--- datasets: - Lin-Chen/ShareGPT4V pipeline_tag: image-text-to-text library_name: xtuner ---
[![Generic badge](https://img.shields.io/badge/GitHub-%20XTuner-black.svg)](https://github.com/InternLM/xtuner)
## Model llava-phi-3-mini is a LLaVA model fine-tuned from [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co./microsoft/Phi-3-mini-4k-instruct) and [CLIP-ViT-Large-patch14-336](https://huggingface.co./openai/clip-vit-large-patch14-336) with [ShareGPT4V-PT](https://huggingface.co./datasets/Lin-Chen/ShareGPT4V) and [InternVL-SFT](https://github.com/OpenGVLab/InternVL/tree/main/internvl_chat#prepare-training-datasets) by [XTuner](https://github.com/InternLM/xtuner). **Note: This model is in official LLaVA format.** Resources: - GitHub: [xtuner](https://github.com/InternLM/xtuner) - HuggingFace LLaVA format model: [xtuner/llava-phi-3-mini-hf](https://huggingface.co./xtuner/llava-phi-3-mini-hf) - GGUF LLaVA model: [xtuner/llava-phi-3-mini-gguf](https://huggingface.co./xtuner/llava-phi-3-mini-gguf) - XTuner LLaVA format model: [xtuner/llava-phi-3-mini-xtuner](https://huggingface.co./xtuner/llava-phi-3-mini-xtuner) ## Details | Model | Visual Encoder | Projector | Resolution | Pretraining Strategy | Fine-tuning Strategy | Pretrain Dataset | Fine-tune Dataset | Pretrain Epoch | Fine-tune Epoch | | :-------------------- | ------------------: | --------: | ---------: | ---------------------: | ------------------------: | ------------------------: | -----------------------: | -------------- | --------------- | | LLaVA-v1.5-7B | CLIP-L | MLP | 336 | Frozen LLM, Frozen ViT | Full LLM, Frozen ViT | LLaVA-PT (558K) | LLaVA-Mix (665K) | 1 | 1 | | LLaVA-Llama-3-8B | CLIP-L | MLP | 336 | Frozen LLM, Frozen ViT | Full LLM, LoRA ViT | LLaVA-PT (558K) | LLaVA-Mix (665K) | 1 | 1 | | LLaVA-Llama-3-8B-v1.1 | CLIP-L | MLP | 336 | Frozen LLM, Frozen ViT | Full LLM, LoRA ViT | ShareGPT4V-PT (1246K) | InternVL-SFT (1268K) | 1 | 1 | | **LLaVA-Phi-3-mini** | CLIP-L | MLP | 336 | Frozen LLM, Frozen ViT | Full LLM, Full ViT | ShareGPT4V-PT (1246K) | InternVL-SFT (1268K) | 1 | 2 | ## Results
Image
| Model | MMBench Test (EN) | MMMU Val | SEED-IMG | AI2D Test | ScienceQA Test | HallusionBench aAcc | POPE | GQA | TextVQA | MME | MMStar | | :-------------------- | :---------------: | :-------: | :------: | :-------: | :------------: | :-----------------: | :--: | :--: | :-----: | :------: | :----: | | LLaVA-v1.5-7B | 66.5 | 35.3 | 60.5 | 54.8 | 70.4 | 44.9 | 85.9 | 62.0 | 58.2 | 1511/348 | 30.3 | | LLaVA-Llama-3-8B | 68.9 | 36.8 | 69.8 | 60.9 | 73.3 | 47.3 | 87.2 | 63.5 | 58.0 | 1506/295 | 38.2 | | LLaVA-Llama-3-8B-v1.1 | 72.3 | 37.1 | 70.1 | 70.0 | 72.9 | 47.7 | 86.4 | 62.6 | 59.0 | 1469/349 | 45.1 | | **LLaVA-Phi-3-mini** | 69.2 | 41.4 | 70.0 | 69.3 | 73.7 | 49.8 | 87.3 | 61.5 | 57.8 | 1477/313 | 43.7 | ## Quickstart ### Chat by LLaVA official library 1. Install official LLaVA library ```bash pip install git+https://github.com/haotian-liu/LLaVA.git ``` 2. Chat by below script
cli.py ```python import argparse from io import BytesIO import requests import torch from llava.constants import DEFAULT_IMAGE_TOKEN, IMAGE_TOKEN_INDEX from llava.conversation import Conversation, SeparatorStyle from llava.mm_utils import process_images, tokenizer_image_token from llava.model import LlavaLlamaForCausalLM from PIL import Image from transformers import (AutoTokenizer, BitsAndBytesConfig, StoppingCriteria, StoppingCriteriaList, TextStreamer) def load_image(image_file): if image_file.startswith('http://') or image_file.startswith('https://'): response = requests.get(image_file) image = Image.open(BytesIO(response.content)).convert('RGB') else: image = Image.open(image_file).convert('RGB') return image class StopWordStoppingCriteria(StoppingCriteria): """StopWord stopping criteria.""" def __init__(self, tokenizer, stop_word): self.tokenizer = tokenizer