PaluLlama-3-8B-Instruct

Compressed Meta Llama-3-8B-Instruct with Palu

Overview

This repository contains a compressed version of the Meta Llama-3-8B-Instruct model, utilizing the Palu framework for KV-Cache compression. Palu reduces the hidden dimensions of the KV-Cache through low-rank decomposition, significantly reducing the model's memory footprint while maintaining or enhancing performance.

Meta Llama-3-8B-Instruct: Palu Compression Results

Perplexity (PPL)

Zero-shot Evaluation

meta-llama-3-8b-instruct-palu

meta-llama-3-8b-instruct (Base)

Long-Bench Evaluation

triviaqa

qasper

---

Key Features

• Model: Meta Llama-3-8B-Instruct
• Compression Framework: Palu
• Compression Rate: Up to 91.25% memory reduction
• Accuracy: Maintained or improved perplexity compared to the base model

Installation

Clone the Repository

Ensure you have Git and Conda installed on your system.

git clone --recurse-submodules https://github.com/shadowpa0327/Palu.git
cd Palu

Set Up the Environment

Create and activate a Conda environment.

conda create -n Palu python=3.10
conda activate Palu
pip install -r requirements.txt

Install Third-Party Libraries

pip install -e 3rdparty/lm-evaluation-harness
pip install -e 3rdparty/fast-hadamard-transform

Usage

Compress the Model

To compress Meta Llama-3-8B-Instruct using Palu's low-rank decomposition, use the following command:

python compress.py \
--model_id="meta-llama/Llama-3-8b-instruct" \
--calib_dataset wikitext2 \
--param_ratio_target 0.7 \
--search_method fisher_uniform \
--head_group_size 4 \
--dump_huggingface_model \
--use_cache 

The compressed model will be saved in the Meta-Llama-3-8b-instruct_ratio-0.7_gs-4-fisher_uniform directory in Hugging Face format.

Evaluate the Compressed Model

Perplexity

To evaluate the perplexity on the wikitext2 dataset with sequence length 2048, run:

python run_ppl_eval.py \
--model_name_or_path /Path/To/Palu/Model \
--datasets wikitext2 \
--seqlen 2048

To evaluate with 3-bit low-rank aware quantization, use:

python run_ppl_eval.py \
--model_name_or_path /Path/To/Palu/Model \
--datasets wikitext2 \
--seqlen 4096 \
--lt_bits 3 \
--lt_hadamard 

Zero-shot Evaluation

For zero-shot evaluations, use the following command:

CUDA_VISIBLE_DEVICES=0 python run_lm_eval.py \
--model_name_or_path "/Path/To/Palu/Model" \
--tasks "openbookqa,hellaswag,piqa,arc_easy,arc_challenge,winogrande"

Long-Bench Evaluation

Evaluate the compressed model on long-bench tasks:

CUDA_VISIBLE_DEVICES=0 python run_long_bench.py \
--model_name_or_path /Path/To/Palu/Model

Latency Evaluation

Attention Module

Evaluate the latency of the Palu-compressed attention module:

CUDA_VISIBLE_DEVICES=0 python run_latency_attention.py \
--rank_k 1024 --rank_v 3072 --group_size 4 \
--prompt_len 65536 --palu

Reconstruction Kernel

Evaluate the latency of the reconstruction kernel:

CUDA_VISIBLE_DEVICES=0 python run_latency_kernel.py \
--total_rank 1024  --group_size 4

Conclusion

This compressed version of Meta Llama-3-8B-Instruct, powered by Palu, is optimized for memory efficiency without compromising performance. Whether you're working with large datasets or deploying models in memory-constrained environments, this setup is designed to provide robust results.