Fix model correctness and Hugging Face compatibility

README.md

@@ -62,7 +62,6 @@ See the full [UTRBERT collection](https://huggingface.co/collections/Taykhoom/ut
 | **[UTRBERT-5mer](https://huggingface.co/Taykhoom/UTRBERT-5mer)** | 5 | 1029 | |
 | [UTRBERT-6mer](https://huggingface.co/Taykhoom/UTRBERT-6mer) | 6 | 4101 | |
 
-
 ## Usage
 
 ### Embedding generation
@@ -193,8 +192,7 @@ adds selectable `sdpa` and `flash_attention_2` inference backends.
 ## Credits
 
 Original model and code by Yang et al. Source: [GitHub](https://github.com/yangyn533/3UTRBERT).
-The HF conversion code was authored primarily by [Claude Code](https://claude.ai/code)
-and reviewed manually by Taykhoom Dalal.
+Hugging Face port maintained by Taykhoom Dalal.
 
 ## License
 

config.json

@@ -4,9 +4,9 @@
   ],
   "model_type": "bert_updated",
   "auto_map": {
-    "AutoConfig": "Taykhoom/BERT-updated--configuration_bert_updated.BertUpdatedConfig",
-    "AutoModel": "Taykhoom/BERT-updated--modeling_bert.BertModel",
-    "AutoModelForMaskedLM": "Taykhoom/BERT-updated--modeling_bert.BertForMaskedLM"
+    "AutoConfig": "configuration_bert_updated.BertUpdatedConfig",
+    "AutoModel": "modeling_bert.BertModel",
+    "AutoModelForMaskedLM": "modeling_bert.BertForMaskedLM"
   },
   "attention_probs_dropout_prob": 0.1,
   "hidden_act": "gelu",

configuration_bert_updated.py

@@ -0,0 +1,43 @@
+from transformers import PretrainedConfig
+
+
+class BertUpdatedConfig(PretrainedConfig):
+    model_type = "bert_updated"
+
+    auto_map = {
+        "AutoConfig": "configuration_bert_updated.BertUpdatedConfig",
+        "AutoModel": "modeling_bert.BertModel",
+        "AutoModelForMaskedLM": "modeling_bert.BertForMaskedLM",
+    }
+
+    def __init__(
+        self,
+        vocab_size=30522,
+        hidden_size=768,
+        num_hidden_layers=12,
+        num_attention_heads=12,
+        intermediate_size=3072,
+        hidden_act="gelu",
+        mlm_hidden_act=None,
+        hidden_dropout_prob=0.1,
+        attention_probs_dropout_prob=0.1,
+        max_position_embeddings=512,
+        type_vocab_size=2,
+        initializer_range=0.02,
+        layer_norm_eps=1e-12,
+        **kwargs,
+    ):
+        super().__init__(**kwargs)
+        self.vocab_size = vocab_size
+        self.hidden_size = hidden_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+        self.intermediate_size = intermediate_size
+        self.hidden_act = hidden_act
+        self.mlm_hidden_act = mlm_hidden_act
+        self.hidden_dropout_prob = hidden_dropout_prob
+        self.attention_probs_dropout_prob = attention_probs_dropout_prob
+        self.max_position_embeddings = max_position_embeddings
+        self.type_vocab_size = type_vocab_size
+        self.initializer_range = initializer_range
+        self.layer_norm_eps = layer_norm_eps

