---
license: llama2
train: false
inference: false
pipeline_tag: text-generation
---

## Llama-2-7b-hf-4bit_g64-HQQ
This is a version of the LLama-2-7B-hf model quantized to 4-bit via Half-Quadratic Quantization (HQQ): https://mobiusml.github.io/hqq_blog/

To run the model, install the HQQ library from https://github.com/mobiusml/hqq and use it as follows:
``` Python
model_id = 'mobiuslabsgmbh/Llama-2-7b-hf-4bit_g64-HQQ'

from hqq.engine.hf import HQQModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained(model_id)
model     = HQQModelForCausalLM.from_quantized(model_id)
```

*Limitations*: <br>
-Only supports single GPU runtime.<br>
-Not compatible with HuggingFace's PEFT.<br>