Upload README.md

README.md

@@ -1,58 +1,113 @@
 ---
+license: gemma
 base_model: google/gemma-3-4b-it
-library_name: transformers
-model_name: checkpoints
 tags:
-- generated_from_trainer
-- trl
-- sft
-licence: license
+- vision-language-model
+- TEM
+- microscopy
+- materials-science
+- gemma
+- scientific-VLM
+language:
+- en
+pipeline_tag: image-text-to-text
 ---
 
-# Model Card for checkpoints
+# ATOMIC-Gemma
 
-This model is a fine-tuned version of [google/gemma-3-4b-it](https://huggingface.co/google/gemma-3-4b-it).
-It has been trained using [TRL](https://github.com/huggingface/trl).
+ATOMIC-Gemma is a domain-specific Vision-Language Model for Transmission Electron Microscopy (TEM), fine-tuned from Gemma3-4B-IT using Stage 2 instruction tuning on TEM conversation data.
 
-## Quick start
+> **Note:** ATOMIC-Gemma is developed after the ECCV 2026 submission deadline and is **not part of the published paper**. It is released here to demonstrate the generalizability of the ATOMIC training pipeline across different base model architectures.
 
-```python
-from transformers import pipeline
+For the published paper and full pipeline, please refer to our GitHub repository:
+👉 [https://github.com/SemiMIRTLab/ATOMIC](https://github.com/SemiMIRTLab/ATOMIC)
 
-question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="None", device="cuda")
-output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
-print(output["generated_text"])
-```
+---
 
-## Training procedure
+## Model Details
 
- 
+| | |
+|---|---|
+| **Base Model** | Gemma3-4B-IT (`google/gemma-3-4b-it`) |
+| **Training Stage** | Stage 2 (instruction tuning) only |
+| **Training Data** | 60K Stage 2 conversations |
+| **Domain** | Transmission Electron Microscopy (TEM) |
+| **Modalities** | CTEM, HR-TEM, STEM, Diffraction |
 
+---
 
+## Inference
 
-This model was trained with SFT.
+ATOMIC-Gemma can be loaded directly via `transformers`:
+
+```python
+from transformers import AutoProcessor, Gemma3ForConditionalGeneration
+from PIL import Image
+import torch
+
+model_id = "LabSmart/ATOMIC-Gemma"
+
+model = Gemma3ForConditionalGeneration.from_pretrained(
+    model_id,
+    device_map="auto",
+    torch_dtype=torch.bfloat16
+).eval()
+processor = AutoProcessor.from_pretrained(model_id)
+
+image = Image.open("your_TEM_image.png").convert("RGB")
+
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {"type": "image", "image": image},
+            {"type": "text", "text": "What type of TEM image is this?"}
+        ]
+    }
+]
+
+inputs = processor.apply_chat_template(
+    messages,
+    add_generation_prompt=True,
+    tokenize=True,
+    return_dict=True,
+    return_tensors="pt"
+).to(model.device, dtype=torch.bfloat16)
+
+input_len = inputs["input_ids"].shape[-1]
+
+with torch.inference_mode():
+    generation = model.generate(**inputs, max_new_tokens=256, do_sample=False)
+
+generation = generation[0][input_len:]
+response = processor.decode(generation, skip_special_tokens=True)
+print(response)
+```
 
-### Framework versions
+---
 
-- TRL: 1.4.0
-- Transformers: 5.9.0
-- Pytorch: 2.12.0.dev20260407+cu128
-- Datasets: 4.8.5
-- Tokenizers: 0.22.2
+## Training Data
 
-## Citations
+Training data is available on HuggingFace:
+👉 [https://huggingface.co/datasets/LabSmart/ATOMIC_dataset](https://huggingface.co/datasets/LabSmart/ATOMIC_dataset)
 
+---
 
+## Citation
 
-Cite TRL as:
-    
 ```bibtex
-@software{vonwerra2020trl,
-  title   = {{TRL: Transformers Reinforcement Learning}},
-  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
-  license = {Apache-2.0},
-  url     = {https://github.com/huggingface/trl},
-  year    = {2020}
+@inproceedings{atomic2026eccv,
+  title     = {ATOMIC: A Domain-Specific Vision-Language Model
+               for Transmission Electron Microscopy},
+  author    = {Tu, C. and Hsu, Shu-han and others},
+  booktitle = {Proceedings of ECCV 2026},
+  year      = {2026},
+  note      = {BibTeX will be updated upon publication}
 }
-```
+```
+
+---
+
+## License
+
+This model is released under the [Gemma Terms of Use](https://ai.google.dev/gemma/terms). It is intended for academic research purposes only.