modeling_bert.py

@@ -0,0 +1,547 @@
+import math
+from typing import Optional, Tuple, Union
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+import torch.utils.checkpoint
+from transformers.activations import ACT2FN
+from transformers import PreTrainedModel, PretrainedConfig
+from transformers.modeling_outputs import BaseModelOutputWithPooling, MaskedLMOutput
+
+from .configuration_bert_updated import BertUpdatedConfig
+
+
+class BertSelfAttention(nn.Module):
+
+    def __init__(self, config):
+        super().__init__()
+        self.num_attention_heads = config.num_attention_heads
+        self.attention_head_size = config.hidden_size // config.num_attention_heads
+        self.all_head_size = self.num_attention_heads * self.attention_head_size
+
+        self.query = nn.Linear(config.hidden_size, self.all_head_size)
+        self.key = nn.Linear(config.hidden_size, self.all_head_size)
+        self.value = nn.Linear(config.hidden_size, self.all_head_size)
+        self.dropout = nn.Dropout(config.attention_probs_dropout_prob)
+
+    def _split_heads(self, x: torch.Tensor) -> torch.Tensor:
+        B, T, _ = x.shape
+        return x.view(B, T, self.num_attention_heads, self.attention_head_size).permute(0, 2, 1, 3)
+
+    def forward(
+        self,
+        hidden_states: torch.Tensor,
+        key_padding_mask: Optional[torch.Tensor] = None,
+        output_attentions: bool = False,
+        head_mask: Optional[torch.Tensor] = None,
+    ) -> Tuple[torch.Tensor, Optional[torch.Tensor]]:
+        q = self._split_heads(self.query(hidden_states))
+        k = self._split_heads(self.key(hidden_states))
+        v = self._split_heads(self.value(hidden_states))
+
+        scale = math.sqrt(self.attention_head_size)
+        scores = torch.matmul(q, k.transpose(-1, -2)) / scale
+        if key_padding_mask is not None:
+            scores = scores.masked_fill(key_padding_mask[:, None, None, :], float("-inf"))
+        probs = torch.nan_to_num(
+            F.softmax(scores.float(), dim=-1),
+            nan=0.0,
+        )
+        context_probs = self.dropout(probs)
+        if head_mask is not None:
+            context_probs = context_probs * head_mask
+        context = torch.matmul(context_probs.to(v.dtype), v)
+
+        B, _, T, _ = context.shape
+        context = context.permute(0, 2, 1, 3).contiguous().view(B, T, self.all_head_size)
+
+        if output_attentions:
+            return context, probs
+        return context, None
+
+
+class BertSdpaSelfAttention(BertSelfAttention):
+
+    def forward(
+        self,
+        hidden_states: torch.Tensor,
+        key_padding_mask: Optional[torch.Tensor] = None,
+        output_attentions: bool = False,
+        head_mask: Optional[torch.Tensor] = None,
+    ) -> Tuple[torch.Tensor, Optional[torch.Tensor]]:
+        if output_attentions or head_mask is not None:
+            return super().forward(
+                hidden_states,
+                key_padding_mask,
+                output_attentions=output_attentions,
+                head_mask=head_mask,
+            )
+
+        B, T, _ = hidden_states.shape
+        q = self._split_heads(self.query(hidden_states))
+        k = self._split_heads(self.key(hidden_states))
+        v = self._split_heads(self.value(hidden_states))
+
+        attn_mask = None
+        if key_padding_mask is not None:
+            attn_mask = torch.zeros(B, 1, 1, T, dtype=q.dtype, device=q.device)
+            attn_mask = attn_mask.masked_fill(key_padding_mask[:, None, None, :], float("-inf"))
+
+        context = F.scaled_dot_product_attention(
+            q,
+            k,
+            v,
+            attn_mask=attn_mask,
+            dropout_p=self.dropout.p if self.training else 0.0,
+        )
+        context = context.permute(0, 2, 1, 3).contiguous().view(B, T, self.all_head_size)
+        return context, None
+
+
+class BertFlashSelfAttention(BertSelfAttention):
+
+    def forward(
+        self,
+        hidden_states: torch.Tensor,
+        key_padding_mask: Optional[torch.Tensor] = None,
+        output_attentions: bool = False,
+        head_mask: Optional[torch.Tensor] = None,
+    ) -> Tuple[torch.Tensor, Optional[torch.Tensor]]:
+        if (
