boatchrnthn's picture
Update README.md
ddd0981 verified
metadata
license: mit
tags:
  - trl
  - sft
  - retail
  - finance
  - unsloth
language:
  - en
  - th
base_model:
  - unsloth/Llama-3.2-3B-Instruct
pipeline_tag: text-generation
datasets:
  - airesearch/WangchanThaiInstruct

PoonrooSLM Prototype: 3B (พูนรู้ SLM)

This model is currently on experiment and be able to run on Ollama and LM Studio as the experimental version.

  • Lightweight, text-only models that fit onto edge and mobile devices, finetuned version of Llama3.2 with WangchanThaiInstruct Dataset (only Financial and Retail tags)

  • Support context length of 128K tokens and are state-of-the-art in their class for on-device use cases like summarization, instruction following, and rewriting tasks running locally at the edge.

  • The Model empower developers to build personalized, on-device agentic applications with strong privacy where data never leaves the device.

  • Outperforms the Gemma 2 2B and Phi 3.5-mini (3.8B) models on tasks such as following instructions, summarization, prompt rewriting, and tool-use, while the 1B is competitive with Gemma.

  • Multilingual Support in one single model. (Including Thai Language)

  • Enhance more model capabilities by using RAG (Retrieval Augmented Generation) + Responsible AI supported