Update README.md

README.md

@@ -1,3 +1,363 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+datasets:
+- AIDC-AI/Ovis-dataset
+library_name: transformers
+tags:
+- MLLM
+pipeline_tag: image-text-to-text
+language:
+- en
+---
+
+# Ovis1.6-Llama3.2-3B-GPTQ-Int4
+<div align="center">
+  <img src=https://cdn-uploads.huggingface.co/production/uploads/637aebed7ce76c3b834cea37/3IK823BZ8w-mz_QfeYkDn.png width="30%"/>
+</div>
+
+## Introduction
+[GitHub](https://github.com/AIDC-AI/Ovis) | [Demo](https://huggingface.co/spaces/AIDC-AI/Ovis1.6-Gemma2-9B) | [Paper](https://arxiv.org/abs/2405.20797) 
+
+
+We are excited to announce the open-sourcing of **Ovis-1.6**, our latest multi-modal large language model. Ovis is a novel Multimodal Large Language Model (MLLM) architecture, designed to structurally align visual and textual embeddings.
+
+<div align="center">
+    <img src="https://cdn-uploads.huggingface.co/production/uploads/658a8a837959448ef5500ce5/TIlymOb86R6_Mez3bpmcB.png" width="100%" />
+</div>
+
+## Model
+Built upon Ovis1.5, **Ovis1.6** further enhances high-resolution image processing, is trained on a larger, more diverse, and higher-quality dataset, and refines the training process with DPO training following instruction-tuning.
+
+| Ovis MLLMs        | ViT         | LLM                |                          Model Weights                          | Demo                                                             |
+|:------------------|:-----------:|:------------------:|:---------------------------------------------------------------:|:----------------------------------------------------------------:|
+| Ovis1.6-Gemma2-9B | Siglip-400M | Gemma2-9B-It       | [Huggingface](https://huggingface.co/AIDC-AI/Ovis1.6-Gemma2-9B) | [Space](https://huggingface.co/spaces/AIDC-AI/Ovis1.6-Gemma2-9B) |
+| Ovis1.6-Llama3.2-3B | Siglip-400M | Llama-3.2-3B-Instruct       | [Huggingface](https://huggingface.co/AIDC-AI/Ovis1.6-Llama3.2-3B) | [Space](https://huggingface.co/spaces/AIDC-AI/Ovis1.6-Llama3.2-3B) |
+| Ovis1.6-Gemma2-9B-GPTQ-Int4 | Siglip-400M | Gemma2-9B-It       | [Huggingface](https://huggingface.co/AIDC-AI/Ovis1.6-Gemma2-9B-GPTQ-Int4) | - |
+| Ovis1.6-Llama3.2-3B-GPTQ-Int4 | Siglip-400M | Llama-3.2-3B-Instruct       | [Huggingface](https://huggingface.co/AIDC-AI/Ovis1.6-Llama3.2-3B-GPTQ-Int4) | - |
+
+## Quantized Model
+We quantized Ovis1.6 with AutoGPTQ. Follow these steps to run it.
+
+### Installation
+1. Run the following commands to get a basic environment. Be sure to run with CUDA 12.1.
+```bash
+conda create -n <your_env_name> python=3.10
+conda activate <your_env_name>
+pip install torch==2.2.1 torchvision==0.17.1 torchaudio==2.2.1 --index-url https://download.pytorch.org/whl/cu121
+pip install numpy==1.24.3 transformers==4.44.2 pillow==10.3.0 gekko pandas
+```
+2. Build AutoGPTQ: We customized AutoGPTQ to support Ovis model quantization. You need to build from source to install the customized version.
+```bash
+git clone https://github.com/AIDC-AI/AutoGPTQ.git
+cd AutoGPTQ
+pip install -vvv --no-build-isolation -e .
+```
+Check [this](https://github.com/AutoGPTQ/AutoGPTQ/issues/194) first if you are building inside a Docker container.
