Instructions to use zerofata/G4-MeroMero-v2-31B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use zerofata/G4-MeroMero-v2-31B-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf zerofata/G4-MeroMero-v2-31B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf zerofata/G4-MeroMero-v2-31B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf zerofata/G4-MeroMero-v2-31B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf zerofata/G4-MeroMero-v2-31B-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 zerofata/G4-MeroMero-v2-31B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf zerofata/G4-MeroMero-v2-31B-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 zerofata/G4-MeroMero-v2-31B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf zerofata/G4-MeroMero-v2-31B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/zerofata/G4-MeroMero-v2-31B-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use zerofata/G4-MeroMero-v2-31B-GGUF with Ollama:
```
ollama run hf.co/zerofata/G4-MeroMero-v2-31B-GGUF:Q4_K_M
```

Unsloth Studio

How to use zerofata/G4-MeroMero-v2-31B-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 zerofata/G4-MeroMero-v2-31B-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 zerofata/G4-MeroMero-v2-31B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for zerofata/G4-MeroMero-v2-31B-GGUF to start chatting

How to use zerofata/G4-MeroMero-v2-31B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf zerofata/G4-MeroMero-v2-31B-GGUF:Q4_K_M

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": "zerofata/G4-MeroMero-v2-31B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use zerofata/G4-MeroMero-v2-31B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf zerofata/G4-MeroMero-v2-31B-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "zerofata/G4-MeroMero-v2-31B-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use zerofata/G4-MeroMero-v2-31B-GGUF with Docker Model Runner:
```
docker model run hf.co/zerofata/G4-MeroMero-v2-31B-GGUF:Q4_K_M
```

Lemonade

How to use zerofata/G4-MeroMero-v2-31B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull zerofata/G4-MeroMero-v2-31B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.G4-MeroMero-v2-31B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use zerofata/G4-MeroMero-v2-31B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf zerofata/G4-MeroMero-v2-31B-GGUF:Q4_K_M

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 zerofata/G4-MeroMero-v2-31B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

zerofata commited on 7 days ago

Commit

705d96b

verified ·

1 Parent(s): bab4192

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -539,11 +539,11 @@ base_model:
 </div>
 <div class="gs-sbody">
 <p></p>
-<p>A finetune of Gemma 4 31B designed for creative tasks. Intended to be a more creative version of <a href="https://huggingface.co/zerofata/G4-MeroMero-31B">G4-MeroMero-31B</a>.</p>
 <p>This model is the result of a lot of experimentation and learning. Trying to make Gemma 4 more creative without destroying the intelligence is... difficult. To put it mildly.</p>
 <p style="margin-top:16px">Heavily inspired by a few research papers, <a href="https://arxiv.org/abs/2604.03136">StoryScope: Investigating idiosyncrasies in AI fiction
-</a> and particularly <a href="https://arxiv.org/abs/2605.26492">Elias in the Lighthouse, Again?</a>. Measuring these narrative tics and attractors against simple prompts seems to be a good way to target the model's slop: anything that repeatedly occurs across generations of such a generic prompt is something the model is overusing.</p>
-<p>Compared to the original, swipes are notably more diverse and feel less like Gemma. RP slop is measurably lower (at least for the type of slop I measure). IFEval / GSM8K / MMLU-Pro are more or less the same as stock. The only intelligence drop I've really noticed so far is when you get a swipe that goes a bit hot.</p>
 <p>Supports both thinking and non thinking. Reasoning averages longer than stock Gemma 4, but shorter than MeroMero v1.</p>
 </div>
 </div>
@@ -603,7 +603,7 @@ base_model:
 <div class="gs-sbody">
 <table class="gs-etable">
 <tr><th></th><th class="gs-ecol">Mero Mero v2</th><th>Mero Mero v1</th><th>Stock Gemma 4</th></tr>
-<tr class="gs-egroup"><td colspan="4">Swipe diversity &mdash; given an RP conversation, with 8 swipes, measures how different the ideas in those swipes are, GLM-judged</td></tr>
 <tr><td>Thinking off</td><td class="gs-best">0.72</td><td>0.57</td><td>0.43</td></tr>
 <tr><td>Thinking on</td><td class="gs-best">0.62</td><td>0.49</td><td>0.32</td></tr>
 <tr class="gs-egroup"><td colspan="4">Slop &amp; attractors &mdash; lower is better</td></tr>

 </div>
 <div class="gs-sbody">
 <p></p>
+<p>A finetune of Gemma 4 31B designed for creative tasks, particularly narrative RP. Intended to be a more creative version of <a href="https://huggingface.co/zerofata/G4-MeroMero-31B">G4-MeroMero-31B</a>.</p>
 <p>This model is the result of a lot of experimentation and learning. Trying to make Gemma 4 more creative without destroying the intelligence is... difficult. To put it mildly.</p>
 <p style="margin-top:16px">Heavily inspired by a few research papers, <a href="https://arxiv.org/abs/2604.03136">StoryScope: Investigating idiosyncrasies in AI fiction
+</a> and particularly <a href="https://arxiv.org/abs/2605.26492">Elias in the Lighthouse, Again?</a>. Measuring these narrative tics and attractors against simple prompts seems to be a good way to target the model's slop and kick start giving Gemma 4 some diversity: anything that repeatedly occurs across generations of such a generic prompt is something the model is overusing.</p>
+<p>Compared to the original, swipes are notably more diverse and feel less like Gemma. RP slop is measurably lower (at least for the type of slop I measure). IFEval / GSM8K / MMLU-Pro are the same as stock with no obvious degradation. The only intelligence drop I've really noticed so far is when you get a swipe that goes a bit hot.</p>
 <p>Supports both thinking and non thinking. Reasoning averages longer than stock Gemma 4, but shorter than MeroMero v1.</p>
 </div>
 </div>
 <div class="gs-sbody">
 <table class="gs-etable">
 <tr><th></th><th class="gs-ecol">Mero Mero v2</th><th>Mero Mero v1</th><th>Stock Gemma 4</th></tr>
+<tr class="gs-egroup"><td colspan="4">Swipe diversity &mdash; given an RP conversation, generate 8 swipes and evaluate how varied the beats in those swipes are, GLM-judged with a rubric.</td></tr>
 <tr><td>Thinking off</td><td class="gs-best">0.72</td><td>0.57</td><td>0.43</td></tr>
 <tr><td>Thinking on</td><td class="gs-best">0.62</td><td>0.49</td><td>0.32</td></tr>
 <tr class="gs-egroup"><td colspan="4">Slop &amp; attractors &mdash; lower is better</td></tr>