--- tags: - int8 - vllm - quantized - 8-bit language: - en - de - fr - it - pt - hi - es - th pipeline_tag: text-generation license: llama3.1 base_model: meta-llama/Meta-Llama-3.1-8B quantized_by: neuralmagic --- # Meta-Llama-3.1-8B-quantized.w8a8 ## Model Overview - **Model Architecture:** Meta-Llama-3 - **Input:** Text - **Output:** Text - **Model Optimizations:** - **Activation quantization:** INT8 - **Weight quantization:** INT8 - **Intended Use Cases:** Intended for commercial and research use multiple languages. Similarly to [Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B), 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). - **Release Date:** 7/31/2024 - **Version:** 1.0 - **License(s):** Llama3.1 - **Model Developers:** Neural Magic Quantized version of [Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B). It achieves an average score of 62.71 on the [OpenLLM](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) benchmark (version 1), whereas the unquantized model achieves 63.03. ### Model Optimizations This model was obtained by quantizing the weights of [Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) 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](https://arxiv.org/abs/2210.17323) 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 sequences taken from Neural Magic's [LLM compression calibration dataset](https://huggingface.co/datasets/neuralmagic/LLM_compression_calibration). ## Deployment This model can be deployed efficiently using the [vLLM](https://docs.vllm.ai/en/latest/) backend, as shown in the example below. ```python from vllm import LLM, SamplingParams from transformers import AutoTokenizer model_id = "neuralmagic/Meta-Llama-3.1-8B-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 aslo supports OpenAI-compatible serving. See the [documentation](https://docs.vllm.ai/en/latest/) for more details. ## Creation This model was created by using the [llm-compressor](https://github.com/vllm-project/llm-compressor) library as presented in the code snipet below. ```python 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" num_samples = 256 max_seq_len = 8192 tokenizer = AutoTokenizer.from_pretrained(model_id) tokenizer = AutoTokenizer.from_pretrained(model_id) def preprocess_fn(example): return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)} ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train") ds = ds.shuffle().select(range(num_samples)) ds = ds.map(preprocess_fn) recipe = GPTQModifier( targets="Linear", scheme="W8A8", 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-3.1-8B-quantized.w8a16") ``` ## Evaluation The model was evaluated on the [OpenLLM](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) leaderboard tasks (version 1) with the [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness/tree/383bbd54bc621086e05aa1b030d8d4d5635b25e6) (commit 383bbd54bc621086e05aa1b030d8d4d5635b25e6) and the [vLLM](https://docs.vllm.ai/en/stable/) engine, using the following command: ``` lm_eval \ --model vllm \ --model_args pretrained="neuralmagic/Meta-Llama-3-8B-quantized.w8a8",dtype=auto,gpu_memory_utilization=0.4,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \ --tasks openllm \ --batch_size auto ``` ### Accuracy #### Open LLM Leaderboard evaluation scores
Benchmark | Meta-Llama-3-8B | Meta-Llama-3-8B-quantized.w8a8(this model) | Recovery |
MMLU (5-shot) | 65.07 | 64.95 | 99.8% |
ARC Challenge (25-shot) | 58.11 | 58.62 | 100.9% |
GSM-8K (5-shot, strict-match) | 50.64 | 49.51 | 97.8% |
Hellaswag (10-shot) | 82.30 | 81.63 | 99.2% |
Winogrande (5-shot) | 77.90 | 78.22 | 100.4% |
TruthfulQA (0-shot, mc2) | 44.15 | 43.36 | 98.2% |
Average | 63.03 | 62.71 | 99.5% |