Instructions to use Esobold/EsoTest_GGUFs with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Esobold/EsoTest_GGUFs 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 Esobold/EsoTest_GGUFs:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Esobold/EsoTest_GGUFs:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Esobold/EsoTest_GGUFs:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Esobold/EsoTest_GGUFs: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 Esobold/EsoTest_GGUFs:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Esobold/EsoTest_GGUFs: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 Esobold/EsoTest_GGUFs:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Esobold/EsoTest_GGUFs:Q4_K_M

Use Docker

docker model run hf.co/Esobold/EsoTest_GGUFs:Q4_K_M

LM Studio
Jan
Ollama
How to use Esobold/EsoTest_GGUFs with Ollama:
```
ollama run hf.co/Esobold/EsoTest_GGUFs:Q4_K_M
```
Unsloth Desktop

How to use Esobold/EsoTest_GGUFs with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Esobold/EsoTest_GGUFs:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Esobold/EsoTest_GGUFs:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Esobold/EsoTest_GGUFs with Docker Model Runner:
```
docker model run hf.co/Esobold/EsoTest_GGUFs:Q4_K_M
```

Lemonade

How to use Esobold/EsoTest_GGUFs with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Esobold/EsoTest_GGUFs:Q4_K_M

Run and chat with the model

lemonade run user.EsoTest_GGUFs-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Esobold/EsoTest_GGUFs with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Esobold/EsoTest_GGUFs: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 Esobold/EsoTest_GGUFs:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Esobold/EsoTest_GGUFs with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Esobold/EsoTest_GGUFs: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 "Esobold/EsoTest_GGUFs: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"

ToastyPigeon commited on 23 days ago

Commit

b43b18b

verified ·

1 Parent(s): 482ff57

Upload README_robinson_bengunn.md with huggingface_hub

Browse files

Files changed (1) hide show

README_robinson_bengunn.md +16 -0

README_robinson_bengunn.md ADDED Viewed

	@@ -0,0 +1,16 @@

+# Robinson & BenGunn — FM's nearswap t-gradient research pair (Gemma-4 31B)
+Two experimental variants of the TijuanaBible recipe (nearswap, base
+`nbeerbower/Gemma4-Gutenberg-31B-Heretic`, swapped model
+`ReadyArt/gemma-4-31B-it-scotoma-2`, layers 0-60), with `t` swept
+linearly across layers instead of held flat at 0.0002:
+- **robinson-31b-Q4_K_M.gguf** — `t: [0.0003, 0.0001]` (aggressive-early gradient;
+  hypothesis: punctuation/quirk storage lives in early layers, so weighting them
+  harder may overcome Gemma-isms)
+- **bengunn-31b-Q4_K_M.gguf** — `t: [0.0001, 0.0003]` (late-weighted; the mirror
+  test)
+Both Q4_K_M, bf16 math throughout, faithful reimplementation of mergekitty
+nearswap (weight = clamp(t/max(|a-b|,1e-6), 0, 1)). Recipes by FM; merged on
+request via autumn's server.