+
+### Usage
+Below is a code snippet to run **Ovis1.6-Llama3.2-3B-GPTQ-Int4** with multimodal inputs. For additional usage instructions, including inference wrapper and Gradio UI, please refer to [Ovis GitHub](https://github.com/AIDC-AI/Ovis?tab=readme-ov-file#inference).
+```python
+import torch
+from PIL import Image
+from transformers import GenerationConfig
+from auto_gptq.modeling import OvisLlamaGPTQForCausalLM
+
+# load model
+load_device = "cuda:0" # customize load device
+model = OvisLlamaGPTQForCausalLM.from_pretrained(
+    "AIDC-AI/Ovis1.6-Llama3.2-3B-GPTQ-Int4",
+    device=load_device,
+    trust_remote_code=True
+)
+model.model.generation_config = GenerationConfig.from_pretrained("AIDC-AI/Ovis1.6-Llama3.2-3B-GPTQ-Int4")
+text_tokenizer = model.get_text_tokenizer()
+visual_tokenizer = model.get_visual_tokenizer()
+
+# enter image path and prompt
+image_path = input("Enter image path: ")
+image = Image.open(image_path)
+text = input("Enter prompt: ")
+query = f'<image>\n{text}'
+
+# format conversation
+prompt, input_ids, pixel_values = model.preprocess_inputs(query, [image])
+attention_mask = torch.ne(input_ids, text_tokenizer.pad_token_id)
+input_ids = input_ids.unsqueeze(0).to(device=model.device)
+attention_mask = attention_mask.unsqueeze(0).to(device=model.device)
+pixel_values = [pixel_values.to(dtype=visual_tokenizer.dtype, device=visual_tokenizer.device)]
+
+# generate output
+with torch.inference_mode():
+    gen_kwargs = dict(
+        max_new_tokens=1024,
+        do_sample=False,
+        top_p=None,
+        top_k=None,
+        temperature=None,
+        repetition_penalty=None,
+        eos_token_id=model.generation_config.eos_token_id,
+        pad_token_id=text_tokenizer.pad_token_id,
+        use_cache=True
+    )
+    output_ids = model.generate(input_ids, pixel_values=pixel_values, attention_mask=attention_mask, **gen_kwargs)[0]
+    output = text_tokenizer.decode(output_ids, skip_special_tokens=True)
+    print(f'Output:\n{output}')
+```
+
+<details>
+<summary>Batch inference</summary>
+
+```python
+batch_inputs = [
+    ('example_image1.jpeg', 'Describe the content of this image.'),
+    ('example_image2.jpeg', 'What is the equation in the image?')
+]
+
+batch_input_ids = []
+batch_attention_mask = []
+batch_pixel_values = []
+
+for image_path, text in batch_inputs:
+    image = Image.open(image_path)
+    query = f'<image>\n{text}'
+    prompt, input_ids, pixel_values = model.preprocess_inputs(query, [image])
+    attention_mask = torch.ne(input_ids, text_tokenizer.pad_token_id)
+    input_ids = input_ids.unsqueeze(0).to(device=model.device)
+    attention_mask = attention_mask.unsqueeze(0).to(device=model.device)
+    pixel_values = [pixel_values.to(dtype=visual_tokenizer.dtype, device=visual_tokenizer.device)]
+    batch_input_ids.append(input_ids.squeeze())
+    batch_attention_mask.append(attention_mask.squeeze())
+    batch_pixel_values.append(pixel_values)
+
+pad_batch_input_ids = torch.nn.utils.rnn.pad_sequence([i.flip(dims=[0]) for i in batch_input_ids],batch_first=True, padding_value=0.0).flip(dims=[1])
+pad_batch_input_ids =  pad_batch_input_ids[:,-model.config.multimodal_max_length:]
+pad_batch_attention_mask = torch.nn.utils.rnn.pad_sequence([i.flip(dims=[0]) for i in batch_attention_mask],batch_first=True, padding_value=False).flip(dims=[1])
+pad_batch_attention_mask = pad_batch_attention_mask[:,-model.config.multimodal_max_length:]
+pad_batch_pixel_values = [item for sublist in batch_pixel_values for item in sublist]
+
+# generate output
+with torch.inference_mode():
+    gen_kwargs = dict(
+        max_new_tokens=1024,
+        do_sample=False,
+        top_p=None,
+        top_k=None,
+        temperature=None,
+        repetition_penalty=None,
+        eos_token_id=model.generation_config.eos_token_id,
+        pad_token_id=text_tokenizer.pad_token_id,
+        use_cache=True
+    )
+    output_ids = model.generate(pad_batch_input_ids, pixel_values=pad_batch_pixel_values, attention_mask=pad_batch_attention_mask, **gen_kwargs)
+
+for i in range(len(batch_input_ids)):
+    output = text_tokenizer.decode(output_ids[i], skip_special_tokens=True)
+    print(f'Output_{i}:\n{output}')
+```
+</details>
+
+
+## Quantize Your Own Ovis Model with AutoGPTQ
+We provide a demonstration code snippet for you to quantize your own fine-tuned **Ovis1.6-Llama3.2-3B** model. Before running the code, you need to **follow the ABOVE installation steps** to obtain an environment for quantization.
