Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,213 @@
 ---
+language:
+- en
+- ko
+- zh
 license: apache-2.0
+library_name: peft
+pipeline_tag: visual-question-answering
+tags:
+- vision
+- visual-question-answering
+- multimodal
+- qwen
+- lora
+- tcm
+- traditional-chinese-medicine
+- tongue-diagnosis
 ---
+
+# ViTCM_LLM - Traditional Chinese Medicine Tongue Diagnosis Model
+
+This is a LoRA (Low-Rank Adaptation) adapter for the Qwen2.5-VL-32B-Instruct model, fine-tuned specifically for Traditional Chinese Medicine (TCM) tongue diagnosis tasks.
+
+## Model Details
+
+### Model Description
+
+- **Developed by:** Mark-CHAE
+- **Model type:** LoRA Adapter for Qwen2.5-VL-32B-Instruct
+- **Language(s) (NLP):** Chinese, Korean, English
+- **License:** Apache-2.0
+- **Finetuned from model:** Qwen/Qwen2.5-VL-32B-Instruct
+- **Specialization:** Traditional Chinese Medicine Tongue Diagnosis
+
+### Model Sources
+
+- **Repository:** [Mark-CHAE/shezhen](https://huggingface.co/Mark-CHAE/shezhen)
+- **Base Model:** [Qwen/Qwen2.5-VL-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct)
+
+## Uses
+
+### Direct Use
+
+This LoRA adapter can be used with the base Qwen2.5-VL-32B-Instruct model for multimodal vision-language tasks including:
+
+- Traditional Chinese Medicine tongue diagnosis
+- Tongue image analysis and interpretation
+- Visual question answering for medical images
+- Multimodal medical conversations
+- Symptom analysis from tongue images
+
+### Downstream Use
+
+The adapter can be loaded with the base model for inference or further fine-tuning on specific TCM diagnosis tasks.
+
+### Out-of-Scope Use
+
+This model should not be used for:
+
+- Generating harmful, offensive, or inappropriate content
+- Creating deepfakes or misleading visual content
+- Any illegal activities
+- Making actual medical diagnoses without proper medical supervision
+
+### Recommendations
+
+Users should:
+
+- Verify outputs for accuracy and appropriateness
+- Be aware of potential biases in the model
+- Use appropriate safety measures when deploying
+- Not rely solely on this model for medical diagnosis
+- Consult qualified medical professionals for actual diagnosis
+
+## How to Get Started with the Model
+
+### Using the Inference Widget
+
+You can try the model directly in the browser using the Visual Question Answering widget above. Simply upload a tongue image and ask a question about it.
+
+### Using the Model in Code
+
+```python
+from peft import PeftModel
+from transformers import AutoTokenizer, AutoModelForCausalLM, AutoProcessor
+import torch
+from PIL import Image
+
+# Load base model and tokenizer
+base_model = AutoModelForCausalLM.from_pretrained(
+    "Qwen/Qwen2.5-VL-32B-Instruct",
+    torch_dtype=torch.float16,
+    device_map="auto"
+)
+tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-VL-32B-Instruct")
+processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-32B-Instruct")
