Meta Llama 3.1 8B Instruct Quantized.w8a8

🚀 Meta-Llama-3.1-8B-Instruct-quantized.w8a8

This is a quantized version of Meta-Llama-3.1-8B-Instruct, optimized for multi - language commercial and research use, with high recovery rates on multiple benchmarks.

🚀 Quick Start

This model can be deployed efficiently using the vLLM backend. Here is an example:

from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a8"
number_gpus = 1
max_model_len = 8192

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

✨ Features

• Model Architecture: Meta - Llama - 3, with text input and text output.
• Model Optimizations:
  • Activation quantization: INT8
  • Weight quantization: INT8
• Intended Use Cases: Intended for commercial and research use in multiple languages, similar to [Meta - Llama - 3.1 - 8B - Instruct](https://huggingface.co/meta - llama/Meta - Llama - 3.1 - 8B - Instruct), for assistant - like chat.
• Out - of - scope: Use in any manner that violates applicable laws or regulations (including trade compliance laws).
• Release Date: 7/11/2024
• Version: 1.0
• License(s): Llama3.1
• Model Developers: Neural Magic

This model was evaluated on several tasks to assess its quality in comparison to the unquantized model, including multiple - choice, math reasoning, and open - ended text generation. It achieves 105.4% recovery for the Arena - Hard evaluation, 100.3% for OpenLLM v1 (using Meta's prompting when available), 101.5% for OpenLLM v2, 99.7% for HumanEval pass@1, and 98.8% for HumanEval+ pass@1.

🔧 Technical Details

Model Optimizations

This model was obtained by quantizing the weights of [Meta - Llama - 3.1 - 8B - Instruct](https://huggingface.co/meta - llama/Meta - Llama - 3.1 - 8B - Instruct) to INT8 data type. This optimization reduces the number of bits used to represent weights and activations from 16 to 8, reducing GPU memory requirements (by approximately 50%) and increasing matrix - multiply compute throughput (by approximately 2x). Weight quantization also reduces disk size requirements by approximately 50%.

Only weights and activations of the linear operators within transformers blocks are quantized. Weights are quantized with a symmetric static per - channel scheme, where a fixed linear scaling factor is applied between INT8 and floating point representations for each output channel dimension. Activations are quantized with a symmetric dynamic per - token scheme, computing a linear scaling factor at runtime for each token between INT8 and floating point representations. The GPTQ algorithm is applied for quantization, as implemented in the [llm - compressor](https://github.com/vllm - project/llm - compressor) library. GPTQ used a 1% damping factor and 256 sequences of 8,192 random tokens.

Creation

This model was created by using the [llm - compressor](https://github.com/vllm - project/llm - compressor) library, as shown in the following code:

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-3.1-8B-Instruct"

num_samples = 256
max_seq_len = 8192

tokenizer = AutoTokenizer.from_pretrained(model_id)

max_token_id = len(tokenizer.get_vocab()) - 1
input_ids = [[random.randint(0, max_token_id) for _ in range(max_seq_len)] for _ in range(num_samples)]
attention_mask = num_samples * [max_seq_len * [1]]
ds = Dataset.from_dict({"input_ids": input_ids, "attention_mask": attention_mask})

recipe = GPTQModifier(
  targets="Linear",
  scheme="W8A8",
  ignore=["lm_head"],
  dampening_frac=0.01,
)

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

oneshot(
  model=model,
  dataset=ds,
  recipe=recipe,
  max_seq_length=max_seq_len,
  num_calibration_samples=num_samples,
)

model.save_pretrained("Meta-Llama-3.1-8B-Instruct-quantized.w8a8")

📚 Documentation

Evaluation

This model was evaluated on the well - known Arena - Hard, OpenLLM v1, OpenLLM v2, HumanEval, and HumanEval+ benchmarks. In all cases, model outputs were generated with the vLLM engine.

• Arena - Hard evaluations were conducted using the [Arena - Hard - Auto](https://github.com/lmarena/arena - hard - auto) repository. The model generated a single answer for each prompt from Arena - Hard, and each answer was judged twice by GPT - 4.
• OpenLLM v1 and v2 evaluations were conducted using Neural Magic's fork of [lm - evaluation - harness](https://github.com/neuralmagic/lm - evaluation - harness/tree/llama_3.1_instruct) (branch llama_3.1_instruct). This version of the lm - evaluation - harness includes versions of MMLU, ARC - Challenge and GSM - 8K that match the prompting style of [Meta - Llama - 3.1 - Instruct - evals](https://huggingface.co/datasets/meta - llama/Meta - Llama - 3.1 - 8B - Instruct - evals) and a few fixes to OpenLLM v2 tasks.
• HumanEval and HumanEval+ evaluations were conducted using Neural Magic's fork of the EvalPlus repository.

Detailed model outputs are available as HuggingFace datasets for [Arena - Hard](https://huggingface.co/datasets/neuralmagic/quantized - llama - 3.1 - arena - hard - evals), [OpenLLM v2](https://huggingface.co/datasets/neuralmagic/quantized - llama - 3.1 - leaderboard - v2 - evals), and [HumanEval](https://huggingface.co/datasets/neuralmagic/quantized - llama - 3.1 - humaneval - evals).

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

Accuracy

Reproduction

The results were obtained using the following commands:

MMLU

lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a8",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
  --tasks mmlu_llama_3.1_instruct \
  --fewshot_as_multiturn \
  --apply_chat_template \
  --num_fewshot 5 \
  --batch_size auto

MMLU - CoT

lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a8",dtype=auto,max_model_len=4064,max_gen_toks=1024,tensor_parallel_size=1 \
  --tasks mmlu_cot_0shot_llama_3.1_instruct \
  --apply_chat_template \
  --num_fewshot 0 \
  --batch_size auto

ARC - Challenge

lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a8",dtype=auto,max_model_len=3940,max_gen_toks=100,tensor_parallel_size=1 \
  --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-3.1-8B-Instruct-quantized.w8a8",dtype=auto,max_model_len=4096,max_gen_toks=1024,tensor_parallel_size=1 \
  --tasks gsm8k_cot_llama_3.1_instruct \
  --fewshot_as_multiturn \
  --apply_chat_template \
  --num_fewshot 8 \
  --batch_size auto

Hellaswag

lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a8",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \
  --tasks hellaswag \
  --num_fewshot 10 \
  --batch_size auto

Winogrande

lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a8",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \
  --tasks winogrande \
  --num_fewshot 5 \
  --batch_size auto

TruthfulQA

lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a8",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \
  --tasks truthfulqa \
  --num_fewshot 0 \
  --batch_size auto

OpenLLM v2

lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a8",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
  --apply_chat_template \
  --fewshot_as_multiturn \
  --tasks leaderboard \
  --batch_size auto

MMLU Portuguese

lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a8",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
  --tasks mmlu_pt_llama_3.1_instruct \
  --fewshot_as_multiturn \
  --apply_chat_template \
  --num_fewshot 

📄 License

The license for this model is Llama3.1.