+```python
+from typing import Dict, Sequence, Union, List
+import copy
+import logging
+
+from auto_gptq import BaseQuantizeConfig
+from auto_gptq.modeling import OvisLlamaGPTQForCausalLM
+import torch
+from torch.utils.data import Dataset, DataLoader
+from PIL import Image
+
+
+# Specify paths and hyperparameters for quantization
+model_path = "path/to/finetuned/model"
+quantize_save_path = "path/to/save/quantized/model"
+IGNORE_ID = -100
+device_idx = 2 # you customize
+torch.cuda.set_device(device_idx)
+quantize_config = BaseQuantizeConfig(
+    bits=4,          # 4 or 8
+    group_size=128,
+    damp_percent=0.1,
+    desc_act=False,  # set to False can significantly speed up inference but the perplexity may slightly bad
+    static_groups=False,
+    sym=True,
+    true_sequential=True,
+)
+
+
+# Load model
+model = OvisLlamaGPTQForCausalLM.from_pretrained(
+    model_path,
+    quantize_config,
+    torch_dtype=torch.bfloat16,
+    multimodal_max_length=2624,
+    llm_attn_implementation='eager',
+    trust_remote_code=True
+).cuda()
+print(f"Model Loaded!")
+
+
+# prepare calibration samples
+class CalibrationDataset(Dataset):
+    """
+    Dataset class for calibration. Initialize with the loaded Ovis model, and a sample list in the following format:
+    data_list = [
+        {
+            "image": "path/to/image/of/this/sample",
+            "conversations": [
+                {
+                    "from": "human",
+                    "value": "<image>\n[Your sample prompt]"
+                },
+                {
+                    "from": "gpt",
+                    "value": "[Anything]"
+                }
+            ]
+        },
+        ...
+    ]
+    """
+    def __init__(self, model, text_max_length, data_list: List[Dict]):
+        self.data = data_list
+        self.model = model
+        self.visual_tokenizer = model.get_visual_tokenizer()
+        self.text_max_length = text_max_length
+    
+
+    def __len__(self):
+        return len(self.data)
+    
+
+    def __getitem__(self, i: int) -> Dict[str, torch.Tensor]:
+        sample = self.data[i]
+        conversations = copy.deepcopy(sample["conversations"])
+        images = [Image.open(sample['image'])]
+        max_partition = 9
+
+        prompt, input_ids, pixel_values, labels = self.model.preprocess_inputs(
+            conversations,
+            images,
+            max_partition=max_partition,
+            generation_preface=None,
+            return_labels=True,
+            propagate_exception=False
+        )
+
+        if pixel_values is None:
+            pixel_values, _ = self.visual_tokenizer.mock_input()
+
+        input_ids = input_ids[:self.text_max_length]
+        labels = labels[:self.text_max_length]
+
+        return dict(
+            pixel_values=pixel_values,
+            input_ids=input_ids,
+            labels=labels
+        )
+
+
+class DataCollatorForMultimodalDatasetGPTQ:
+    def __init__(self, text_tokenizer):
+        self.text_tokenizer = text_tokenizer
+
+    def __call__(self, instances: Sequence[Dict]) -> Dict[str, Union[torch.Tensor, List[torch.Tensor]]]:
+        pixel_values, input_ids, labels = tuple([instance[key] for instance in instances]
+                                                for key in ("pixel_values", "input_ids", "labels"))
+        input_ids = torch.nn.utils.rnn.pad_sequence(
