Update README.md

README.md

@@ -1,3 +1,141 @@
----
-license: cc-by-4.0
----
+---
+license: cc-by-4.0
+datasets:
+- alfredplpl/commoncatalog-cc-by-ext
+- turing-motors/LLaVA-Pretrain-JA
+language:
+- ja
+pipeline_tag: image-to-text
+---
+
+# LLaVA-JP Model Card
+
+## Model detail
+
+**Model type:**
+
+LLaVA-JP is a vision-language model that can converse about input images.<br>
+This model is an LVLM model trained using [google/siglip-so400m-patch14-384](https://huggingface.co/google/siglip-so400m-patch14-384) as the image encoder and [llm-jp/llm-jp-1.3b-v1.0](https://huggingface.co/llm-jp/llm-jp-1.3b-v1.0) as the text decoder. supports the input of 768 x 768 high resolution images by scaling_on_scales method. 
+
+**Training:**
+
+This model was initially trained with the Vision Projector using LLaVA-Pretrain-JA.<br>
+In the second phase, it was fine-tuned with 10.5k of commoncatalog-cc-by-ext.
+
+resources for more information: https://github.com/tosiyuki/LLaVA-JP/tree/main
+
+## How to use the model
+**1. Download dependencies**
+```
+git clone https://github.com/tosiyuki/LLaVA-JP.git
+```
+
+**2. Inference**
+```python
+import torch
+import transformers
+from PIL import Image
+
+from transformers.generation.streamers import TextStreamer
+from llava.constants import DEFAULT_IMAGE_TOKEN, IMAGE_TOKEN_INDEX
+from llava.conversation import conv_templates, SeparatorStyle
+from llava.model.llava_gpt2 import LlavaGpt2ForCausalLM
+from llava.train.dataset import tokenizer_image_token
+
+
+if __name__ == "__main__":
+    model_path = 'toshi456/llava-jp-1.3b-v1.1-commoncatalog-cc-by-ext-10k'
+    device = "cuda" if torch.cuda.is_available() else "cpu"
+    torch_dtype = torch.bfloat16 if device=="cuda" else torch.float32
+
+    model = LlavaGpt2ForCausalLM.from_pretrained(
+        model_path, 
+        low_cpu_mem_usage=True,
+        use_safetensors=True,
+        torch_dtype=torch_dtype,
+        device_map=device,
+    )
+    tokenizer = transformers.AutoTokenizer.from_pretrained(
+        model_path,
+        model_max_length=1532,
+        padding_side="right",
+        use_fast=False,
+    )
+    model.eval()
+
+    conv_mode = "v1"
+    conv = conv_templates[conv_mode].copy()
+
+    # image pre-process
+    image_url = "https://huggingface.co/rinna/bilingual-gpt-neox-4b-minigpt4/resolve/main/sample.jpg"
+    image = Image.open(requests.get(image_url, stream=True).raw).convert('RGB')
+    
+    image_size = model.get_model().vision_tower.image_processor.size["height"]
+    if model.get_model().vision_tower.scales is not None:
+        image_size = model.get_model().vision_tower.image_processor.size["height"] * len(model.get_model().vision_tower.scales)
+    
+    if device == "cuda":
+        image_tensor = model.get_model().vision_tower.image_processor(
+            image, 
+            return_tensors='pt', 
+            size={"height": image_size, "width": image_size}
+        )['pixel_values'].half().cuda().to(torch_dtype)
+    else:
+        image_tensor = model.get_model().vision_tower.image_processor(
+            image, 
+            return_tensors='pt', 
+            size={"height": image_size, "width": image_size}
+        )['pixel_values'].to(torch_dtype)
+
+    # create prompt
+    # ユーザー: <image>\n{prompt}
+    prompt = "画像について説明してください。"
+    inp = DEFAULT_IMAGE_TOKEN + '\n' + prompt
+    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)
+    if device == "cuda":
+        input_ids = input_ids.to(device)
+
+    input_ids = input_ids[:, :-1] # </sep>がinputの最後に入るので削除する
+    stop_str = conv.sep if conv.sep_style != SeparatorStyle.TWO else conv.sep2
+    keywords = [stop_str]
+    streamer = TextStreamer(tokenizer, skip_prompt=True, timeout=20.0)
+
+    # predict
+    with torch.inference_mode():
+        output_id = model.generate(
+            inputs=input_ids,
+            images=image_tensor,
+            do_sample=False,
+            temperature=1.0,
+            top_p=1.0,
+            max_new_tokens=256,
+            streamer=streamer,
+            use_cache=True,
+        )
+
+    """画像には、木製の表面に座っている猫が描かれています。猫は、ラップトップの画面に集中しています。ラップトップは、黒い金属フレームと白いキーボードを持つ、鮮やかなオレンジ色です。猫の目は閉じており、リラックスした状態を示唆しています。背景は、猫のラップトップとその周囲の詳細を強調する灰色のテクスチャーです。画像にはテキストや他のオブジェクトは含まれていません。猫とラップトップの相対的な位置関係は、猫がラップトップの画面に集中していることを示唆しています。画像には他のオブジェクトや行動は含まれていません。<EOD|LLM-jp>"""
+```
+
+## Training dataset
+**Stage1 Pretrain**
+- [LLaVA-Pretrain-JA](https://huggingface.co/datasets/turing-motors/LLaVA-Pretrain-JA)
+
+**Stage2 Fine-tuning**
+- [commoncatalog-cc-by-ext](https://huggingface.co/datasets/alfredplpl/commoncatalog-cc-by-ext)
+
+## Acknowledgement
+- [LLaVA](https://llava-vl.github.io/)
+- [LLM-jp](https://llm-jp.nii.ac.jp/)
+- [scaling_on_scales](https://github.com/bfshi/scaling_on_scales/tree/master)
+
+## License
+Apache License 2.0