+            output_attentions
+            or head_mask is not None
+            or (
+                key_padding_mask is not None
+                and (~key_padding_mask).sum(dim=-1).eq(0).any()
+            )
+        ):
+            return super().forward(
+                hidden_states,
+                key_padding_mask,
+                output_attentions=output_attentions,
+                head_mask=head_mask,
+            )
+
+        try:
+            from flash_attn import flash_attn_func, flash_attn_varlen_func
+            from flash_attn.bert_padding import pad_input, unpad_input
+        except ImportError as e:
+            raise ImportError(
+                "flash_attn is required for attn_implementation='flash_attention_2'. "
+                "Install with: pip install flash-attn --no-build-isolation"
+            ) from e
+
+        B, T, _ = hidden_states.shape
+        q = self._split_heads(self.query(hidden_states)).permute(0, 2, 1, 3)
+        k = self._split_heads(self.key(hidden_states)).permute(0, 2, 1, 3)
+        v = self._split_heads(self.value(hidden_states)).permute(0, 2, 1, 3)
+
+        if q.dtype not in (torch.float16, torch.bfloat16):
+            raise ValueError(
+                "flash_attention_2 requires float16 or bfloat16 model weights. "
+                f"Received {q.dtype}."
+            )
+
+        if key_padding_mask is not None and key_padding_mask.any():
+            attend = ~key_padding_mask
+            q_u, indices, cu_seqlens, max_seqlen, _ = unpad_input(q, attend)
+            k_u, _, _, _, _ = unpad_input(k, attend)
+            v_u, _, _, _, _ = unpad_input(v, attend)
+            out_u = flash_attn_varlen_func(
+                q_u, k_u, v_u,
+                cu_seqlens_q=cu_seqlens, cu_seqlens_k=cu_seqlens,
+                max_seqlen_q=max_seqlen, max_seqlen_k=max_seqlen,
+                dropout_p=self.dropout.p if self.training else 0.0,
+                causal=False,
+            )
+            out = pad_input(out_u, indices, B, T)
+        else:
+            out = flash_attn_func(
+                q,
+                k,
+                v,
+                dropout_p=self.dropout.p if self.training else 0.0,
+                causal=False,
+            )
+
+        out = out.reshape(B, T, self.all_head_size)
+        return out, None
+
+
+BERT_SELF_ATTENTION_CLASSES = {
+    "eager": BertSelfAttention,
+    "sdpa": BertSdpaSelfAttention,
+    "flash_attention_2": BertFlashSelfAttention,
+}
+
+
+class BertSelfOutput(nn.Module):
+    def __init__(self, config):
+        super().__init__()
+        self.dense = nn.Linear(config.hidden_size, config.hidden_size)
+        self.LayerNorm = nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps)
+        self.dropout = nn.Dropout(config.hidden_dropout_prob)
+
+    def forward(self, hidden_states: torch.Tensor, input_tensor: torch.Tensor) -> torch.Tensor:
+        hidden_states = self.dropout(self.dense(hidden_states))
+        return self.LayerNorm(hidden_states + input_tensor)
+
+
+class BertAttention(nn.Module):
+    def __init__(self, config):
+        super().__init__()
+        attn_cls = BERT_SELF_ATTENTION_CLASSES[getattr(config, "_attn_implementation", "eager")]
+        self.self = attn_cls(config)
+        self.output = BertSelfOutput(config)
+
+    def forward(
+        self,
+        hidden_states: torch.Tensor,
+        key_padding_mask: Optional[torch.Tensor],
+        output_attentions: bool = False,
+        head_mask: Optional[torch.Tensor] = None,
+    ) -> Tuple[torch.Tensor, Optional[torch.Tensor]]:
+        self_out, attn_weights = self.self(
+            hidden_states,
+            key_padding_mask,
+            output_attentions,
+            head_mask,
+        )
+        return self.output(self_out, hidden_states), attn_weights
+
+
+class BertIntermediate(nn.Module):
+    def __init__(self, config):
+        super().__init__()
+        self.dense = nn.Linear(config.hidden_size, config.intermediate_size)
+        if config.hidden_act in (None, "identity", "linear"):
+            self.intermediate_act_fn = lambda value: value
+        elif isinstance(config.hidden_act, str):
+            self.intermediate_act_fn = ACT2FN[config.hidden_act]
