--- language: - en pipeline_tag: text-generation license: llama3 license_link: https://llama.meta.com/llama3/license/ --- # Meta-Llama-3-70B-Instruct-quantized.w8a16 ## Model Overview - **Model Architecture:** Meta-Llama-3 - **Input:** Text - **Output:** Text - **Model Optimizations:** - **Weight quantization:** INT8 - **Intended Use Cases:** Intended for commercial and research use in English. Similarly to [Meta-Llama-3-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-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:** 7/2/2024 - **Version:** 1.0 - **License(s):** [Llama3](https://llama.meta.com/llama3/license/) - **Model Developers:** Neural Magic Quantized version of [Meta-Llama-3-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct). It achieves an average score of 77.90 on the [OpenLLM](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) benchmark (version 1), whereas the unquantized model achieves 79.18. ### Model Optimizations This model was obtained by quantizing the weights of [Meta-Llama-3-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct) to INT8 data type. This optimization reduces the number of bits per parameter from 16 to 8, reducing the disk size and GPU memory requirements by approximately 50%. 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 INT8 and floating point representations of the quantized weights. [AutoGPTQ](https://github.com/AutoGPTQ/AutoGPTQ) is used for quantization with 10% damping factor and 128 sequences taken from Neural Magic's [LLM compression calibration dataset](https://huggingface.co/datasets/neuralmagic/LLM_compression_calibration). ## Deployment ### Use with vLLM This model can be deployed efficiently using the [vLLM](https://docs.vllm.ai/en/latest/) backend, as shown in the example below (using 2 GPUs). ```python from vllm import LLM, SamplingParams from transformers import AutoTokenizer model_id = "neuralmagic/Meta-Llama-3-70B-Instruct-quantized.w8a16" number_gpus = 2 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) 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. ### Use with transformers This model is supported by Transformers leveraging the integration with the [AutoGPTQ](https://github.com/AutoGPTQ/AutoGPTQ) data format. The following example contemplates how the model can be used using the `generate()` function. ```python from transformers import AutoTokenizer, AutoModelForCausalLM model_id = "neuralmagic/Meta-Llama-3-70B-Instruct-quantized.w8a16" tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype="auto", device_map="auto", ) messages = [ {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"}, {"role": "user", "content": "Who are you?"}, ] input_ids = tokenizer.apply_chat_template( messages, add_generation_prompt=True, return_tensors="pt" ).to(model.device) terminators = [ tokenizer.eos_token_id, tokenizer.convert_tokens_to_ids("<|eot_id|>") ] outputs = model.generate( input_ids, max_new_tokens=256, eos_token_id=terminators, do_sample=True, temperature=0.6, top_p=0.9, ) response = outputs[0][input_ids.shape[-1]:] print(tokenizer.decode(response, skip_special_tokens=True)) ``` ## Creation This model was created by applying the [AutoGPTQ](https://github.com/AutoGPTQ/AutoGPTQ) library as presented in the code snipet below. Although AutoGPTQ was used for this particular model, Neural Magic is transitioning to using [llm-compressor](https://github.com/vllm-project/llm-compressor) which supports several quantization schemes and models not supported by AutoGPTQ. ```python from transformers import AutoTokenizer from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig from datasets import load_dataset model_id = "meta-llama/Meta-Llama-3-70B-Instruct" num_samples = 128 max_seq_len = 8192 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) examples = [tokenizer(example["text"], padding=False, max_length=max_seq_len, truncation=True) for example in ds] quantize_config = BaseQuantizeConfig( bits=8, group_size=-1, desc_act=False, model_file_base_name="model", damp_percent=0.1, ) model = AutoGPTQForCausalLM.from_pretrained( model_id, quantize_config, device_map="auto", ) model.quantize(examples) model.save_pretrained("Meta-Llama-3-70B-Instruct-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 (using 8 GPUs): ``` lm_eval \ --model vllm \ --model_args pretrained="neuralmagic/Meta-Llama-3-70B-Instruct-quantized.w8a16",tensor_parallel_size=8,dtype=auto,gpu_memory_utilization=0.4,add_bos_token=True,max_model_len=4096 \ --tasks openllm \ --batch_size auto ``` ### Accuracy #### Open LLM Leaderboard evaluation scores
Benchmark Meta-Llama-3-70B-Instruct Meta-Llama-3-70B-Instruct-quantized.w8a16 (this model) Recovery
MMLU (5-shot) 80.18 78.69 98.1%
ARC Challenge (25-shot) 72.44 71.59 98.8%
GSM-8K (5-shot, strict-match) 90.83 86.43 95.2%
Hellaswag (10-shot) 85.54 85.65 100.1%
Winogrande (5-shot) 83.19 83.11 98.8%
TruthfulQA (0-shot) 62.92 61.94 98.4%
Average 79.18 77.90 98.4%