|
--- |
|
license: llama2 |
|
train: false |
|
inference: false |
|
pipeline_tag: text-generation |
|
--- |
|
|
|
## Llama-2-70b-hf-2bit_g16_s128-HQQ |
|
This is a version of the LLama-2-70B-hf model quantized to 2-bit via Half-Quadratic Quantization (HQQ): https://mobiusml.github.io/hqq_blog/ |
|
|
|
This model outperforms an fp16 LLama-2-13B (perplexity 4.13 vs. 4.63) for a comparable ~26GB size. |
|
|
|
To run the model, install the HQQ library from https://github.com/mobiusml/hqq and use it as follows: |
|
``` Python |
|
model_id = 'mobiuslabsgmbh/Llama-2-70b-hf-2bit_g16_s128-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> |
|
|
|
|
|
|
|
|
|
|