+        else:
+            self.intermediate_act_fn = config.hidden_act
+
+    def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
+        return self.intermediate_act_fn(self.dense(hidden_states))
+
+
+class BertOutput(nn.Module):
+    def __init__(self, config):
+        super().__init__()
+        self.dense = nn.Linear(config.intermediate_size, config.hidden_size)
+        self.LayerNorm = nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps)
+        self.dropout = nn.Dropout(config.hidden_dropout_prob)
+
+    def forward(self, hidden_states: torch.Tensor, input_tensor: torch.Tensor) -> torch.Tensor:
+        hidden_states = self.dropout(self.dense(hidden_states))
+        return self.LayerNorm(hidden_states + input_tensor)
+
+
+class BertLayer(nn.Module):
+    def __init__(self, config):
+        super().__init__()
+        self.attention = BertAttention(config)
+        self.intermediate = BertIntermediate(config)
+        self.output = BertOutput(config)
+
+    def forward(
+        self,
+        hidden_states: torch.Tensor,
+        key_padding_mask: Optional[torch.Tensor],
+        output_attentions: bool = False,
+        head_mask: Optional[torch.Tensor] = None,
+    ) -> Tuple[torch.Tensor, Optional[torch.Tensor]]:
+        attn_out, attn_weights = self.attention(
+            hidden_states,
+            key_padding_mask,
+            output_attentions,
+            head_mask,
+        )
+        return self.output(self.intermediate(attn_out), attn_out), attn_weights
+
+
+class BertEncoder(nn.Module):
+    def __init__(self, config):
+        super().__init__()
+        self.layer = nn.ModuleList([BertLayer(config) for _ in range(config.num_hidden_layers)])
+        self.gradient_checkpointing = False
+
+    def forward(
+        self,
+        hidden_states: torch.Tensor,
+        key_padding_mask: Optional[torch.Tensor],
+        output_hidden_states: bool = False,
+        output_attentions: bool = False,
+        head_mask: Optional[torch.Tensor] = None,
+    ) -> Tuple:
+        all_hidden_states = (hidden_states,) if output_hidden_states else None
+        all_attentions = () if output_attentions else None
+
+        for layer_index, layer in enumerate(self.layer):
+            layer_head_mask = (
+                head_mask[layer_index] if head_mask is not None else None
+            )
+            if self.gradient_checkpointing and self.training:
+                hidden_states, attn_weights = torch.utils.checkpoint.checkpoint(
+                    layer.__call__,
+                    hidden_states,
+                    key_padding_mask,
+                    output_attentions,
+                    layer_head_mask,
+                    use_reentrant=False,
+                )
+            else:
+                hidden_states, attn_weights = layer(
+                    hidden_states,
+                    key_padding_mask,
+                    output_attentions,
+                    layer_head_mask,
+                )
+            if output_hidden_states:
+                all_hidden_states = all_hidden_states + (hidden_states,)
+            if output_attentions:
+                all_attentions = all_attentions + (attn_weights,)
+
+        return hidden_states, all_hidden_states, all_attentions
+
+
+class BertEmbeddings(nn.Module):
+    def __init__(self, config):
+        super().__init__()
+        self.word_embeddings = nn.Embedding(config.vocab_size, config.hidden_size, padding_idx=config.pad_token_id)
+        self.position_embeddings = nn.Embedding(config.max_position_embeddings, config.hidden_size)
+        self.token_type_embeddings = nn.Embedding(config.type_vocab_size, config.hidden_size)
+        self.LayerNorm = nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps)
+        self.dropout = nn.Dropout(config.hidden_dropout_prob)
+        self.register_buffer("position_ids", torch.arange(config.max_position_embeddings).expand((1, -1)), persistent=False)
+
+    def forward(
+        self,
+        input_ids: Optional[torch.LongTensor] = None,
+        token_type_ids: Optional[torch.LongTensor] = None,
+        position_ids: Optional[torch.LongTensor] = None,
+        inputs_embeds: Optional[torch.FloatTensor] = None,
