--- language: - en pipeline_tag: text-generation license: llama2 --- # Llama-2-7b-chat-quantized.w4a16 ## Model Overview - **Model Architecture:** Llama-2 - **Input:** Text - **Output:** Text - **Model Optimizations:** - **Weight quantization:** INT4 - **Intended Use Cases:** Intended for commercial and research use in English. Similarly to [Llama-2-7b-chat](https://huggingface.co/meta-llama/Llama-2-7b-chat), 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:** 7/11/2024 - **Version:** 1.0 - **License(s)**: [LLama2](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf/blob/main/LICENSE.txt) - **Model Developers:** Neural Magic Quantized version of [Llama-2-7b-chat](https://huggingface.co/meta-llama/Llama-2-7b-chat). It achieves an average score of 52.64 on the [OpenLLM](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) benchmark (version 1), whereas the unquantized model achieves 53.40. ### Model Optimizations This model was obtained by quantizing the weights of [Llama-2-7b-chat](https://huggingface.co/meta-llama/Llama-2-7b-chat) 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 25%. Only the weights of the linear operators within transformers blocks are quantized. Symmetric group-wise quantization is applied, in which a linear scaling per group maps the INT4 and floating point representations of the quantized weights. [AutoGPTQ](https://github.com/AutoGPTQ/AutoGPTQ) is used for quantization with 10% damping factor, group-size as 128 and 512 sequences sampled from [Open-Platypus](https://huggingface.co/datasets/garage-bAInd/Open-Platypus). ## 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. ```python from vllm import LLM, SamplingParams from transformers import AutoTokenizer model_id = "neuralmagic/Llama-2-7b-chat-quantized.w4a16" 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, tokenize=False, add_generation_prompt=True) llm = LLM(model=model_id, tensor_parallel_size=2) 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/Llama-2-7b-chat-quantized.w4a16" 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 import random model_id = "meta-llama/Llama-2-7b-chat" num_samples = 512 max_seq_len = 4096 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) examples = [ tokenizer( example["text"], padding=False, max_length=max_seq_len, truncation=True, ) for example in ds ] quantize_config = BaseQuantizeConfig( bits=4, group_size=128, desc_act=True, 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("Llama-2-7b-chat-quantized.w4a16") ``` ## 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/Llama-2-7b-chat-quantized.w4a16",dtype=auto,tensor_parallel_size=2,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 Llama-2-7b-chat Llama-2-7b-chat-quantized.w4a16(this model) Recovery
MMLU (5-shot) 47.33 46.7 98.66%
ARC Challenge (25-shot) 53.24 53.75 100.95%
GSM-8K (5-shot, strict-match) 23.19 21.75 93.79%
Hellaswag (10-shot) 78.64 77.35 98.36%
Winogrande (5-shot) 72.45 70.4 98.66%
TruthfulQA (0-shot) 45.58 45.94 100.78%
Average 53.40 52.64 98.58%