license: llama3
train: false
inference: false
pipeline_tag: text-generation
This is an experimental HQQ all 2-bit (group-size=64) quantized Llama3-8B-Instruct model.
Llama3-8B is known to be relatively difficult to quantize, espcially at lower bits, as pointed out by https://arxiv.org/abs/2404.14047.
This 2-bit model has been calibrated with a low-rank adapter (HQQ+) to significantly improve the quality, since one-shot quantization with 2-bit results in signficant quality loss.
Moreover, this model is fully compatible with BitBlas and torch.compile for fast inference.
Model Size
| Models | fp16 | HQQ+ 2-bit/gs-64 |
|---|---|---|
| Bitrate (Linear layers) | 16 | 2.63 |
| VRAM | 15.7 (GB) | 4.3 (GB) |
Model Decoding Speed
| Models | fp16 | HQQ+ 2-bit/gs-64 |
|---|---|---|
| Decoding* - short seq (tokens/sec) | 53 | 120 |
| Decoding* - long seq (tokens/sec) | 50 | 95 |
*: RTX 3090
Performance
| Models | fp16 | HQQ+ 2-bit/gs-64 |
|---|---|---|
| ARC (25-shot) | 62.2 | 38.82 |
| HellaSwag (10-shot) | 78.78 | 61.09 |
| MMLU (5-shot) | 67.06 | 38.02 |
| TruthfulQA-MC2 | 51.65 | 50.08 |
| Winogrande (5-shot) | 75.85 | 63.22 |
| GSM8K (5-shot) | 75.97 | 26.31 |
| Average | 68.59 | 46.26 |
While this is significantly better than the best 2-bit Llama3-8B model reported in https://arxiv.org/abs/2404.14047 (DB-LLM: 42.1 for HellaSwag and 60.4 for Winograde), it looks like it's actually better to just use a 4-bit Llama2-7B-chat instead.
Usage
First, install the dependecies:
pip install hqq==0.1.8
pip install bitblas
Then you can use the sample code below:
import torch
from hqq.engine.hf import HQQModelForCausalLM, AutoTokenizer
from hqq.core.quantize import *
from hqq.utils.patching import *
from hqq.utils.generation_hf import HFGenerator
#Load the model
###################################################
model_id = 'mobiuslabsgmbh/Llama-3-8b-instruct_2bitgs64_hqq'
model = HQQModelForCausalLM.from_quantized(model_id, cache_dir='.', compute_dtype=torch.float16, adapter='adapter_v0.1.lora')
tokenizer = AutoTokenizer.from_pretrained(model_id)
patch_linearlayers(model, patch_add_quant_config,
BaseQuantizeConfig(nbits=2, group_size=64, quant_scale=False, quant_zero=False, axis=1))
model.eval();
cleanup()
#Use optimized inference kernels
###################################################
HQQLinear.set_backend(HQQBackend.PYTORCH)
#prepare_for_inference(model) #default backend
prepare_for_inference(model, backend="bitblas", allow_merge=False) #It takes a while...
#Generate
###################################################
#For longer context, make sure to allocate enough cache via the cache_size= parameter
#gen = HFGenerator(model, tokenizer, max_new_tokens=1000, do_sample=True, compile=None) #Slower generation but no warm-up
gen = HFGenerator(model, tokenizer, max_new_tokens=1000, do_sample=True, compile="partial").warmup() #Faster generation, but warm-up takes a while
gen.generate("Write an essay about large language models", print_tokens=True)
gen.generate("Tell me a funny joke!", print_tokens=True)
gen.generate("How to make a yummy chocolate cake?", print_tokens=True)