+    ) -> torch.Tensor:
+        if (input_ids is None) == (inputs_embeds is None):
+            raise ValueError("Specify exactly one of input_ids or inputs_embeds.")
+        B, T = (
+            input_ids.shape
+            if input_ids is not None
+            else inputs_embeds.shape[:2]
+        )
+        if token_type_ids is None:
+            token_type_ids = torch.zeros(
+                (B, T),
+                dtype=torch.long,
+                device=(
+                    input_ids.device
+                    if input_ids is not None
+                    else inputs_embeds.device
+                ),
+            )
+        if position_ids is None:
+            position_ids = self.position_ids[:, :T]
+        x = (
+            self.word_embeddings(input_ids)
+            if inputs_embeds is None
+            else inputs_embeds
+        )
+        x = x + self.token_type_embeddings(token_type_ids)
+        x = x + self.position_embeddings(position_ids)
+        return self.dropout(self.LayerNorm(x))
+
+
+class BertPooler(nn.Module):
+    def __init__(self, config):
+        super().__init__()
+        self.dense = nn.Linear(config.hidden_size, config.hidden_size)
+        self.activation = nn.Tanh()
+
+    def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
+        return self.activation(self.dense(hidden_states[:, 0]))
+
+
+class BertPredictionHeadTransform(nn.Module):
+    def __init__(self, config):
+        super().__init__()
+        self.dense = nn.Linear(config.hidden_size, config.hidden_size)
+        self.LayerNorm = nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps)
+        hidden_act = (
+            config.mlm_hidden_act
+            if getattr(config, "mlm_hidden_act", None) is not None
+            else config.hidden_act
+        )
+        if hidden_act in (None, "identity", "linear"):
+            self.transform_act_fn = lambda value: value
+        elif isinstance(hidden_act, str):
+            self.transform_act_fn = ACT2FN[hidden_act]
+        else:
+            self.transform_act_fn = hidden_act
+
+    def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
+        return self.LayerNorm(self.transform_act_fn(self.dense(hidden_states)))
+
+
+class BertModel(PreTrainedModel):
+    config_class = BertUpdatedConfig
+    base_model_prefix = "bert"
+    _supports_sdpa = True
+    _supports_flash_attn_2 = True
+    supports_gradient_checkpointing = True
+    _keys_to_ignore_on_load_missing = [r"pooler\."]
+
+    def __init__(self, config, add_pooling_layer=True):
+        super().__init__(config)
+        self.embeddings = BertEmbeddings(config)
+        self.encoder = BertEncoder(config)
+        self.pooler = BertPooler(config) if add_pooling_layer else None
+        self.post_init()
+
+    def get_input_embeddings(self):
+        return self.embeddings.word_embeddings
+
+    def set_input_embeddings(self, value):
+        self.embeddings.word_embeddings = value
+
+    def forward(
+        self,
+        input_ids: Optional[torch.LongTensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        token_type_ids: Optional[torch.LongTensor] = None,
+        position_ids: Optional[torch.LongTensor] = None,
+        head_mask: Optional[torch.Tensor] = None,
+        inputs_embeds: Optional[torch.FloatTensor] = None,
+        output_hidden_states: Optional[bool] = None,
+        output_attentions: Optional[bool] = None,
+        return_dict: Optional[bool] = None,
+    ) -> Union[Tuple, BaseModelOutputWithPooling]:
+        output_hidden_states = output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
+        output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
+        return_dict = return_dict if return_dict is not None else self.config.use_return_dict
+
+        if (input_ids is None) == (inputs_embeds is None):
+            raise ValueError("Specify exactly one of input_ids or inputs_embeds.")
+        input_shape = (
+            input_ids.shape
+            if input_ids is not None
+            else inputs_embeds.shape[:2]
+        )
+        input_device = (
+            input_ids.device
+            if input_ids is not None
+            else inputs_embeds.device
