LocalDoc/colbert-az

L = α × KL(softmax(student_scores) || softmax(teacher_scores)) + (1 − α) × InfoNCE

import torch
import torch.nn as nn
import torch.nn.functional as F
from transformers import AutoTokenizer, AutoModel

class ColBERT(nn.Module):
    def __init__(self, model_name: str, embedding_dim: int = 128):
        super().__init__()
        self.backbone = AutoModel.from_pretrained(model_name)
        self.projection = nn.Linear(self.backbone.config.hidden_size, embedding_dim, bias=False)

    @torch.no_grad()
    def encode(self, input_ids, attention_mask, keep_mask=None):
        out = self.backbone(input_ids=input_ids, attention_mask=attention_mask, return_dict=True)
        emb = self.projection(out.last_hidden_state)
        emb = F.normalize(emb, p=2, dim=-1)
        eff_mask = attention_mask if keep_mask is None else attention_mask * keep_mask
        emb = emb * eff_mask.unsqueeze(-1).float()
        return emb, eff_mask

# Load
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
tokenizer = AutoTokenizer.from_pretrained("LocalDoc/colbert-az")

# Add ColBERT special tokens
tokenizer.add_special_tokens({"additional_special_tokens": ["[Q]", "[D]"]})

model = ColBERT("LocalDoc/colbert-az")
model.backbone.resize_token_embeddings(len(tokenizer))

# Load projection layer
from huggingface_hub import hf_hub_download
proj_path = hf_hub_download(repo_id="LocalDoc/colbert-az", filename="projection.pt")
model.projection.load_state_dict(torch.load(proj_path, map_location="cpu"))

model = model.to(device).eval()

# Tokenization helpers
def tokenize_query(text: str, max_len: int = 32):
    text = f"[Q] {text}"
    enc = tokenizer(text, padding="max_length", truncation=True,
                    max_length=max_len, return_tensors="pt")
    # ColBERT trick: replace pad with mask for query expansion
    pad_mask = enc["input_ids"] == tokenizer.pad_token_id
    enc["input_ids"][pad_mask] = tokenizer.mask_token_id
    enc["attention_mask"] = torch.ones_like(enc["input_ids"])
    return enc

def tokenize_doc(text: str, max_len: int = 256):
    text = f"[D] {text}"
    return tokenizer(text, padding=True, truncation=True,
                     max_length=max_len, return_tensors="pt")

# Compute MaxSim score between query and a single document
def maxsim_score(query: str, document: str) -> float:
    q_enc = {k: v.to(device) for k, v in tokenize_query(query).items()}
    d_enc = {k: v.to(device) for k, v in tokenize_doc(document).items()}

    q_emb, _ = model.encode(q_enc["input_ids"], q_enc["attention_mask"])
    d_emb, d_mask = model.encode(d_enc["input_ids"], d_enc["attention_mask"])

    # MaxSim: for each query token, take max similarity over doc tokens, then sum
    sim = torch.einsum("qld,bnd->qlbn", q_emb, d_emb)
    sim = sim.masked_fill(~d_mask.unsqueeze(0).unsqueeze(0).bool(), float("-inf"))
    max_per_token, _ = sim.max(dim=-1)
    score = max_per_token.sum(dim=1).item()
    return score

# Example
query = "Azərbaycan mədəniyyətinin tarixi"
doc = "Azərbaycan mədəniyyəti zəngin tarixə malikdir və qədim dövrlərdən başlayaraq inkişaf edib."
print(f"Score: {maxsim_score(query, doc):.4f}")

@misc{colbert-az-2026,
  title  = {ColBERT-AZ: Late-Interaction Retrieval for Azerbaijani},
  author = {LocalDoc},
  year   = {2026},
  url    = {https://huggingface.co/LocalDoc/colbert-az}
}