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

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use CorelynAI/NeoH 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 CorelynAI/NeoH
# Run inference directly in the terminal:
llama cli -hf CorelynAI/NeoH

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf CorelynAI/NeoH
# Run inference directly in the terminal:
llama cli -hf CorelynAI/NeoH

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 CorelynAI/NeoH
# Run inference directly in the terminal:
./llama-cli -hf CorelynAI/NeoH

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 CorelynAI/NeoH
# Run inference directly in the terminal:
./build/bin/llama-cli -hf CorelynAI/NeoH

Use Docker

docker model run hf.co/CorelynAI/NeoH

LM Studio
Jan

vLLM

How to use CorelynAI/NeoH with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CorelynAI/NeoH"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CorelynAI/NeoH",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CorelynAI/NeoH

Ollama
How to use CorelynAI/NeoH with Ollama:
```
ollama run hf.co/CorelynAI/NeoH
```
Unsloth Desktop

How to use CorelynAI/NeoH with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf CorelynAI/NeoH

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": "CorelynAI/NeoH"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use CorelynAI/NeoH with Docker Model Runner:
```
docker model run hf.co/CorelynAI/NeoH
```

Lemonade

How to use CorelynAI/NeoH with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull CorelynAI/NeoH

Run and chat with the model

lemonade run user.NeoH-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use CorelynAI/NeoH with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf CorelynAI/NeoH

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 CorelynAI/NeoH

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use CorelynAI/NeoH with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf CorelynAI/NeoH

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 "CorelynAI/NeoH" \
  --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"

Corelyn commited on Mar 9

Commit

23b9013

verified ·

1 Parent(s): 31d632a

edited a bit

Browse files

Files changed (1) hide show

README.md +16 -11

README.md CHANGED Viewed

@@ -1,18 +1,23 @@
 ---
 license: apache-2.0
 tags:
-  - text-generation
-  - instruction-tuned
-  - llama
-  - gguf
-  - chatbot
 library_name: llama.cpp
-language: en
 datasets:
-  - custom
 model-index:
-  - name: Corelyn NeoH
-    results: []
 ---
@@ -28,13 +33,13 @@ model-index:
 ## Model Overview
-Corelyn NeoH is a 4-billion parameter LLaMA-based instruction-tuned model, designed for general-purpose assistant tasks and knowledge extraction. It is a fine-tuned variant optimized for instruction-following use cases.
 - Fine-tuning type: Instruct
 - Base architecture: LLaMA
-- Parameter count: 4B
 - Context length: 131,072 tokens

 ---
 license: apache-2.0
 tags:
+- text-generation
+- instruction-tuned
+- llama
+- gguf
+- chatbot
+- code
 library_name: llama.cpp
+language:
+- en
+- rm
 datasets:
+- custom
 model-index:
+- name: Corelyn NeoH
+  results: []
+base_model:
+- bartowski/Llama-3.2-3B-Instruct-uncensored-GGUF
 ---
 ## Model Overview
+Corelyn NeoH is a 3-billion parameter LLaMA-based instruction-tuned model, designed for general-purpose assistant tasks and knowledge extraction. It is a fine-tuned variant optimized for instruction-following use cases.
 - Fine-tuning type: Instruct
 - Base architecture: LLaMA
+- Parameter count: 3B
 - Context length: 131,072 tokens