metadata

tags:
  - int4
  - vllm
language:
  - en
  - de
  - fr
  - it
  - pt
  - hi
  - es
  - th
pipeline_tag: text-generation
license: llama3.1
base_model: meta-llama/Meta-Llama-3.1-405B-Instruct

Meta-Llama-3.1-405B-Instruct-quantized.w4a16

Model Overview

Model Architecture: Meta-Llama-3
- Input: Text
- Output: Text
Model Optimizations:
- Weight quantization: INT4
Intended Use Cases: Intended for commercial and research use in English. Similarly to Meta-Llama-3.1-405B-Instruct, this models is intended for assistant-like chat.
Out-of-scope: Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in languages other than English.
Release Date: 8/9/2024
Version: 1.0
License(s): Llama3.1
Model Developers: Neural Magic

Quantized version of Meta-Llama-3.1-405B-Instruct. It achieves scores within 1% of the scores of the unquantized model for MMLU, ARC-Challenge, GSM-8k, Hellaswag, Winogrande, and TruthfulQA.

Model Optimizations

This model was obtained by quantizing the weights of Meta-Llama-3.1-405B-Instruct to INT4 data type. This optimization reduces the number of bits per parameter from 16 to 4, reducing the disk size and GPU memory requirements by approximately 75%.

Only the weights of the linear operators within transformers blocks are quantized. Symmetric per-channel quantization is applied, in which a linear scaling per output dimension maps the INT4 and floating point representations of the quantized weights. The GPTQ algorithm is applied for quantization, as implemented in the llm-compressor library. GPTQ used a 1% damping factor and 512 sequences of 4,096 random tokens.

Deployment

This model can be deployed efficiently using the vLLM backend, as shown in the example below.

from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Meta-Llama-3.1-405B-Instruct-quantized.w4a16"
number_gpus =  8
max_model_len = 4096

sampling_params = SamplingParams(temperature=0.6, top_p=0.9, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

messages = [
    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
    {"role": "user", "content": "Who are you?"},
]

prompts = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)

llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)

outputs = llm.generate(prompts, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)

vLLM aslo supports OpenAI-compatible serving. See the documentation for more details.

Creation

This model was created by using the llm-compressor library as presented in the code snipet below.

from transformers import AutoTokenizer
from datasets import Dataset
from llmcompressor.transformers import SparseAutoModelForCausalLM, oneshot
from llmcompressor.modifiers.quantization import GPTQModifier
import random

model_id = "meta-llama/Meta-Llama-3.1-405B-Instruct"

num_samples = 512
max_seq_len = 8192

tokenizer = AutoTokenizer.from_pretrained(model_id)

preprocess_fn = lambda example: {"text": "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n{text}".format_map(example)}

dataset_name = "neuralmagic/LLM_compression_calibration"
dataset = load_dataset(dataset_name, split="train")
ds = dataset.shuffle().select(range(num_samples))
ds = ds.map(preprocess_fn)

recipe = GPTQModifier(
  targets="Linear",
  scheme="W4A16",
  ignore=["lm_head"],
  dampening_frac=0.01,
)

model = SparseAutoModelForCausalLM.from_pretrained(
  model_id,
  device_map="auto",
  trust_remote_code=True,
)

oneshot(
  model=model,
  dataset=ds,
  recipe=recipe,
  max_seq_length=max_seq_len,
  num_calibration_samples=num_samples,
)
model.save_pretrained("Meta-Llama-3.1-405B-Instruct-quantized.w4a16")

Evaluation

The model was evaluated on MMLU, ARC-Challenge, GSM-8K, Hellaswag, Winogrande and TruthfulQA. Evaluation was conducted using the Neural Magic fork of lm-evaluation-harness (branch llama_3.1_instruct) and the vLLM engine. This version of the lm-evaluation-harness includes versions of ARC-Challenge, GSM-8K, and MMLU that match the prompting style of Meta-Llama-3.1-Instruct-evals.

Note: Results have been updated after Meta modified the chat template.

Accuracy

Open LLM Leaderboard evaluation scores

Benchmark	Meta-Llama-3.1-405B-Instruct	Meta-Llama-3.1-405B-Instruct-quantized.w4a16 (this model)	Recovery
MMLU (5-shot)	87.38	87.22	99.8%
ARC Challenge (0-shot)	94.97	95.31	100.4%
GSM-8K (CoT, 8-shot, strict-match)	96.44	96.29	99.8%
Hellaswag (10-shot)	88.33	88.27	99.9%
Winogrande (5-shot)	87.21	87.37	100.2%
TruthfulQA (0-shot)	64.64	65.26	101.0%
Average	86.75	86.76	100.0%

Reproduction

The results were obtained using the following commands:

MMLU

lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Meta-Llama-3.1-405B-Instruct-quantized.w4a16",dtype=auto,max_model_len=4096,max_gen_toks=10,tensor_parallel_size=8 \
  --tasks mmlu_llama_3.1_instruct \
  --apply_chat_template \
  --fewshot_as_multiturn \
  --num_fewshot 5 \
  --batch_size auto

ARC-Challenge

lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Meta-Llama-3.1-405B-Instruct-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=8 \
  --tasks arc_challenge_llama_3.1_instruct \
  --apply_chat_template \
  --num_fewshot 0 \
  --batch_size auto

GSM-8K

lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Meta-Llama-3.1-405B-Instruct-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=8 \
  --tasks gsm8k_cot_llama_3.1_instruct \
  --apply_chat_template \
  --fewshot_as_multiturn \
  --num_fewshot 8 \
  --batch_size auto

Hellaswag

lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Meta-Llama-3.1-405B-Instruct-quantized.w4a16",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=8 \
  --tasks hellaswag \
  --num_fewshot 10 \
  --batch_size auto

Winogrande

lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Meta-Llama-3.1-405B-Instruct-quantized.w4a16",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=8 \
  --tasks winogrande \
  --num_fewshot 5 \
  --batch_size auto

TruthfulQA

lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Meta-Llama-3.1-405B-Instruct-quantized.w4a16",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=8 \
  --tasks truthfulqa \
  --num_fewshot 0 \
  --batch_size auto