Update README.md

README.md

@@ -11,191 +11,101 @@ library_name: transformers
 This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
 
 ## Model Details
+**MMICL(Multi-Modal In-Context Learning)** is a multimodal vision-language model that incorporates blip2/instrcutblip. 
+It has the ability to analyze and understand multiple images, as well as follow instructions. 
 
-### Model Description
-
-<!-- Provide a longer summary of what this model is. -->
-
-
-
-- **Developed by:** [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]
-
-### Model Sources [optional]
-
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-
-## Uses
-
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
-### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[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 -->
+### Model Description
+MMICL outperforms the VL model of the same size and performs exceptionally well on complex visual reasoning datasets. 
+Till 21st Aug. 2023, it achieves **state-of-the-art ** performance on both multimodal task leaderboards and a wide range of vision-language tasks. 
+Furthermore, it showcases new capabilities in video understanding and multimodal in-context learning (M-ICL).
++ <mark>**Capability of multiple images refering and reasoning**<mark>
 
-[More Information Needed]
++ <mark>**Manually constructed In-context instruction tuning dataset**<mark>
 
-### Out-of-Scope Use
++ Till 21st Aug. 2023 **1st on [MME](https://github.com/BradyFU/Awesome-Multimodal-Large-Language-Models/tree/Evaluation), 1st on [MMBench](https://opencompass.org.cn/leaderboard-multimodal)**
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
++ Visual Encoder:  VIT-L from CLIP/ ViT-G/14 from EVA-CLIP 
 
-[More Information Needed]
++ Pre-trained LLM: FlanT5-XL/ FlanT5-XXL/ Vicuna-7B/ Vicuna-13B
+<!-- Provide a longer summary of what this model is. -->
 
-## Bias, Risks, and Limitations
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
 
-[More Information Needed]
+- **Developed by:** [More Information Needed]
+- **License:** MIT
+- **Finetuned from model :** [instructblip-flan-t5-xxl](https://huggingface.co/Salesforce/instructblip-flan-t5-xxl)
 
-### Recommendations
+<!-- Provide the basic links for the model. -->
 
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+- **Repository:** [MMICL](https://github.com/HaozheZhao/MIC)
 
-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.
-
-[More Information Needed]
-
-## Training Details
-
-### Training Data
-
-<!-- This should link to a Data 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]
-
-### Training Procedure 
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### 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 Data 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
+```
+# For T5 based model
+from model.instructblip import InstructBlipConfig, InstructBlipModel, InstructBlipPreTrainedModel,InstructBlipForConditionalGeneration,InstructBlipProcessor
+import datasets
+import json
+import transformers
+from PIL import Image
+import torch
+from model.blip2 import Blip2Processor,Blip2ForConditionalGeneration
+from model.blip2 import Blip2Config
+model_type="instructblip"
+model_ckpt="BleachNick/MMICL-Instructblip-T5-xxl"
 
-[More Information Needed]
+if 'blip2' in model_type:
+    model = Blip2ForConditionalGeneration.from_pretrained(
+            model_ckpt,
+            config=config).to('cuda:0',dtype=torch.bfloat16)
+elif 'instructblip' in model_type:
+    model = InstructBlipForConditionalGeneration.from_pretrained(
+        model_ckpt,
+        config=config).to('cuda:0',dtype=torch.bfloat16) 
 
-## 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. -->
+sp = ["图"]+[f"<image{i}>" for i in range(20)]
 
-**BibTeX:**
+processor = InstructBlipProcessor.from_pretrained(
+    model_ckpt
+)
+# processor = Blip2Processor.from_pretrained(
+#     model_ckpt
+# )
 
-[More Information Needed]
+sp = sp+processor.tokenizer.additional_special_tokens[len(sp):]
+processor.tokenizer.add_special_tokens({'additional_special_tokens':sp})
 
-**APA:**
 
-[More Information Needed]
+prompt = ['Use the image 0: <image0>图,image 1: <image1>图 and image 2: <image2>图 as a visual aid to help you calculate the equation accurately. image 0 is 2+1=3.\nimage 1 is 5+6=11.\nimage 2 is"']
 
-## Glossary [optional]
+prompt = " ".join(prompt)
 
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+inputs = processor(images=images, text=prompt, return_tensors="pt")
 
-[More Information Needed]
+inputs['pixel_values'] = inputs['pixel_values'].to(torch.bfloat16)
+inputs['img_mask'] = torch.tensor([[1 for i in range(len(images))]])
+inputs['pixel_values'] = inputs['pixel_values'].unsqueeze(0)
 
-## More Information [optional]
+inputs = inputs.to('cuda:0')
+outputs = model.generate(
+        pixel_values = inputs['pixel_values'],
+        input_ids = inputs['input_ids'],
+        attention_mask = inputs['attention_mask'],
+        img_mask = inputs['img_mask']
+)
+generated_text = processor.batch_decode(outputs, skip_special_tokens=True)[0].strip()
+print(generated_text)
 
-[More Information Needed]
+```
 
-## Model Card Authors [optional]
+####
+ Training Hyperparameters
 
-[More Information Needed]
+- **Training regime:** [fp32, bf16 mixed precision, bf16 non-mixed precision] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
 
-## Model Card Contact
 
-[More Information Needed]