Add AMD MI300X GPU reference

README.md

@@ -12,6 +12,7 @@ tags:
 - text-classification
 - modernbert
 - multilingual
+- amd-mi300x
 base_model: jhu-clsp/mmBERT-base
 datasets:
 - llm-semantic-router/feedback-detector-dataset
@@ -39,7 +40,7 @@ model-index:
 
 # mmBERT Feedback Detector
 
-A high-performance multilingual 4-class feedback classification model fine-tuned on [mmBERT-base](https://huggingface.co/jhu-clsp/mmBERT-base).
+A high-performance multilingual 4-class feedback classification model fine-tuned on [mmBERT-base](https://huggingface.co/jhu-clsp/mmBERT-base) using **AMD MI300X GPU**.
 
 ## Model Description
 
@@ -65,7 +66,7 @@ This model classifies user feedback into 4 categories:
 - **Dataset**: [llm-semantic-router/feedback-detector-dataset](https://huggingface.co/datasets/llm-semantic-router/feedback-detector-dataset)
 - **Size**: 51,694 examples (46,524 train / 5,170 validation)
 - **Languages**: English, Japanese, Turkish
-- **Labeling**: GPT-OSS-120B via vLLM
+- **Labeling**: GPT-OSS-120B via vLLM on AMD MI300X
 - **Sources**: MultiWOZ, SGD, INSCIT, MIMICS, Hazumi, Consumer Complaints
 
 ## Training Configuration
@@ -78,7 +79,15 @@ This model classifies user feedback into 4 categories:
 | Learning Rate | 2e-5 |
 | Max Length | 512 |
 | Optimizer | AdamW |
-| Hardware | AMD MI300X (ROCm) |
+
+### Hardware
+
+| Component | Specification |
+|-----------|---------------|
+| **GPU** | AMD Instinct MI300X |
+| **VRAM** | 192 GB HBM3 |
+| **Framework** | PyTorch with ROCm |
+| **Training Time** | ~2 minutes |
 
 ## Usage