gghfez/WizardLM-2-22b-RP-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf gghfez/WizardLM-2-22b-RP-GGUF:Q4_K_M

Use Docker

docker model run hf.co/gghfez/WizardLM-2-22b-RP-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use gghfez/WizardLM-2-22b-RP-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gghfez/WizardLM-2-22b-RP-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": "gghfez/WizardLM-2-22b-RP-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/gghfez/WizardLM-2-22b-RP-GGUF:Q4_K_M

SGLang

How to use gghfez/WizardLM-2-22b-RP-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "gghfez/WizardLM-2-22b-RP-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gghfez/WizardLM-2-22b-RP-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "gghfez/WizardLM-2-22b-RP-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gghfez/WizardLM-2-22b-RP-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use gghfez/WizardLM-2-22b-RP-GGUF with Ollama:
```
ollama run hf.co/gghfez/WizardLM-2-22b-RP-GGUF:Q4_K_M
```

Unsloth Studio new

How to use gghfez/WizardLM-2-22b-RP-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 gghfez/WizardLM-2-22b-RP-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 gghfez/WizardLM-2-22b-RP-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for gghfez/WizardLM-2-22b-RP-GGUF to start chatting

Docker Model Runner
How to use gghfez/WizardLM-2-22b-RP-GGUF with Docker Model Runner:
```
docker model run hf.co/gghfez/WizardLM-2-22b-RP-GGUF:Q4_K_M
```

Lemonade

How to use gghfez/WizardLM-2-22b-RP-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull gghfez/WizardLM-2-22b-RP-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.WizardLM-2-22b-RP-GGUF-Q4_K_M

List all available models

lemonade list

GGUF Quants of gghfez/WizardLM-2-22B-RP

Original Model Card:

gghfez/WizardLM2-22b-RP

⚠️ IMPORTANT: Experimental Model - Not recommended for Production Use

This is an experimental model created through bespoke, unorthodox merging techniques
The safety alignment and guardrails from the original WizardLM2 model may be compromised
This model is intended for creative writing and roleplay purposes ONLY
Use at your own risk and with appropriate content filtering in place

This model is an experimental derivative of WizardLM2-8x22B, created by extracting the individual experts from the original mixture-of-experts (MoE) model, renaming the mlp modules to match the Mistral architecture, and merging them into a single dense model using linear merging via mergekit.

The resulting model initially produced gibberish, but after fine-tuning on synthetic data generated by the original WizardLM2-8x22B, it regained the ability to generate relatively coherent text. However, the model exhibits confusion about world knowledge and mixes up the names of well known people.

Despite efforts to train the model on factual data, the confusion persisted, so instead I trained it for creative tasks.

As a result, this model is not recommended for use as a general assistant or for tasks that require accurate real-world knowledge (don't bother running MMLU-Pro on it).

It actually retrieves details out of context very accurately, but I still can't recommend it for anything other than creative tasks.

Prompt format

Mistral-v1 + the system tags from Mistral-V7 :

[SYSTEM_PROMPT] {system}[SYSTEM_PROMPT] [INST] {prompt}[/INST]

NOTE: This model is based on WizardLM2-8x22B, which is a finetune of Mixtral-8x22B - not to be confused with the more recent Mistral-Small-22B model. As such, it uses the same vocabulary and tokenizer as Mixtral-v0.1 and inherites the Apache2.0 license. I expanded the vocab to include the system prompt and instruction tags before training (including embedding heads).

Quants

TODO

Examples:

Strength: Information Extraction from Context

[example 1]

Weakness: Basic Factual Knowledge

[example 2]

Downloads last month: 14

GGUF

Model size

22B params

Architecture

llama

Hardware compatibility

4-bit

5-bit

6-bit

Model tree for gghfez/WizardLM-2-22b-RP-GGUF

Base model

alpindale/WizardLM-2-8x22B

Finetuned

gghfez/WizardLM-2-22b-RP

Quantized

(6)

this model