MiniCPM5-2B-SFT-Pashto-Instruct-GGUF

MiniCPM5-2B-SFT-Pashto-Instruct-GGUF 🚀⚡️🇦🇫

MiniCPM5-2B-SFT-Pashto-Instruct-GGUF contains optimized GGUF builds of nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct. Designed for ultra-low latency, lightweight local execution, and seamless edge integration on CPUs, laptops, mobile devices, and consumer GPUs using llama.cpp and Ollama.

---

Highlights & Features

• High Precision Execution: Includes full-precision f16 GGUF exports for maximum fidelity and zero degradation in Pashto token generation.
• Edge Optimized: Run specialized Pashto LLMs locally on consumer hardware without high VRAM requirements.
• Full Toolchain Compatibility: Ready for immediate deployment in llama.cpp, Ollama, LM Studio, and mobile runtime environments.

---

Quickstart & Usage Guide

1. Running with llama.cpp

Run directly from your command line using llama-cli:

# Clone or download the GGUF file
huggingface-cli download nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct-GGUF MiniCPM5-2B-SFT-Pashto.F16.gguf --local-dir .

# Execute prompt
./llama-cli -m MiniCPM5-2B-SFT-Pashto.F16.gguf \
  -p "د پښتو او مصنوعي ځیرکتیا پرمختګ څرنګه ارزوې؟" \
  -n 256 \
  --temp 0.7

2. Running with Ollama

Create a simple Modelfile:

FROM ./MiniCPM5-2B-SFT-Pashto.F16.gguf
PARAMETER temperature 0.7
PARAMETER top_p 0.9
SYSTEM "تاسو یو هوښیار او مرسته کوونکی د پښتو ژبې د مصنوعي ځیرکتیا مرستیال یاست."

Create and launch the model:

ollama create pashto-minicpm -f Modelfile
ollama run pashto-minicpm "د افغان معارف په وده کې د ټیکنالوژۍ اغېزې څه دي؟"

---

Model Specifications

---

Project Context

Developed under the iPashto.ai initiative, advancing open-weights Pashto Natural Language Processing (NLP) tools, quantization protocols, and edge deployment pipelines.