self.stop_word = stop_word self.length = len(self.stop_word) def __call__(self, input_ids, *args, **kwargs) -> bool: cur_text = self.tokenizer.decode(input_ids[0]) cur_text = cur_text.replace('\r', '').replace('\n', '') return cur_text[-self.length:] == self.stop_word def get_stop_criteria(tokenizer, stop_words=[]): stop_criteria = StoppingCriteriaList() for word in stop_words: stop_criteria.append(StopWordStoppingCriteria(tokenizer, word)) return stop_criteria def main(args): kwargs = {'device_map': args.device} if args.load_8bit: kwargs['load_in_8bit'] = True elif args.load_4bit: kwargs['load_in_4bit'] = True kwargs['quantization_config'] = BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_compute_dtype=torch.float16, bnb_4bit_use_double_quant=True, bnb_4bit_quant_type='nf4') else: kwargs['torch_dtype'] = torch.float16 tokenizer = AutoTokenizer.from_pretrained(args.model_path) model = LlavaLlamaForCausalLM.from_pretrained( args.model_path, low_cpu_mem_usage=True, **kwargs) vision_tower = model.get_vision_tower() if not vision_tower.is_loaded: vision_tower.load_model(device_map=args.device) image_processor = vision_tower.image_processor conv = Conversation( system=system='<|system|>\nAnswer the questions.', roles=('<|user|>\n', '<|assistant|>\n'), messages=[], offset=0, sep_style=SeparatorStyle.MPT, sep='<|end|>', ) roles = conv.roles image = load_image(args.image_file) image_size = image.size image_tensor = process_images([image], image_processor, model.config) if type(image_tensor) is list: image_tensor = [ image.to(model.device, dtype=torch.float16) for image in image_tensor ] else: image_tensor = image_tensor.to(model.device, dtype=torch.float16) while True: try: inp = input(f'{roles[0]}: ') except EOFError: inp = '' if not inp: print('exit...') break print(f'{roles[1]}: ', end='') if image is not None: inp = DEFAULT_IMAGE_TOKEN + '\n' + inp image = None conv.append_message(conv.roles[0], inp) conv.append_message(conv.roles[1], None) prompt = conv.get_prompt() input_ids = tokenizer_image_token( prompt, tokenizer, IMAGE_TOKEN_INDEX, return_tensors='pt').unsqueeze(0).to(model.device) stop_criteria = get_stop_criteria( tokenizer=tokenizer, stop_words=[conv.sep]) streamer = TextStreamer( tokenizer, skip_prompt=True, skip_special_tokens=True) with torch.inference_mode(): output_ids = model.generate( input_ids, images=image_tensor, image_sizes=[image_size], do_sample=True if args.temperature > 0 else False, temperature=args.temperature, max_new_tokens=args.max_new_tokens, streamer=streamer, stopping_criteria=stop_criteria, use_cache=True) outputs = tokenizer.decode(output_ids[0]).strip() conv.messages[-1][-1] = outputs if args.debug: print('\n', {'prompt': prompt, 'outputs': outputs}, '\n') if __name__ == '__main__': parser = argparse.ArgumentParser() parser.add_argument( '--model-path', type=str, default='xtuner/llava-llama-3-8b-v1_1-hf') parser.add_argument('--image-file', type=str, required=True) parser.add_argument('--device', type=str, default='auto') parser.add_argument('--temperature', type=float, default=0.2) parser.add_argument('--max-new-tokens', type=int, default=512) parser.add_argument('--load-8bit', action='store_true') parser.add_argument('--load-4bit', action='store_true') parser.add_argument('--debug', action='store_true') args = parser.parse_args() main(args) ```
``` python ./cli.py --model-path xtuner/llava-phi-3-mini --image-file https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/tests/data/tiger.jpeg --load-4bit ``` ### Reproduce Please refer to [docs](https://github.com/InternLM/xtuner/tree/main/xtuner/configs/llava/phi3_mini_4k_instruct_clip_vit_large_p14_336#readme). ## Citation ```bibtex @misc{2023xtuner, title={XTuner: A Toolkit for Efficiently Fine-tuning LLM}, author={XTuner Contributors}, howpublished = {\url{https://github.com/InternLM/xtuner}}, year={2023} } ```