+            input_ids,
+            batch_first=True,
+            padding_value=self.text_tokenizer.pad_token_id)
+        attention_mask = torch.ne(input_ids, self.text_tokenizer.pad_token_id)
+        labels = torch.nn.utils.rnn.pad_sequence(
+            labels,
+            batch_first=True,
+            padding_value=IGNORE_ID)
+
+        num_valid_label = torch.not_equal(labels, IGNORE_ID).sum().item()
+        if num_valid_label == 0:
+            logging.warning(
+                f'[DataCollatorForMultimodalDatasetGPTQ] All labels are ignored, may causing training instability\n{input_ids=}\n{attention_mask=}\n{labels=}')
+
+        return dict(
+            input_ids=input_ids,
+            attention_mask=attention_mask,
+            labels=labels,
+            pixel_values=pixel_values
+        )
+
+
+class MyDataLoader(DataLoader):
+    def __len__(self):
+        return len(self.dataset) // self.batch_size # must set drop last=True
+
+
+# prepare your own calibration samples here
+data_list = [
+    {
+        "image": "path/to/image/of/this/sample",
+        "conversations": [
+            {
+                "from": "human",
+                "value": "<image>\n[Your sample prompt]"
+            },
+            {
+                "from": "gpt",
+                "value": "[Anything]"
+            }
+        ]
+    }
+]
+train_dataset = CalibrationDataset(model, text_max_length=832, data_list=data_list)
+print(f"Dataset Loaded!")
+print(f"Total length of the training set: {len(train_dataset)}")
+
+train_loader = MyDataLoader(
+    train_dataset,
+    collate_fn=DataCollatorForMultimodalDatasetGPTQ(model.get_text_tokenizer()),
+    shuffle=False,
+    batch_size=4,
+    drop_last=True,
+    pin_memory=True,
+    num_workers=8
+)
+print(f"Dataloader Loaded!")
+
+
+# start quantizing
+model.quantize(train_loader, cache_examples_on_gpu=False)
+print(f"Model Quantized! Now Saving...")
+
+model.save_quantized(quantize_save_path, use_safetensors=True)
+print(f"ALL Done!")
+```
+
+
+## Performance
+Here we report the performance of Ovis1.6-Llama3.2-3B-GPTQ-Int4. The results are obtained with VLMEvalkit.
+Benchmark:
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/645cb4b4a03f3ebb0bde20e0/Mjf7-rZ8eRk-58G9716l9.png)
+
+VRAM usage:
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/645cb4b4a03f3ebb0bde20e0/QcL3X_5-EvyD95-yP8MJ8.png)
+
+
+## Citation
+If you find Ovis useful, please cite the paper
+```
+@article{lu2024ovis,
+  title={Ovis: Structural Embedding Alignment for Multimodal Large Language Model},
+  author={Shiyin Lu and Yang Li and Qing-Guo Chen and Zhao Xu and Weihua Luo and Kaifu Zhang and Han-Jia Ye},
+  year={2024},
+  journal={arXiv:2405.20797}
+}
+```
+
+## License
+This project is licensed under the [Apache License, Version 2.0](https://www.apache.org/licenses/LICENSE-2.0.txt) (SPDX-License-Identifier: Apache-2.0).
+
+## Disclaimer
+We used compliance-checking algorithms during the training process, to ensure the compliance of the trained model to the best of our ability. Due to the complexity of the data and the diversity of language model usage scenarios, we cannot guarantee that the model is completely free of copyright issues or improper content. If you believe anything infringes on your rights or generates improper content, please contact us, and we will promptly address the matter.