+        )
+        if attention_mask is None:
+            attention_mask = torch.ones(input_shape, device=input_device)
+        key_padding_mask = attention_mask.eq(0)
+        if not key_padding_mask.any():
+            key_padding_mask = None
+        head_mask = self.get_head_mask(
+            head_mask,
+            self.config.num_hidden_layers,
+        )
+        if all(mask is None for mask in head_mask):
+            head_mask = None
+
+        x = self.embeddings(
+            input_ids=input_ids,
+            token_type_ids=token_type_ids,
+            position_ids=position_ids,
+            inputs_embeds=inputs_embeds,
+        )
+        last_hidden_state, all_hidden_states, all_attentions = self.encoder(
+            x, key_padding_mask,
+            output_hidden_states=output_hidden_states,
+            output_attentions=output_attentions,
+            head_mask=head_mask,
+        )
+        pooled = self.pooler(last_hidden_state) if self.pooler is not None else None
+
+        if not return_dict:
+            output = (last_hidden_state, pooled)
+            if output_hidden_states:
+                output += (all_hidden_states,)
+            if output_attentions:
+                output += (all_attentions,)
+            return output
+
+        return BaseModelOutputWithPooling(
+            last_hidden_state=last_hidden_state,
+            pooler_output=pooled,
+            hidden_states=all_hidden_states,
+            attentions=all_attentions,
+        )
+
+
+class BertForMaskedLM(PreTrainedModel):
+    config_class = BertUpdatedConfig
+    base_model_prefix = "bert"
+    _supports_sdpa = True
+    _supports_flash_attn_2 = True
+    supports_gradient_checkpointing = True
+    _keys_to_ignore_on_load_unexpected = [r"bert\.pooler\."]
+
+    def __init__(self, config):
+        super().__init__(config)
+        self.bert = BertModel(config, add_pooling_layer=False)
+        self.transform = BertPredictionHeadTransform(config)
+        self.cls = nn.Linear(config.hidden_size, config.vocab_size)
+        self.post_init()
+
+    def get_input_embeddings(self):
+        return self.bert.embeddings.word_embeddings
+
+    def set_input_embeddings(self, value):
+        self.bert.embeddings.word_embeddings = value
+
+    def get_output_embeddings(self):
+        return self.cls
+
+    def set_output_embeddings(self, value):
+        self.cls = value
+
+    def forward(
+        self,
+        input_ids: Optional[torch.LongTensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        token_type_ids: Optional[torch.LongTensor] = None,
+        position_ids: Optional[torch.LongTensor] = None,
+        head_mask: Optional[torch.Tensor] = None,
+        inputs_embeds: Optional[torch.FloatTensor] = None,
+        labels: Optional[torch.LongTensor] = None,
+        output_hidden_states: Optional[bool] = None,
+        output_attentions: Optional[bool] = None,
+        return_dict: Optional[bool] = None,
+    ) -> Union[Tuple, MaskedLMOutput]:
+        return_dict = return_dict if return_dict is not None else self.config.use_return_dict
+
+        outputs = self.bert(
+            input_ids=input_ids,
+            attention_mask=attention_mask,
+            token_type_ids=token_type_ids,
+            position_ids=position_ids,
+            head_mask=head_mask,
+            inputs_embeds=inputs_embeds,
+            output_hidden_states=output_hidden_states,
+            output_attentions=output_attentions,
+            return_dict=True,
+        )
+        logits = self.cls(self.transform(outputs.last_hidden_state))
+
+        loss = None
+        if labels is not None:
+            loss = F.cross_entropy(logits.view(-1, self.config.vocab_size), labels.view(-1), ignore_index=-100)
+
+        if not return_dict:
+            output = (logits,)
+            if output_hidden_states:
+                output += (outputs.hidden_states,)
+            if output_attentions:
+                output += (outputs.attentions,)
+            return (loss,) + output if loss is not None else output
+
+        return MaskedLMOutput(
+            loss=loss, logits=logits,
+            hidden_states=outputs.hidden_states, attentions=outputs.attentions,
+        )