Quantization of large language model

Job ID: 37418974

Budget: $250 – $750 USD

I am looking for a skilled freelancer to help me with the quantization of a large language model. The ideal candidate should have experience in the following:

- Moderate compression: The desired level of compression for the language model is a balanced trade-off between model size and performance.
- Python programming: The project should be implemented using Python.
- Both Weight and Activation Quantization: The preferred method of quantization is to apply both weight and activation quantization techniques. Preferably QLoRA
- Training & fine-tuning the Quantized Model: for using it as a ChatBot for Text Summarisation & Q&A proprietary data (containing text, tables, images, basic calculations)

If you have expertise in these areas, please apply for this project.