+
+# Load LoRA adapter
+model = PeftModel.from_pretrained(base_model, "Mark-CHAE/shezhen")
+
+# Prepare inputs
+image = Image.open("tongue_image.jpg")
+question = "根据图片判断舌诊内容"
+
+prompt = f"<|im_start|>user\n<image>\n{question}<|im_end|>\n<|im_start|>assistant\n"
+
+inputs = processor(
+    text=prompt,
+    images=image,
+    return_tensors="pt"
+)
+
+# Generate response
+with torch.no_grad():
+    outputs = model.generate(
+        **inputs,
+        max_length=512,
+        temperature=0.7,
+        top_p=0.9,
+        do_sample=True,
+        pad_token_id=tokenizer.eos_token_id
+    )
+
+response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+answer = response.split("<|im_start|>assistant")[-1].strip()
+print(answer)
+```
+
+## Training Details
+
+### Training Data
+
+The model was fine-tuned on multimodal vision-language data including Chinese, Korean, and English content, with specific focus on Traditional Chinese Medicine tongue diagnosis scenarios.
+
+### Training Procedure
+
+#### Training Hyperparameters
+
+- **Training regime:** LoRA fine-tuning
+- **LoRA rank:** 64
+- **LoRA alpha:** 128
+- **Target modules:** v_proj, qkv, attn.proj, q_proj, gate_proj, down_proj, up_proj, o_proj, k_proj
+- **Training steps:** 2700
+- **Epochs:** ~8.9
+
+#### Speeds, Sizes, Times
+
+- **Adapter size:** 2.2GB
+- **Base model:** Qwen2.5-VL-32B-Instruct (32B parameters)
+
+## Evaluation
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+Evaluation was performed on multimodal vision-language benchmarks with focus on medical image understanding and TCM tongue diagnosis.
+
+#### Metrics
+
+Standard vision-language evaluation metrics including accuracy, BLEU, and human evaluation scores.
+
+### Results
+
+[Evaluation results to be added]
+
+#### Summary
+
+This LoRA adapter provides an efficient way to adapt the Qwen2.5-VL-32B-Instruct model for Traditional Chinese Medicine tongue diagnosis tasks while maintaining the base model's capabilities.
+
+## Technical Specifications
+
+### Model Architecture and Objective
+
+- **Architecture:** LoRA adapter for Qwen2.5-VL-32B-Instruct
+- **Objective:** Multimodal vision-language understanding and generation, specialized for TCM tongue diagnosis
+
+### Compute Infrastructure
+
+#### Hardware
+
+[To be specified]
+
+#### Software
+
+- PEFT 0.15.2
+- Transformers library
+- PyTorch
+
+## Citation
+
+**BibTeX:**
+
+```bibtex
+@misc{vitcm-llm,
+  author = {Mark-CHAE},
+  title = {ViTCM_LLM: Traditional Chinese Medicine Tongue Diagnosis Model},
+  year = {2024},
+  url = {https://huggingface.co/Mark-CHAE/shezhen}
+}
+```
+
+**APA:**
+
+Mark-CHAE. (2024). ViTCM_LLM: Traditional Chinese Medicine Tongue Diagnosis Model. Hugging Face. https://huggingface.co/Mark-CHAE/shezhen
+
+## Model Card Contact
+
+For questions about this model, please contact the model author.
+
+### Framework versions
+
+- PEFT 0.15.2

adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-VL-32B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "qkv",
+    "attn.proj",
+    "q_proj",
+    "gate_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

app.py

@@ -0,0 +1,149 @@
+import streamlit as st
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM, AutoProcessor
+from peft import PeftModel
+from PIL import Image
+import io
+
+# Page configuration
+st.set_page_config(
+    page_title="ViTCM_LLM Tongue Diagnosis",
+    page_icon="🖼️",
+    layout="wide"
+)
+
+# Title
+st.title("🖼️ ViTCM_LLM Tongue Diagnosis")
+st.markdown("**ViTCM_LLM - Traditional Chinese Medicine Tongue Diagnosis Model**")
+
+# Model loading
+@st.cache_resource
+def load_model():
+    """Load the ViTCM_LLM model for TCM tongue diagnosis."""
+    try:
+        # Tokenizer and processor
+        tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-VL-32B-Instruct")
+        processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-32B-Instruct")
+        
+        # Base model
+        base_model = AutoModelForCausalLM.from_pretrained(
+            "Qwen/Qwen2.5-VL-32B-Instruct",
+            torch_dtype=torch.float16,
+            device_map="auto"
+        )
+        
+        # LoRA adapter
+        model = PeftModel.from_pretrained(base_model, "Mark-CHAE/shezhen")
+        
+        return model, tokenizer, processor
+    except Exception as e:
+        st.error(f"Model loading failed: {e}")
+        return None, None, None
+
+# Sidebar
+with st.sidebar:
+    st.header("⚙️ Settings")
+    
+    # Inference parameters
+    max_length = st.slider("Max tokens", 100, 1024, 512)
+    temperature = st.slider("Temperature", 0.1, 2.0, 0.7, 0.1)
+    top_p = st.slider("Top-p", 0.1, 1.0, 0.9, 0.05)
+    
+    # Model load button
+    if st.button("🚀 Load Model", type="primary"):
+        with st.spinner("Loading ViTCM_LLM model..."):
+            model, tokenizer, processor = load_model()
+            if model is not None:
+                st.session_state.model = model
+                st.session_state.tokenizer = tokenizer
+                st.session_state.processor = processor
+                st.session_state.model_loaded = True
+                st.success("✅ ViTCM_LLM model loaded successfully!")
+
+# Main content
+if not st.session_state.get('model_loaded', False):
+    st.info("👈 Click 'Load Model' button in the sidebar to start tongue diagnosis.")
+    st.stop()
+
+# Image upload
+st.header("📸 Tongue Image Upload")
+uploaded_file = st.file_uploader(
+    "Upload a tongue image for TCM diagnosis",
+    type=['png', 'jpg', 'jpeg']
+)
+
+if uploaded_file is not None:
+    # Display image
+    image = Image.open(uploaded_file)
+    st.image(image, caption="Uploaded tongue image", use_column_width=True)
+    
+    # Question input
+    st.header("❓ Tongue Diagnosis Question")
+    question = st.text_area(
+        "Ask a question about the tongue image for TCM diagnosis",
+        placeholder="e.g., 根据图片判断舌诊内容",
+        height=100
+    )
+    
+    # Analyze button
+    if st.button("🔍 Analyze Tongue", type="primary") and question.strip():
+        with st.spinner("Analyzing tongue for TCM diagnosis..."):
+            try:
+                # Construct prompt
+                prompt = f"<|im_start|>user\n<image>\n{question}<|im_end|>\n<|im_start|>assistant\n"
+                
+                # Process inputs
+                inputs = st.session_state.processor(
+                    text=prompt,
+                    images=image,
+                    return_tensors="pt"
+                )
+                
+                # Inference
+                with torch.no_grad():
+                    outputs = st.session_state.model.generate(
+                        **inputs,
+                        max_length=max_length,
+                        temperature=temperature,
+                        top_p=top_p,
+                        do_sample=True,
+                        pad_token_id=st.session_state.tokenizer.eos_token_id
+                    )
+                
+                # Process results
+                response = st.session_state.tokenizer.decode(outputs[0], skip_special_tokens=True)
+                answer = response.split("<|im_start|>assistant")[-1].strip()
+                
+                # Display results
+                st.header("💡 TCM Tongue Diagnosis")
+                st.markdown(f"**Question:** {question}")
+                st.markdown(f"**Diagnosis:** {answer}")
+                
+            except Exception as e:
+                st.error(f"Error occurred during tongue analysis: {e}")
+
+# Usage examples
+with st.expander("📚 Tongue Diagnosis Examples"):
+    st.markdown("""
+    ### Tongue Diagnosis Questions:
+    - 根据图片判断舌诊内容
+    - 分析舌头的颜色和形状
+    - 判断舌苔的厚薄和颜色
+    - 分析舌头的裂纹和斑点
+    - 评估舌头的整体健康状况
+    """)
+
+# Model information
+with st.expander("ℹ️ Model Information"):
+    st.markdown("""
+    ### ViTCM_LLM - Traditional Chinese Medicine Tongue Diagnosis Model
+    
+    - **Base Model**: Qwen/Qwen2.5-VL-32B-Instruct
+    - **Adapter**: Mark-CHAE/shezhen (ViTCM_LLM)
+    - **Language**: Chinese
+    - **License**: Apache-2.0
+    - **Specialization**: Traditional Chinese Medicine Tongue Diagnosis
+    """)
+
+st.markdown("---")
+st.markdown("**ViTCM_LLM Tongue Diagnosis** | Powered by Qwen2.5-VL-32B-Instruct") 

