Add README

README.md

@@ -1,3 +1,66 @@
 ---
 license: gpl-3.0
 ---
+
+## Using CrossDNA 8.1M
+```python
+import os
+os.environ.setdefault("DISABLE_TORCH_COMPILE", "1")  
+
+import torch
+if hasattr(torch, "compile"):
+    def _no_compile(fn=None, *args, **kwargs):
+        if fn is None:
+            def deco(f): return f
+            return deco
+        return fn
+    torch.compile = _no_compile
+
+import torch
+from transformers import AutoTokenizer, AutoModelForMaskedLM
+
+# Hugging Face Remote Repository Example
+# repo_id = "chengCCC/CrossDNA_pretrain"
+# subdir = "8.1M"
+
+# tok = AutoTokenizer.from_pretrained(repo_id, subfolder=subdir, trust_remote_code=True, local_files_only=True)
+# model = AutoModelForMaskedLM.from_pretrained(repo_id, subfolder=subdir, trust_remote_code=True, local_files_only=True).eval()
+
+# Local Model Example
+MODEL_DIR = "/data/zhaol/projects/huggingface_crossdna/crossdna"
+tok = AutoTokenizer.from_pretrained(MODEL_DIR, trust_remote_code=True, local_files_only=True)
+model = AutoModelForMaskedLM.from_pretrained(MODEL_DIR, trust_remote_code=True, local_files_only=True).eval()
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model.to(device)
+
+# 512bp DNA sequence
+seq = "ACGT" * 128
+
+
+enc = tok(seq, return_tensors="pt", add_special_tokens=False)
+
+
+x = enc["input_ids"].to(device)  # [1, L]
+
+# Key: map tokenizer IDs back to the model-required range [0..4]
+#   A, C, G, T, N: 7..11 -> 0..4
+#   All other tokens (UNK/PAD/SEP/CLS/...) are treated as N (=4)
+x = torch.where(x >= 7, x - 7, torch.full_like(x, 4))
+
+# ======  embedding ======
+was_pretrain = getattr(model.backbone, "pretrain", False)
+was_for_repr = getattr(model.backbone, "for_representation", False)
+model.backbone.pretrain = False
+model.backbone.for_representation = True
+
+with torch.inference_mode():
+    embeddings, _ = model.backbone(x)   # [B, L, H]
+
+print("input_ids.shape =", tuple(x.shape)) # input_ids.shape = (1, 512)
+print("embeddings.shape =", tuple(embeddings.shape)) # embeddings.shape = (1, 512, 128)
+
+model.backbone.pretrain = was_pretrain
+model.backbone.for_representation = was_for_repr
+
+```