Instructions to use Okyanus/pomona-nutrient-ph-ec-reasoner-v0.1.1-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 Okyanus/pomona-nutrient-ph-ec-reasoner-v0.1.1-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 Okyanus/pomona-nutrient-ph-ec-reasoner-v0.1.1-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf Okyanus/pomona-nutrient-ph-ec-reasoner-v0.1.1-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Okyanus/pomona-nutrient-ph-ec-reasoner-v0.1.1-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf Okyanus/pomona-nutrient-ph-ec-reasoner-v0.1.1-GGUF:F16

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 Okyanus/pomona-nutrient-ph-ec-reasoner-v0.1.1-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf Okyanus/pomona-nutrient-ph-ec-reasoner-v0.1.1-GGUF:F16

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 Okyanus/pomona-nutrient-ph-ec-reasoner-v0.1.1-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Okyanus/pomona-nutrient-ph-ec-reasoner-v0.1.1-GGUF:F16

Use Docker

docker model run hf.co/Okyanus/pomona-nutrient-ph-ec-reasoner-v0.1.1-GGUF:F16

LM Studio
Jan

vLLM

How to use Okyanus/pomona-nutrient-ph-ec-reasoner-v0.1.1-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Okyanus/pomona-nutrient-ph-ec-reasoner-v0.1.1-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": "Okyanus/pomona-nutrient-ph-ec-reasoner-v0.1.1-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Okyanus/pomona-nutrient-ph-ec-reasoner-v0.1.1-GGUF:F16

Ollama
How to use Okyanus/pomona-nutrient-ph-ec-reasoner-v0.1.1-GGUF with Ollama:
```
ollama run hf.co/Okyanus/pomona-nutrient-ph-ec-reasoner-v0.1.1-GGUF:F16
```
Unsloth Desktop

How to use Okyanus/pomona-nutrient-ph-ec-reasoner-v0.1.1-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Okyanus/pomona-nutrient-ph-ec-reasoner-v0.1.1-GGUF:F16

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": "Okyanus/pomona-nutrient-ph-ec-reasoner-v0.1.1-GGUF:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Okyanus/pomona-nutrient-ph-ec-reasoner-v0.1.1-GGUF with Docker Model Runner:
```
docker model run hf.co/Okyanus/pomona-nutrient-ph-ec-reasoner-v0.1.1-GGUF:F16
```

Lemonade

How to use Okyanus/pomona-nutrient-ph-ec-reasoner-v0.1.1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Okyanus/pomona-nutrient-ph-ec-reasoner-v0.1.1-GGUF:F16

Run and chat with the model

lemonade run user.pomona-nutrient-ph-ec-reasoner-v0.1.1-GGUF-F16

List all available models

lemonade list

Hermes Agent

How to use Okyanus/pomona-nutrient-ph-ec-reasoner-v0.1.1-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 Okyanus/pomona-nutrient-ph-ec-reasoner-v0.1.1-GGUF:F16

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 Okyanus/pomona-nutrient-ph-ec-reasoner-v0.1.1-GGUF:F16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Okyanus/pomona-nutrient-ph-ec-reasoner-v0.1.1-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Okyanus/pomona-nutrient-ph-ec-reasoner-v0.1.1-GGUF:F16

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 "Okyanus/pomona-nutrient-ph-ec-reasoner-v0.1.1-GGUF:F16" \
  --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"

Okyanus commited on 22 days ago

Commit

1578e70

verified ·

1 Parent(s): edbe171

Fix stale "prepared locally only" claim; add verified ollama pull instructions

Browse files

Files changed (1) hide show

README.md +12 -4

README.md CHANGED Viewed

@@ -19,7 +19,7 @@ tags:
 # Pomona Nutrient / pH-EC Reasoner v0.1.1 GGUF
-**Experimental runtime artifact. Prepared locally only; not uploaded.** This F16 GGUF is a conversion of the
 Pomona Nutrient/pH-EC v0.1.1 correction LoRA merged into
 `Qwen/Qwen2.5-0.5B-Instruct`.
@@ -49,8 +49,15 @@ Related platform: [okyanu/pomona](https://github.com/okyanu/pomona)
 ## Usage
-This is a raw GGUF model for llama.cpp-compatible runtimes. The local Ollama
-wrapper used for testing was:
 ```text
 FROM pomona-nutrient-ph-ec-v0.1.1-f16.gguf
@@ -60,7 +67,8 @@ PARAMETER num_predict 220
 Use the exact task prompt and keep deterministic validation in front of any
 fertigation workflow. A prompt or runtime wrapper is not a substitute for the
-deterministic Pomona safety route.
 For the guarded path, use `scripts/models/guard_nutrient_ph_ec_output.py` or
 the Pomona model-router deterministic route. `guarded_evaluation.json` records

 # Pomona Nutrient / pH-EC Reasoner v0.1.1 GGUF
+**Experimental runtime artifact, published for local testing.** This F16 GGUF is a conversion of the
 Pomona Nutrient/pH-EC v0.1.1 correction LoRA merged into
 `Qwen/Qwen2.5-0.5B-Instruct`.
 ## Usage
+Pull directly from Hugging Face with Ollama:
+```bash
+ollama pull hf.co/Okyanus/pomona-nutrient-ph-ec-reasoner-v0.1.1-GGUF
+```
+Verified on a clean pull: 994 MB download, ~1.1 GB RAM while loaded (100%
+GPU offload reported on Apple Silicon), under 2 seconds per inference once
+loaded. The local Ollama wrapper used for internal testing was:
 ```text
 FROM pomona-nutrient-ph-ec-v0.1.1-f16.gguf
 Use the exact task prompt and keep deterministic validation in front of any
 fertigation workflow. A prompt or runtime wrapper is not a substitute for the
+deterministic Pomona safety route. Model-only output is not guaranteed
+schema-perfect even with `format: json` — see the evaluation numbers above.
 For the guarded path, use `scripts/models/guard_nutrient_ph_ec_output.py` or
 the Pomona model-router deterministic route. `guarded_evaluation.json` records