chat_template.jinja

@@ -0,0 +1,7 @@
+{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

config.json

@@ -0,0 +1,29 @@
+{
+  "task": "visual-question-answering",
+  "model": {
+    "framework": "pytorch",
+    "type": "causal-lm"
+  },
+  "inference": {
+    "max_length": 512,
+    "temperature": 0.7,
+    "top_p": 0.9
+  },
+  "inputs": {
+    "question": {
+      "type": "string",
+      "description": "The question about the tongue image for TCM diagnosis (e.g., '根据图片判断舌诊内容')"
+    },
+    "image": {
+      "type": "string",
+      "description": "Base64 encoded tongue image"
+    }
+  },
+  "outputs": {
+    "answer": {
+      "type": "string",
+      "description": "The TCM tongue diagnosis analysis"
+    }
+  },
+  "description": "ViTCM_LLM - Traditional Chinese Medicine Tongue Diagnosis Model"
+} 

config.toml

@@ -0,0 +1,15 @@
+[theme]
+primaryColor = "#FF6B6B"
+backgroundColor = "#FFFFFF"
+secondaryBackgroundColor = "#F0F2F6"
+textColor = "#262730"
+font = "sans serif"
+
+[server]
+headless = true
+port = 8501
+enableCORS = false
+enableXsrfProtection = false
+
+[browser]
+gatherUsageStats = false 

inference.py

@@ -0,0 +1,70 @@
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM, AutoProcessor
+from peft import PeftModel
+from PIL import Image
+import base64
+import io
+
+# Load model and tokenizer
+@torch.no_grad()
+def load_model():
+    """Load the ViTCM_LLM model for Traditional Chinese Medicine Tongue diagnosis."""
+    tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-VL-32B-Instruct")
+    processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-32B-Instruct")
+    
+    base_model = AutoModelForCausalLM.from_pretrained(
+        "Qwen/Qwen2.5-VL-32B-Instruct",
+        torch_dtype=torch.float16,
+        device_map="auto"
+    )
+    
+    model = PeftModel.from_pretrained(base_model, "Mark-CHAE/shezhen")
+    return model, tokenizer, processor
+
+# Initialize model
+model, tokenizer, processor = load_model()
+
+def query(question: str, image: str) -> str:
+    """
+    Analyze tongue image for Traditional Chinese Medicine diagnosis.
+    
+    Args:
+        question: The question about the tongue image (e.g., "根据图片判断舌诊内容")
+        image: Base64 encoded image string
+    
+    Returns:
+        The TCM diagnosis analysis of the tongue
+    """
+    try:
+        # Decode base64 image
+        image_data = base64.b64decode(image)
+        image_pil = Image.open(io.BytesIO(image_data))
+        
+        # Construct prompt for TCM tongue diagnosis
+        prompt = f"<|im_start|>user\n<image>\n{question}<|im_end|>\n<|im_start|>assistant\n"
+        
+        # Process inputs
+        inputs = processor(
+            text=prompt,
+            images=image_pil,
+            return_tensors="pt"
+        )
+        
+        # Generate response
+        outputs = model.generate(
+            **inputs,
+            max_length=512,
+            temperature=0.7,
+            top_p=0.9,
+            do_sample=True,
+            pad_token_id=tokenizer.eos_token_id
+        )
+        
+        # Decode response
+        response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+        answer = response.split("<|im_start|>assistant")[-1].strip()
+        
+        return answer
+        
+    except Exception as e:
+        return f"Error processing request: {str(e)}" 

