Text Generation
GGUF
English
Maring Naga
llama-3
llama-3.2
fine-tuned
maringgpt
maring-language
nlp
conversational
Instructions to use komomike/MaringGPT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use komomike/MaringGPT 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 komomike/MaringGPT # Run inference directly in the terminal: llama cli -hf komomike/MaringGPT
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf komomike/MaringGPT # Run inference directly in the terminal: llama cli -hf komomike/MaringGPT
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf komomike/MaringGPT # Run inference directly in the terminal: ./build/bin/llama cli -hf komomike/MaringGPT
Use Docker
docker model run hf.co/komomike/MaringGPT
- Llama new
- LM Studio
- Jan
- vLLM
How to use komomike/MaringGPT with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "komomike/MaringGPT" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "komomike/MaringGPT", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/komomike/MaringGPT
- Ollama
How to use komomike/MaringGPT with Ollama:
ollama run hf.co/komomike/MaringGPT
- Unsloth Desktop
- Pi
How to use komomike/MaringGPT with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf komomike/MaringGPT
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:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "komomike/MaringGPT" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use komomike/MaringGPT with Docker Model Runner:
docker model run hf.co/komomike/MaringGPT
- Lemonade
How to use komomike/MaringGPT with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull komomike/MaringGPT
Run and chat with the model
lemonade run user.MaringGPT-{{QUANT_TAG}}List all available models
lemonade list
- Hermes Agent
How to use komomike/MaringGPT with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf komomike/MaringGPT
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://127.0.0.1:9931/v1 hermes config set model.default komomike/MaringGPT
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use komomike/MaringGPT with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf komomike/MaringGPT
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://127.0.0.1:9931/v1 \ --custom-model-id "komomike/MaringGPT" \ --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"
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,37 +1,80 @@
|
|
| 1 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
|
| 3 |
-
**
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
|
| 5 |
---
|
| 6 |
|
| 7 |
## ๐ธ Demo Preview
|
| 8 |
|
| 9 |
-
|
| 10 |
-
|
|
|
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
## โจ Key Features
|
| 14 |
|
| 15 |
-
|
| 16 |
-
|
| 17 |
-
|
| 18 |
|
| 19 |
---
|
| 20 |
|
| 21 |
-
## โ๏ธ Training
|
|
|
|
|
|
|
| 22 |
|
| 23 |
-
|
| 24 |
-
|
| 25 |
-
|
| 26 |
-
|
|
|
|
|
|
|
| 27 |
|
| 28 |
---
|
| 29 |
|
| 30 |
## ๐ Quickstart
|
| 31 |
|
| 32 |
-
Run **MaringGPT** locally using
|
| 33 |
|
| 34 |
-
### Installation
|
| 35 |
|
| 36 |
```bash
|
| 37 |
pip install --upgrade transformers torch accelerate
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: llama3.2
|
| 3 |
+
base_model: meta-llama/Llama-3.2-3B-Instruct
|
| 4 |
+
language:
|
| 5 |
+
- en
|
| 6 |
+
- nng
|
| 7 |
+
pipeline_tag: text-generation
|
| 8 |
+
tags:
|
| 9 |
+
- llama-3
|
| 10 |
+
- llama-3.2
|
| 11 |
+
- fine-tuned
|
| 12 |
+
- maringgpt
|
| 13 |
+
- maring-language
|
| 14 |
+
- nlp
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
<div align="center">
|
| 18 |
+
|
| 19 |
+
# ๐ MaringGPT
|
| 20 |
|
| 21 |
+
**A modern, lightweight AI model built to preserve, translate, and advance digital support for the Maring language.**
|
| 22 |
+
|
| 23 |
+
[](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct)
|
| 24 |
+
[](https://llama.meta.com/license)
|
| 25 |
+
[](https://github.com/unslothai/unsloth)
|
| 26 |
+
|
| 27 |
+
</div>
|
| 28 |
+
|
| 29 |
+
---
|
| 30 |
+
|
| 31 |
+
## ๐ About the Maring Language & History
|
| 32 |
+
|
| 33 |
+
> *"Meiringba" / "Maringa" โ People who keep the unquenched fire alive.*
|
| 34 |
+
|
| 35 |
+
**Maring** (ISO 639-3: `nng`) is a Sino-Tibetan language spoken primarily by the Maring community in the Tengnoupal and Chandel districts of Manipur, Northeast India.
|
| 36 |
+
|
| 37 |
+
* **Ethno-Linguistic Roots:** Linguistically classified within the Tibeto-Burman branch, Maring shares unique connections with both Tangkhulic and Kuki-Chin languages.
|
| 38 |
+
* **Cultural Identity:** Traditionally an oral-rich language, its speakers are deeply connected to the hills of Southeast Manipur.
|
| 39 |
+
* **The Digital Gap:** Like many indigenous languages of Northeast India, Maring remains under-represented in modern computational linguistics and digital datasets. **MaringGPT** is created to help bridge this gap by bringing native context and modern AI capabilities into a fine-tuned LLM.
|
| 40 |
|
| 41 |
---
|
| 42 |
|
| 43 |
## ๐ธ Demo Preview
|
| 44 |
|
| 45 |
+
| Preview 01 | Preview 02 |
|
| 46 |
+
| :---: | :---: |
|
| 47 |
+
|  |  |
|
| 48 |
+
|
| 49 |
---
|
| 50 |
|
| 51 |
## โจ Key Features
|
| 52 |
|
| 53 |
+
* ๐ฃ๏ธ **Language Awareness:** Fine-tuned to understand context and structured text associated with Maring language instruction.
|
| 54 |
+
* โก **Ultra-Efficient (3B Parameters):** Designed on Meta's Llama 3.2 3B architecture, enabling low latency and local execution on consumer GPUs or mobile platforms.
|
| 55 |
+
* ๐ฏ **Instruction-Tuned:** Structured dialogue handling via ChatML / Llama-3 system prompts for crisp, natural conversations.
|
| 56 |
|
| 57 |
---
|
| 58 |
|
| 59 |
+
## โ๏ธ Training Setup
|
| 60 |
+
|
| 61 |
+
The model was fine-tuned using parameter-efficient optimization techniques:
|
| 62 |
|
| 63 |
+
| Parameter | Specification |
|
| 64 |
+
| :--- | :--- |
|
| 65 |
+
| **Base Model** | `meta-llama/Llama-3.2-3B-Instruct` |
|
| 66 |
+
| **Method** | QLoRA (4-bit Quantization) via Unsloth |
|
| 67 |
+
| **Precision** | `bfloat16` |
|
| 68 |
+
| **Data Format** | Custom conversational instruction-response pairs |
|
| 69 |
|
| 70 |
---
|
| 71 |
|
| 72 |
## ๐ Quickstart
|
| 73 |
|
| 74 |
+
Run **MaringGPT** locally using Python and the `transformers` library:
|
| 75 |
|
| 76 |
+
### 1. Installation
|
| 77 |
|
| 78 |
```bash
|
| 79 |
pip install --upgrade transformers torch accelerate
|
| 80 |
+
|