Add inference handler for HF Endpoints

README.md

@@ -1,22 +1,202 @@
 ---
-base_model: unsloth/qwen2-vl-2b-instruct-bnb-4bit
-tags:
-- text-generation-inference
-- transformers
-- unsloth
-- qwen2_vl
-- trl
-license: apache-2.0
-language:
-- en
+base_model: unsloth/Qwen2-VL-2B-Instruct
+library_name: peft
 ---
 
-# Uploaded  model
+# Model Card for Model ID
 
-- **Developed by:** BoghdadyJR
-- **License:** apache-2.0
-- **Finetuned from model :** unsloth/qwen2-vl-2b-instruct-bnb-4bit
+<!-- Provide a quick summary of what the model is/does. -->
 
-This qwen2_vl model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **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]
+
+### 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 -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+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 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]
+
+### 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 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]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.2

adapter_config.json

@@ -24,13 +24,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "k_proj",
+    "v_proj",
+    "up_proj",
     "o_proj",
     "down_proj",
-    "q_proj",
-    "up_proj",
-    "v_proj"
+    "gate_proj",
+    "k_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7942ec41c2ac0084a6ecf27663ee3b7cff3f3d7ccc1c9d77b9a984835e9d0e79
-size 36981072
+oid sha256:d63b8e9eca3db32d6df66e661439564f2f3e6f76473bd8deb46d213a0467fc40
+size 36986952

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 %}

handler.py

@@ -0,0 +1,122 @@
+from typing import Dict, List, Any
+from unsloth import FastVisionModel
+from PIL import Image
+import torch
+
+class EndpointHandler():
+    def __init__(self, path=""):
+        # Load model and tokenizer
+        self.model, self.tokenizer = FastVisionModel.from_pretrained(
+            path,
+            device_map="auto",
+            load_in_4bit=False,  # Use 4bit to reduce memory use. False for 16bit LoRA
+            use_gradient_checkpointing="unsloth",  # True or "unsloth" for long context
+        )
+        
+        # Enable for inference
+        FastVisionModel.for_inference(self.model)
+        
+        # Store the instruction template
+        self.instruction = """
+A conversation between a Healthcare Provider and an AI Medical Image Analysis Assistant. The provider shares a medical image, and the Assistant generates a clear description/report. The assistant first analyzes the image systematically, then provides a concise report. The analysis process and report are enclosed within <thinking> </thinking><answer> </answer>.
+
+Always respond in this format:
+
+<thinking>
+1. Initial Assessment:
+   - What type of image is this? (X-ray, CT, MRI, etc.)
+   - Which body part/region is shown?
+   - Is the image quality adequate?
+
+2. Key Findings:
+   - What are the normal structures visible?
+   - Are there any abnormalities?
+   - What are the important measurements?
+
+3. Clinical Significance:
+   - What are the main clinical findings?
+   - Are there any critical findings?
+</thinking>
+
+<answer>
+Brief Structured Report:
+1. EXAM TYPE: [imaging type and body region]
+2. FINDINGS: [key observations and abnormalities]
+3. IMPRESSION: [summary and clinical significance]
+</answer>
+"""
+
+    def __call__(self, data: Any) -> List[Dict[str, Any]]:
+        """
+        Args:
+            data (:obj:):
+                includes the input data and the parameters for the inference.
+                Expected format:
+                {
+                    "inputs": {
+                        "image": PIL.Image object,
+                        "instruction": optional_custom_instruction
+                    },
+                    "parameters": {
+                        "max_new_tokens": 512,
+                        "temperature": 0.7,
+                        "top_p": 0.9,
+                        ...
+                    }
+                }
+        Return:
+            A :obj:`list`:. The list contains a dictionary with:
+                - "generated_text": The model's response
+        """
+        inputs = data.pop("inputs", data)
+        parameters = data.pop("parameters", {})
+        
+        # Extract image and instruction
+        image = inputs.get("image")
+        custom_instruction = inputs.get("instruction", self.instruction)
+        
+        # Prepare messages
+        messages = [
+            {"role": "user", "content": [
+                {"type": "image"},
+                {"type": "text", "text": custom_instruction}
+            ]}
+        ]
+        
+        # Apply chat template
+        input_text = self.tokenizer.apply_chat_template(messages, add_generation_prompt=True)
+        
+        # Tokenize inputs
+        model_inputs = self.tokenizer(
+            image,
+            input_text,
+            add_special_tokens=False,
+            return_tensors="pt",
+        ).to(self.model.device)
+        
+        # Set default parameters
+        generation_params = {
+            "max_new_tokens": parameters.get("max_new_tokens", 512),
+            "temperature": parameters.get("temperature", 0.7),
+            "top_p": parameters.get("top_p", 0.9),
+            "min_p": parameters.get("min_p", 0.1),
+            "use_cache": True,
+            "do_sample": parameters.get("do_sample", True),
+            "repetition_penalty": parameters.get("repetition_penalty", 1.1),
+        }
+        
+        output_ids = self.model.generate(
+                **model_inputs,
+                **generation_params
+        )
+            
+        
+        # Decode output
+        generated_text = self.tokenizer.decode(output_ids[0], skip_special_tokens=True)
+        
+        # Extract only the generated response (remove the prompt)
+        response = generated_text.split(custom_instruction)[-1].strip()
+        
+        return [{
+            "generated_text": response
+        }]

requirements.txt

@@ -0,0 +1,5 @@
+torch>=2.0.0
+transformers>=4.36.0
+unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git
+Pillow>=9.0.0
+accelerate>=0.25.0

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00ff1d43b119596534f778ecc067f5b457d2ce2fe2665ab12fe7a8705fda3437
-size 11420639
+oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
+size 11420371

tokenizer_config.json

@@ -130,22 +130,15 @@
     "<|video_pad|>"
   ],
   "bos_token": null,
-  "chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",
   "extra_special_tokens": {},
-  "max_length": 2048,
   "model_max_length": 32768,
-  "pad_to_multiple_of": null,
   "pad_token": "<|vision_pad|>",
-  "pad_token_type_id": 0,
   "padding_side": "right",
   "processor_class": "Qwen2VLProcessor",
   "split_special_tokens": false,
-  "stride": 0,
   "tokenizer_class": "Qwen2Tokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "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": "Qwen2VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "size_divisor": null,
+  "temporal_patch_size": 2,
+  "video_processor_type": "Qwen2VLVideoProcessor"
+}