Update README.md

README.md

@@ -1,6 +1,10 @@
 ---
 library_name: transformers
-tags: []
+datasets:
+- benchang1110/TaiVision-pretrain-1M
+language:
+- zh
+pipeline_tag: image-text-to-text
 ---
 
 # Model Card for Model ID
@@ -11,189 +15,101 @@ tags: []
 
 ## Model Details
 
-### Model Description
-
-<!-- Provide a longer summary of what this model is. -->
-
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+## English
+# TaiVisionLM: The First of Its Kind! 🚀
 
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
+🌟 This is a very fast and small (only 1.2B parameters) visual language model on Hugging Face that responds to Traditional Chinese instructions given an image input! 🌟
 
-### Model Sources [optional]
+✨ Developed compatible with the Transformers library, TaiVisionLM is a breeze to load, fine-tune, and use for lightning-fast inferences—all without needing any external libraries! ⚡️
 
-<!-- Provide the basic links for the model. -->
+Ready to experience the Traditional Chinese visual language model? Let's go! 🖼️🤖
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
 
-## Uses
+## Traditional Chinese
+# 臺視: 首創獨一無二的視覺語言模型!! 🚀
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+🌟 TaiVisionLM 是一個非常快速且小巧的視覺語言模型（僅有 12 億參數），在 Hugging Face 上可以根據圖像輸入來回應繁體中文指令！🌟
 
-### Direct Use
+✨ TaiVisionLM 與 Transformers 完全相容，易於載入、微調和使用，用於快速推理——不需要任何外部庫！⚡️
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+準備好體驗這個繁體中文視覺語言模型了嗎？讓我們開始吧！🖼️🤖
 
-[More Information Needed]
 
-### Downstream Use [optional]
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+---
 
-[More Information Needed]
+# Model Details
 
-### Out-of-Scope Use
+## English
+This model is a multimodal large language model that combines [SigLIP](https://huggingface.co/docs/transformers/en/model_doc/siglip) as its vision encoder with [Tinyllama](https://huggingface.co/benchang1110/Taiwan-tinyllama-v1.0-chat) as its language model. The vision projector connects the two modalities together. 
+Its architecture closely resembles [PaliGemma](https://huggingface.co/docs/transformers/v4.44.0/model_doc/paligemma).
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+Here's the summary of the development process:
 
-[More Information Needed]
+1) **Unimodal pretraining**
+    - In this stage, instead of pretraining both modalities from scratch, I leverage the image encoder from [google/siglip-base-patch16-224-multilingual](https://huggingface.co/google/siglip-base-patch16-224-multilingual) and the language model trained by ourselves (https://huggingface.co/benchang1110/Taiwan-tinyllama-v1.0-chat).
+2) **Feature Alignment**
+    - Following the [LLaVA training recipe](https://github.com/haotian-liu/LLaVA?tab=readme-ov-file#train), I train the vision projector using 1B image-text pairs to align visual and textual features.
+3) **Task Specific Training**
+    - The aligned model undergoes further training for tasks such as short captioning, detailed captioning, and simple visual question answering, using over 1M image-prompt-completion triplets.
+    We will undergo this stage after the dataset is ready!
 
-## Bias, Risks, and Limitations
+## 中文
+這個模型是一個多模態的語言模型，結合了 [SigLIP](https://huggingface.co/docs/transformers/en/model_doc/siglip) 作為其視覺編碼器，並使用 [Tinyllama](https://huggingface.co/benchang1110/Taiwan-tinyllama-v1.0-chat) 作為語言模型。視覺投影器將這兩種模態結合在一起。  
+其架構與 [PaliGemma](https://huggingface.co/docs/transformers/v4.44.0/model_doc/paligemma) 非常相似。
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+以下是開發過程的摘要：
 
-[More Information Needed]
+1) **單模態預訓練**
+   - 在這個階段，我利用了 [google/siglip-base-patch16-224-multilingual](https://huggingface.co/google/siglip-base-patch16-224-multilingual) 的圖像編碼器，以及我們自己訓練的語言模型（[Taiwan-tinyllama-v1.0-chat](https://huggingface.co/benchang1110/Taiwan-tinyllama-v1.0-chat)）。
+2) **特徵對齊**
+   - ���據 [LLaVA](https://github.com/haotian-liu/LLaVA?tab=readme-ov-file#train)，我使用 10 億個圖文配對數據來訓練視覺投影器，以對齊視覺和文本特徵。
+3) **任務特定訓練**
+   - 對齊後的模型進行進一步的訓練，針對短描述、詳細描述和簡單視覺問答等任務，使用超過 100 萬組圖像-提示-完成三元組數據進行訓練。我們將在數據集準備好後進行這一階段的訓練！
 
-### Recommendations
+### Model Description
+<!-- Provide a longer summary of what this model is. -->
 
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+- **Developed by:** [ucsahin](https://huggingface.co/benchang1110)
+- **Model type:** [Image-Text-to-Text](https://huggingface.co/tasks/image-text-to-text)
+- **Language(s) (NLP):** *Turkish*
+- **License:** *Apache license 2.0*
 
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+---
 
 ## How to Get Started with the Model
 
-Use the code below to get started with the model.
+In Transformers, you can load the model and do inference as follows:
 
-[More Information Needed]
+**IMPORTANT NOTE:** TaiVisionLM model is not yet integrated natively into the Transformers library. So you need to set ```trust_remote_code=True``` when loading the model. It will download the ```configuration_taivisionlm.py```, ```modeling_taivisionlm.py``` and ```processing_taivisionlm.py``` files from the repo. You can check out the content of these files under the *Files and Versions* tab and pin the specific versions if you have any concerns regarding malicious code.
 
-## Training Details
+```python
+from transformers import AutoProcessor, AutoModelForCausalLM, AutoConfig
+from PIL import Image
+import requests
+import torch
 
-### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
+config = AutoConfig.from_pretrained("benchang1110/TaiVision-base",trust_remote_code=True)
+processor = AutoProcessor.from_pretrained("benchang1110/TaiVision-base",trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained("benchang1110/TaiVision-base",trust_remote_code=True,torch_dtype=torch.float16,attn_implementation="sdpa").to('cuda')
+model.eval()
+url = "https://media.wired.com/photos/598e35fb99d76447c4eb1f28/master/pass/phonepicutres-TA.jpg"
+image = Image.open(requests.get(url, stream=True).raw).convert("RGB")
+text = "描述圖片"
+inputs = processor(text=text,images=image, return_tensors="pt",padding=False).to('cuda')
+outputs = processor.tokenizer.decode(model.generate(**inputs,max_length=512)[0])
+print(outputs)
+```
 
 ### Training Procedure
-
 <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+The following training hyperparameters are used in feature alignment and task specific training stages respectively:
 
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
+- **Feature Alignment**
 
-[More Information Needed]
+| Data size    | Global Batch Size | Learning Rate | Epochs | Max Length | Weight Decay |
+|--------------|-------------------|---------------|--------|------------|--------------|
+| 1B        | 16               | 5e-4          | 1      | 2048       | 1e-5            |
 
-## Model Card Contact
 
-[More Information Needed]
+We use full-parameter finetuning for the projector and apply LoRA to the language model.