Willie999

Anidane

Deploy Dedicated

README

License: apache-2.0

Model Details

Developed by: WILLIAMS OPOKU & SAMUEL AGYEMANG
Model Type: Multimodal Vision-Language Model (Image-Text to Text)
Base Model: google/medgemma-1.5-4b-it (Gemma 3 / MedSigLIP Core)
Fine-Tuning Method: QLoRA (4-bit quantized) via Unsloth
Primary Domain: Ophthalmology, Retinal Image Diagnostic Reporting

Intended Uses & Limitations

Intended Use

Clinical Assistant Tool: Providing detailed descriptive impressions of fundus abnormalities (e.g., microaneurysms, vascular alterations, optic disc changes).
Research & Education: Analyzing pathological trends in public ophthalmic imagery datasets, with an emphasis on mitigating geographic screening biases in underrepresented cohorts.

Limitations & Out of Scope

Not a Standalone Diagnostic Tool: Anidane is designed strictly as an assistive reporting tool and must not be used for definitive medical diagnoses without certified practitioner oversight.
Data Demographics: While optimized to interpret global clinical profiles, the model's accuracy is closely tied to the imaging quality and distribution found within the underlying train sets.

Training Details

Training Dataset

Dataset Source: smrndmdude/eye-diseases-dataset
Modality: High-resolution eye/fundus photography paired with localized clinical diagnostic captions.

Hyperparameters & Optimization

The model was fine-tuned using the following configurations:

Quantization: 4-bit NormalFloat4 (NF4)
LoRA Rank ( $r$ ): 16
LoRA Alpha ( $α$ ): 16
Optimizer: adamw_8bit
Learning Rate: $2 \times 1 0 - 4$ (Linear decay)
Gradient Accumulation Steps: 4
Batch Size: 2 per device
59

Training Loss Curve Performance

During fine-tuning, the model displayed highly stable convergence characteristics, with training loss scaling down seamlessly as follows:

Initial Phase (Step 1): 6.061622
Mid Phase (Step 30): 0.171660
Final Convergence Phase (Step 59): 0.080335

How to Use the Model

You can load and query Anidane using the Hugging Face transformers library or via unsloth for accelerated inference.

python

import torch from PIL import Image from transformers import AutoProcessor from unsloth import FastVisionModel # Import FastVisionModel   model_id = "Willie999/Anidane"   processor = AutoProcessor.from_pretrained(model_id) # Use FastVisionModel for loading the model, consistent with training # FastVisionModel.from_pretrained returns a tuple (model, processor), so we unpack it. model, _ = FastVisionModel.from_pretrained(     model_name = model_id, # Use model_name for FastVisionModel     torch_dtype=torch.bfloat16,     device_map="auto" )   # Load a target retinal image image = Image.open("/content/red-eye-disease.jpg").convert("RGB")   messages = [     {         "role": "user",         "content": [             {"type": "image"},             {"type": "text", "text": "Analyze this fundus/eye photograph. Provide a clear diagnostic assessment focusing on localized anomalies."}         ]     } ]   prompt = processor.apply_chat_template(messages, add_generation_prompt=True) inputs = processor(text=prompt, images=image, return_tensors="pt").to(model.device)   with torch.no_grad():     generated_ids = model.generate(         input_ids=inputs["input_ids"],         pixel_values=inputs["pixel_values"], # Explicitly pass pixel_values         max_new_tokens=256,         do_sample=False     )   response = processor.batch_decode(     generated_ids[:, inputs["input_ids"].shape[1]:],     skip_special_tokens=True )[0]   print("Anidane Analysis:", response)

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Container

Run this model inference with full control and performance in your environment.

Learn more

Model Details

Model Provider

Willie999

Model Tree

Base

google/medgemma-1.5-4b-it

Adapter

this model

Input Modalities

Text

Output Modalities

Text

Supported Functionality

Dedicated EndpointsContainer

Explore FriendliAI today

Get started Talk to an engineer

README

License: apache-2.0

Model Details

Developed by: WILLIAMS OPOKU & SAMUEL AGYEMANG
Model Type: Multimodal Vision-Language Model (Image-Text to Text)
Base Model: google/medgemma-1.5-4b-it (Gemma 3 / MedSigLIP Core)
Fine-Tuning Method: QLoRA (4-bit quantized) via Unsloth
Primary Domain: Ophthalmology, Retinal Image Diagnostic Reporting

Intended Uses & Limitations

Intended Use

Clinical Assistant Tool: Providing detailed descriptive impressions of fundus abnormalities (e.g., microaneurysms, vascular alterations, optic disc changes).
Research & Education: Analyzing pathological trends in public ophthalmic imagery datasets, with an emphasis on mitigating geographic screening biases in underrepresented cohorts.

Limitations & Out of Scope

Not a Standalone Diagnostic Tool: Anidane is designed strictly as an assistive reporting tool and must not be used for definitive medical diagnoses without certified practitioner oversight.
Data Demographics: While optimized to interpret global clinical profiles, the model's accuracy is closely tied to the imaging quality and distribution found within the underlying train sets.

Training Details

Training Dataset

Dataset Source: smrndmdude/eye-diseases-dataset
Modality: High-resolution eye/fundus photography paired with localized clinical diagnostic captions.

Hyperparameters & Optimization

The model was fine-tuned using the following configurations:

Quantization: 4-bit NormalFloat4 (NF4)
LoRA Rank ( $r$ ): 16
LoRA Alpha ( $α$ ): 16
Optimizer: adamw_8bit
Learning Rate: $2 \times 1 0 - 4$ (Linear decay)
Gradient Accumulation Steps: 4
Batch Size: 2 per device
59

Training Loss Curve Performance

During fine-tuning, the model displayed highly stable convergence characteristics, with training loss scaling down seamlessly as follows:

Initial Phase (Step 1): 6.061622
Mid Phase (Step 30): 0.171660
Final Convergence Phase (Step 59): 0.080335

How to Use the Model

You can load and query Anidane using the Hugging Face transformers library or via unsloth for accelerated inference.

python

import torch from PIL import Image from transformers import AutoProcessor from unsloth import FastVisionModel # Import FastVisionModel   model_id = "Willie999/Anidane"   processor = AutoProcessor.from_pretrained(model_id) # Use FastVisionModel for loading the model, consistent with training # FastVisionModel.from_pretrained returns a tuple (model, processor), so we unpack it. model, _ = FastVisionModel.from_pretrained(     model_name = model_id, # Use model_name for FastVisionModel     torch_dtype=torch.bfloat16,     device_map="auto" )   # Load a target retinal image image = Image.open("/content/red-eye-disease.jpg").convert("RGB")   messages = [     {         "role": "user",         "content": [             {"type": "image"},             {"type": "text", "text": "Analyze this fundus/eye photograph. Provide a clear diagnostic assessment focusing on localized anomalies."}         ]     } ]   prompt = processor.apply_chat_template(messages, add_generation_prompt=True) inputs = processor(text=prompt, images=image, return_tensors="pt").to(model.device)   with torch.no_grad():     generated_ids = model.generate(         input_ids=inputs["input_ids"],         pixel_values=inputs["pixel_values"], # Explicitly pass pixel_values         max_new_tokens=256,         do_sample=False     )   response = processor.batch_decode(     generated_ids[:, inputs["input_ids"].shape[1]:],     skip_special_tokens=True )[0]   print("Anidane Analysis:", response)