Update README.md

README.md

@@ -12,7 +12,7 @@ pipeline_tag: fill-mask
 [![Data](https://img.shields.io/badge/🤗%20Training%20Data-2T%20Tokens-green)](https://huggingface.co/datasets/jhu-clsp)
 [![GitHub](https://img.shields.io/badge/GitHub-Code-black)](https://github.com/jhu-clsp/ettin-encoder-vs-decoder)
 
-> 🎯 **TL;DR**: State-of-the-art paired encoder and decoder models (17M-1B params) trained identically for fair comparison. First open replication of ModernBERT recipe.
+> 🎯 **TL;DR**: State-of-the-art paired encoder and decoder models (17M-1B params) trained identically for fair comparison. First open replication of ModernBERT recipe. Decoder version beats Llama 3.2.
 
 📄 [Paper (Coming Soon)](https://github.com/jhu-clsp/ettin-encoder-vs-decoder) | 🚀 [GitHub Repository](https://github.com/jhu-clsp/ettin-encoder-vs-decoder)
 
@@ -202,30 +202,9 @@ This checkpoint availability enables detailed analysis of training dynamics, los
 
 ## Usage Examples
 
-### Encoder: Text Classification & Embeddings
-
-```python
-from transformers import AutoTokenizer, AutoModel
-import torch
-
-# Load model and tokenizer
-tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/ettin-encoder-150m")
-model = AutoModel.from_pretrained("jhu-clsp/ettin-encoder-150m")
-
-def get_embeddings(text):
-    inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True)
-    with torch.no_grad():
-        outputs = model(**inputs)
-    # Use [CLS] token representation
-    return outputs.last_hidden_state[:, 0, :]
-
-# Example usage
-text = "This movie is absolutely fantastic!"
-embeddings = get_embeddings(text)
-print(f"Embedding shape: {embeddings.shape}")
-```
-
 ### Encoder: Masked Language Modeling
+<details>
+<summary>Click to expand <strong>encoder</strong> usage examples</summary>
 
 ```python
 from transformers import AutoTokenizer, AutoModelForMaskedLM
@@ -254,8 +233,13 @@ predictions = predict_masked_token(masked_text)
 print(f"Predictions: {predictions}")
 ```
 
+</details>
+
 ### Decoder: Text Generation
 
+<details>
+<summary>Click to expand <strong>decoder text generation</strong></summary>
+  
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
@@ -289,21 +273,8 @@ generated = generate_text(prompt)
 print(generated)
 ```
 
-### Decoder: Few-Shot Learning
+</details>
 
-```python
-# Example: Few-shot sentiment classification
-prompt = '''
-Examples:
-Text: "I love this movie!" Sentiment: Positive
-Text: "This is terrible." Sentiment: Negative
-Text: "It was okay." Sentiment: Neutral
-
-Text: "Absolutely amazing film!" Sentiment:'''
-
-result = generate_text(prompt, max_length=len(tokenizer.encode(prompt)) + 10)
-print(result)
-```
 
 ## 🔬 Research Applications