README.md

---
license: apache-2.0
---

# The Quantized Google Gemma 2 2B Instruction Tuned Model

Original Base Model: `google/gemma-2-2b-it`.<br>
Link: [https://huggingface.co/google/gemma-2-2b-it](https://huggingface.co/google/gemma-2-2b-it)

## Quantization Configurations
```
"quantization_config": {
    "batch_size": 1,
    "bits": 4,
    "block_name_to_quantize": null,
    "cache_block_outputs": true,
    "damp_percent": 0.1,
    "dataset": null,
    "desc_act": false,
    "exllama_config": {
      "version": 1
    },
```

## Source Codes
Source Codes: [https://github.com/vkola-lab/medpodgpt/tree/main/quantization](https://github.com/vkola-lab/medpodgpt/tree/main/quantization).