model_card.md

@@ -0,0 +1,199 @@
+---
+language:
+- en
+- ko
+license: apache-2.0
+library_name: peft
+pipeline_tag: visual-question-answering
+tags:
+- vision
+- visual-question-answering
+- multimodal
+- qwen
+- lora
+- tcm
+- traditional-chinese-medicine
+---
+
+# ViTCM_LLM - Traditional Chinese Medicine Diagnosis Model
+
+This is a LoRA (Low-Rank Adaptation) adapter for the Qwen2.5-VL-32B-Instruct model, fine-tuned specifically for Traditional Chinese Medicine (TCM) diagnosis tasks.
+
+## Model Details
+
+### Model Description
+
+- **Developed by:** Mark-CHAE
+- **Model type:** LoRA Adapter for Qwen2.5-VL-32B-Instruct
+- **Language(s) (NLP):** English, Korean
+- **License:** Apache-2.0
+- **Finetuned from model:** Qwen/Qwen2.5-VL-32B-Instruct
+- **Specialization:** Traditional Chinese Medicine Diagnosis
+
+### Model Sources
+
+- **Repository:** [Mark-CHAE/shezhen](https://huggingface.co/Mark-CHAE/shezhen)
+- **Base Model:** [Qwen/Qwen2.5-VL-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct)
+
+## Uses
+
+### Direct Use
+
+This LoRA adapter can be used with the base Qwen2.5-VL-32B-Instruct model for multimodal vision-language tasks including:
+
+- Image understanding and description
+- Visual question answering
+- Image-text generation
+- Multimodal conversations
+- Traditional Chinese Medicine diagnosis
+- Symptom analysis from medical images
+
+### Downstream Use
+
+The adapter can be loaded with the base model for inference or further fine-tuning on specific TCM diagnosis tasks.
+
+### Out-of-Scope Use
+
+This model should not be used for:
+
+- Generating harmful, offensive, or inappropriate content
+- Creating deepfakes or misleading visual content
+- Any illegal activities
+- Making actual medical diagnoses without proper medical supervision
+
+### Recommendations
+
+Users should:
+
+- Verify outputs for accuracy and appropriateness
+- Be aware of potential biases in the model
+- Use appropriate safety measures when deploying
+- Not rely solely on this model for medical diagnosis
+- Consult qualified medical professionals for actual diagnosis
+
+## How to Get Started with the Model
+
+### Using the Inference Widget
+
+You can try the model directly in the browser using the Visual Question Answering widget above. Simply upload an image and ask a question about it.
+
+### Using the Model in Code
+
+```python
+from peft import PeftModel
+from transformers import AutoTokenizer, AutoModelForCausalLM, AutoProcessor
+import torch
+from PIL import Image
+
+# Load base model and tokenizer
+base_model = AutoModelForCausalLM.from_pretrained(
+    "Qwen/Qwen2.5-VL-32B-Instruct",
+    torch_dtype=torch.float16,
+    device_map="auto"
+)
+tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-VL-32B-Instruct")
+processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-32B-Instruct")
+
+# Load LoRA adapter
+model = PeftModel.from_pretrained(base_model, "Mark-CHAE/shezhen")
+
+# Prepare inputs
+image = Image.open("your_image.jpg")
+question = "根据图片判断舌诊内容"
+
+prompt = f"<|im_start|>user\n<image>\n{question}<|im_end|>\n<|im_start|>assistant\n"
+
+inputs = processor(
+    text=prompt,
+    images=image,
+    return_tensors="pt"
+)
+
+# Generate response
+with torch.no_grad():
+    outputs = model.generate(
+        **inputs,
+        max_length=512,
+        temperature=0.7,
+        top_p=0.9,
+        do_sample=True,
+        pad_token_id=tokenizer.eos_token_id
+    )
+
+response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+answer = response.split("<|im_start|>assistant")[-1].strip()
+print(answer)
+```
+
+## Training Details
+
+### Training Data
+
+The model was fine-tuned on multimodal vision-language data including English and Korean content, with specific focus on Traditional Chinese Medicine diagnosis scenarios.
+
+### Training Procedure
+
+#### Training Hyperparameters
+
+- **Training regime:** LoRA fine-tuning
+- **LoRA rank:** 64
+- **LoRA alpha:** 128
+- **Target modules:** v_proj, qkv, attn.proj, q_proj, gate_proj, down_proj, up_proj, o_proj, k_proj
+
+#### Speeds, Sizes, Times
+
+- **Adapter size:** 2.2GB
+- **Base model:** Qwen2.5-VL-32B-Instruct (32B parameters)
+
+## Evaluation
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+Evaluation was performed on multimodal vision-language benchmarks with focus on medical image understanding.
+
+#### Metrics
+
+Standard vision-language evaluation metrics including accuracy, BLEU, and human evaluation scores.
+
+### Results
+
+[Evaluation results to be added]
+
+#### Summary
+
+This LoRA adapter provides an efficient way to adapt the Qwen2.5-VL-32B-Instruct model for Traditional Chinese Medicine diagnosis tasks while maintaining the base model's capabilities.
+
+
+## Technical Specifications
+
+### Model Architecture and Objective
+
+- **Architecture:** LoRA adapter for Qwen2.5-VL-32B-Instruct
+- **Objective:** Multimodal vision-language understanding and generation, specialized for TCM Tongue diagnosis
+
+### Compute Infrastructure
+
+#### Hardware
+
+[To be specified]
+
+#### Software
+
+- PEFT 0.15.2
+- Transformers library
+- PyTorch
+
+
+**APA:**
+
+Mark-CHAE. (2024). ViTCM_LLM: Traditional Chinese Medicine Diagnosis Model. Hugging Face. https://huggingface.co/Mark-CHAE/shezhen
+
+## Model Card Contact
+
+For questions about this model, please contact the model author.
+
+### Framework versions
+
+- PEFT 0.15.2 

