Instructions to use McaTech/Nonet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use McaTech/Nonet with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="McaTech/Nonet", filename="ChatNONET-135m-tuned-q8_0.gguf", )
llm.create_chat_completion( messages = [ { "role": "user", "content": "What is the capital of France?" } ] ) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use McaTech/Nonet 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 McaTech/Nonet:Q8_0 # Run inference directly in the terminal: llama cli -hf McaTech/Nonet:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf McaTech/Nonet:Q8_0 # Run inference directly in the terminal: llama cli -hf McaTech/Nonet:Q8_0
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 McaTech/Nonet:Q8_0 # Run inference directly in the terminal: ./llama-cli -hf McaTech/Nonet:Q8_0
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 McaTech/Nonet:Q8_0 # Run inference directly in the terminal: ./build/bin/llama-cli -hf McaTech/Nonet:Q8_0
Use Docker
docker model run hf.co/McaTech/Nonet:Q8_0
- LM Studio
- Jan
- vLLM
How to use McaTech/Nonet with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "McaTech/Nonet" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "McaTech/Nonet", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/McaTech/Nonet:Q8_0
- Ollama
How to use McaTech/Nonet with Ollama:
ollama run hf.co/McaTech/Nonet:Q8_0
- Unsloth Studio
How to use McaTech/Nonet 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 McaTech/Nonet 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 McaTech/Nonet to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for McaTech/Nonet to start chatting
- Atomic Chat new
- Docker Model Runner
How to use McaTech/Nonet with Docker Model Runner:
docker model run hf.co/McaTech/Nonet:Q8_0
- Lemonade
How to use McaTech/Nonet with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull McaTech/Nonet:Q8_0
Run and chat with the model
lemonade run user.Nonet-Q8_0
List all available models
lemonade list
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,4 +1,4 @@
|
|
| 1 |
-
|
| 2 |
---
|
| 3 |
license: apache-2.0
|
| 4 |
language:
|
|
@@ -16,15 +16,15 @@ inference: true
|
|
| 16 |
pipeline_tag: text-generation
|
| 17 |
---
|
| 18 |
|
| 19 |
-
#
|
| 20 |
|
| 21 |
-
**
|
| 22 |
|
| 23 |
## Model Details
|
| 24 |
|
| 25 |
### Model Description
|
| 26 |
|
| 27 |
-
|
| 28 |
|
| 29 |
| Model Name | Base Model | Size |
|
| 30 |
|----------------------------------|--------------------|--------|
|
|
@@ -61,7 +61,7 @@ ChatNONET is intended for lightweight offline use, particularly on local devices
|
|
| 61 |
|
| 62 |
## Bias, Risks, and Limitations
|
| 63 |
|
| 64 |
-
|
| 65 |
|
| 66 |
### Recommendations
|
| 67 |
|
|
@@ -111,7 +111,7 @@ make
|
|
| 111 |
title={ChatNONET: Offline Quantized Q&A Models},
|
| 112 |
author={Michael Cobol Agan},
|
| 113 |
year={2025},
|
| 114 |
-
note={\url{https://huggingface.co/
|
| 115 |
}
|
| 116 |
```
|
| 117 |
|
|
@@ -119,5 +119,3 @@ make
|
|
| 119 |
|
| 120 |
* **Author:** Michael Cobol Agan (McaTech)
|
| 121 |
* **Website / Download App:** https://mcatech.odoo.com/innovation
|
| 122 |
-
|
| 123 |
-
```
|
|
|
|
| 1 |
+
|
| 2 |
---
|
| 3 |
license: apache-2.0
|
| 4 |
language:
|
|
|
|
| 16 |
pipeline_tag: text-generation
|
| 17 |
---
|
| 18 |
|
| 19 |
+
# NONET
|
| 20 |
|
| 21 |
+
**NONET** is a family of **offline**, quantized large language models fine-tuned for **question answering** with **direct, concise answers**. Designed for local execution using `llama.cpp`, NONET is available in multiple sizes and optimized for Android or Python-based environments.
|
| 22 |
|
| 23 |
## Model Details
|
| 24 |
|
| 25 |
### Model Description
|
| 26 |
|
| 27 |
+
NONET is intended for lightweight offline use, particularly on local devices like mobile phones or single-board computers. The models have been **fine-tuned for direct-answer QA** and quantized to **int8 (q8_0)** using `llama.cpp`.
|
| 28 |
|
| 29 |
| Model Name | Base Model | Size |
|
| 30 |
|----------------------------------|--------------------|--------|
|
|
|
|
| 61 |
|
| 62 |
## Bias, Risks, and Limitations
|
| 63 |
|
| 64 |
+
NONET may reproduce biases present in its base models or fine-tuning data. Outputs should not be relied upon for sensitive or critical decisions.
|
| 65 |
|
| 66 |
### Recommendations
|
| 67 |
|
|
|
|
| 111 |
title={ChatNONET: Offline Quantized Q&A Models},
|
| 112 |
author={Michael Cobol Agan},
|
| 113 |
year={2025},
|
| 114 |
+
note={\url{https://huggingface.co/McaTech/Nonet}},
|
| 115 |
}
|
| 116 |
```
|
| 117 |
|
|
|
|
| 119 |
|
| 120 |
* **Author:** Michael Cobol Agan (McaTech)
|
| 121 |
* **Website / Download App:** https://mcatech.odoo.com/innovation
|
|
|
|
|
|