Add library requirements, tokenizer loading notes, and UNEXPECTED key explanation

README.md

@@ -42,8 +42,30 @@ Fine-tuned from [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai
 ## 🚀 Quick Start
 
 ```bash
-pip install transformers peft torch
+pip install "transformers>=4.48" "peft>=0.14" "huggingface_hub>=0.27" torch
 ```
+> **Important:** ModernBERT requires `transformers >= 4.48`. Older versions will fail with `KeyError: 'modernbert'`.
+
+### Requirements
+
+| Library | Minimum Version | Notes |
+|---------|----------------|-------|
+| `transformers` | **>= 4.48** | ModernBERT architecture support |
+| `peft` | **>= 0.14** | Compatible `hf_hub_download` API |
+| `huggingface_hub` | **>= 0.27** | No deprecated `use_auth_token` |
+| `torch` | **>= 2.0** | CUDA support |
+
+```bash
+pip install "transformers>=4.48" "peft>=0.14" "huggingface_hub>=0.27" torch
+```
+
+### Loading Notes
+
+**Tokenizer:** Load from the *base model* (`answerdotai/ModernBERT-base`), NOT from this adapter repo. The adapter repo stores LoRA weights only; the tokenizer lives with the base model.
+
+**UNEXPECTED keys on load:** When loading `AutoModel.from_pretrained("answerdotai/ModernBERT-base")`, you may see warnings about UNEXPECTED keys (`head.norm.weight`, `head.dense.weight`, `decoder.bias`). These are the base model's **MLM (masked language model) head weights** that exist in the pretrained checkpoint but are not used by `AutoModel` (which loads only the encoder backbone). This is **completely normal** and safe to ignore.
+
+
 
 ```python
 from transformers import AutoModel, AutoTokenizer
@@ -61,6 +83,7 @@ model = PeftModel.from_pretrained(
 )
 model.eval()
 
+# IMPORTANT: Load tokenizer from BASE MODEL, not from adapter repo
 tokenizer = AutoTokenizer.from_pretrained(
     "answerdotai/ModernBERT-base",
     trust_remote_code=True