Update README.md

README.md

@@ -133,6 +133,41 @@ def score(seq: str) -> float:
     targets = ids[:, 1:]
     logp = F.log_softmax(logits.float(), dim=-1).gather(-1, targets.unsqueeze(-1)).squeeze(-1)
     return logp.mean().item()
+
+# QY: not sure if we still want to keep this per-token log-probabilities score function,
+# because we now have a more elegant one in modeling_carbon.py:
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+repo = "HuggingFaceBio/Carbon-3B"
+
+# Load tokenizer and model
+tok = AutoTokenizer.from_pretrained(repo, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+    repo,
+    torch_dtype=torch.bfloat16,
+    trust_remote_code=True
+).cuda().eval()
+
+# Setup tokenizer for bp-level scoring (required for score_sequence)
+model.setup_tokenizer(tok)
+
+# Score sequences - automatically handles BOS token and padding
+sequences = ["ATCG" * 1024, "ACAT" * 2048]
+bp_probs_list, actual_probs_list = model.score_sequence(sequences)
+
+# bp_probs_list: list of [seq_len_i, 4] tensors - probability distribution over A/T/C/G at each position
+# actual_probs_list: list of [seq_len_i] tensors - probability of the actual base at each position
+
+# Compute metrics for each sequence
+for i, (seq, actual_probs) in enumerate(zip(sequences, actual_probs_list)):
+    log_likelihood = actual_probs.log().sum().item()  # Total log-likelihood
+    perplexity = torch.exp(-actual_probs.log().mean()).item()  # Perplexity
+
+    print(f"Sequence {i+1} (length {len(seq)}):")
+    print(f"  Log-likelihood: {log_likelihood:.2f}")
+    print(f"  Perplexity: {perplexity:.4f}")
+    print(f"  Mean probability: {actual_probs.mean().item():.4f}")
 ```
 
 For batched scoring with attention masking and full reproducible evaluation pipelines (sequence recovery, ClinVar / BRCA2 / TraitGym VEP, TATA / synonymous-codon perturbation, Genome-NIAH), use the official scripts in the [Carbon evaluation directory](https://github.com/huggingface/carbon/tree/main/evaluation) — see [`perturbation_tasks.py`](https://github.com/huggingface/carbon/blob/main/evaluation/perturbation_tasks.py) for the canonical `score_hf` implementation and [`README.md`](https://github.com/huggingface/carbon/blob/main/evaluation/README.md) for run instructions across all tasks.