metadata
license: llama2
train: false
inference: false
pipeline_tag: text-generation
Llama-2-70b-chat-hf-2bit_g16_s128-HQQ
This is a version of the LLama-2-70B-chat-hf model quantized to 2-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:
from hqq.models.llama_hf import LlamaHQQ
import transformers
model_id = 'mobiuslabsgmbh/Llama-2-70b-chat-hf-2bit_g16_s128-HQQ'
#Load the tokenizer
tokenizer = transformers.AutoTokenizer.from_pretrained(model_id)
#Load the model
model = LlamaHQQ.from_quantized(model_id)
Limitations:
-Only supports single GPU runtime.
-Not compatible with HuggingFace's PEFT.