preprocessor_config.json

@@ -0,0 +1,36 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessorFast",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}

requirements.txt

@@ -0,0 +1,7 @@
+streamlit>=1.28.0
+torch>=2.0.0
+transformers>=4.35.0
+peft>=0.7.0
+Pillow>=9.0.0
+accelerate>=0.20.0
+safetensors>=0.3.0 

space.yml

@@ -0,0 +1,9 @@
+title: ViTCM_LLM Tongue Diagnosis
+emoji: 🖼️
+colorFrom: blue
+colorTo: purple
+sdk: streamlit
+sdk_version: 1.28.0
+app_file: app.py
+pinned: false
+license: apache-2.0 

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:826c64105c507ac95e21ca8febaa9296b699bbd97820f7589c6148d912639205
+size 11422100

tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

video_preprocessor_config.json

@@ -0,0 +1,86 @@
+{
+  "_valid_kwargs_names": [
+    "do_convert_rgb",
+    "do_resize",
+    "size",
+    "size_divisor",
+    "default_to_square",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "do_pad",
+    "do_center_crop",
+    "crop_size",
+    "data_format",
+    "input_data_format",
+    "device",
+    "min_pixels",
+    "max_pixels",
+    "patch_size",
+    "temporal_patch_size",
+    "merge_size"
+  ],
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "model_valid_processing_keys": [
+    "do_convert_rgb",
+    "do_resize",
+    "size",
+    "size_divisor",
+    "default_to_square",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "do_pad",
+    "do_center_crop",
+    "crop_size",
+    "data_format",
+    "input_data_format",
+    "device",
+    "min_pixels",
+    "max_pixels",
+    "patch_size",
+    "temporal_patch_size",
+    "merge_size"
+  ],
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "size_divisor": null,
+  "temporal_patch_size": 2,
+  "video_processor_type": "Qwen2VLVideoProcessor"
+}