Upload DisamBertSingleSense

DisamBertSingleSense.py

@@ -0,0 +1,134 @@
+from collections.abc import Generator, Iterable
+from dataclasses import dataclass
+from enum import StrEnum
+
+import numpy as np
+import pandas as pd
+import torch
+import torch.nn as nn
+from transformers import (
+    AutoConfig,
+    AutoModel,
+    ModernBertModel,
+    PreTrainedConfig,
+    PreTrainedModel,
+    PreTrainedTokenizer,
+)
+from transformers.modeling_outputs import TokenClassifierOutput
+
+BATCH_SIZE = 16
+
+
+class ModelURI(StrEnum):
+    BASE = "answerdotai/ModernBERT-base"
+    LARGE = "answerdotai/ModernBERT-large"
+
+
+@dataclass(slots=True, frozen=True)
+class LexicalExample:
+    concept: str
+    definition: str
+
+
+@dataclass(slots=True, frozen=True)
+class PaddedBatch:
+    input_ids: torch.Tensor
+    attention_mask: torch.Tensor
+
+
+class DisamBertSingleSense(PreTrainedModel):
+    def __init__(self, config: PreTrainedConfig):
+        super().__init__(config)
+        if config.init_basemodel:
+            self.BaseModel = AutoModel.from_pretrained(config.name_or_path, device_map="auto")
+            self.config.vocab_size += 2
+            self.BaseModel.resize_token_embeddings(self.config.vocab_size)
+            self.classifier_head = nn.UninitializedParameter()
+            self.bias = nn.UninitializedParameter()
+            self.__entities = None
+        else:
+            self.BaseModel = ModernBertModel(config)
+            self.classifier_head = nn.Parameter(
+                torch.empty((config.ontology_size, config.hidden_size))
+            )
+            self.bias = nn.Parameter(torch.empty((1,config.ontology_size)))
+            self.__entities = pd.Series(config.entities)
+        config.init_basemodel = False
+
+        self.loss = nn.CrossEntropyLoss()
+        self.post_init()
+
+    @classmethod
+    def from_base(cls, base_id: ModelURI):
+        config = AutoConfig.from_pretrained(base_id)
+        config.init_basemodel = True
+        return cls(config)
+
+    def init_classifier(
+        self, entities: Generator[LexicalExample], tokenizer: PreTrainedTokenizer
+    ) -> None:
+        entity_ids = []
+        vectors = []
+        batch = []
+        n = 0
+        with self.BaseModel.device:
+            torch.cuda.empty_cache()
+            for entity in entities:
+                entity_ids.append(entity.concept)
+                batch.append(entity.definition)
+
+                n += 1
+                if n == BATCH_SIZE:
+                    tokens = tokenizer(batch, padding=True, return_tensors="pt")
+                    encoding = self.BaseModel(tokens["input_ids"], tokens["attention_mask"])
+                    vectors.append(encoding.last_hidden_state.detach()[:, 0])
+                    n = 0
+                    batch = []
+            if n > 0:
+                tokens = tokenizer(batch, padding=True, return_tensors="pt")
+                encoding = self.BaseModel(tokens["input_ids"], tokens["attention_mask"])
+                vectors.append(encoding.last_hidden_state.detach()[:, 0])
+
+            self.__entities = pd.Series(entity_ids)
+            self.config.entities = entity_ids
+            self.config.ontology_size = len(entity_ids)
+            self.classifier_head = nn.Parameter(torch.cat(vectors, dim=0))
+            self.bias = nn.Parameter(
+                torch.nn.init.normal_(
+                    torch.empty((1,self.config.ontology_size)),
+                    std=self.classifier_head.std().item() * np.sqrt(self.config.hidden_size),
+                )
+            )
+
+    @property
+    def entities(self) -> pd.Series:
+        if self.__entities is None and hasattr(self.config, "entities"):
+            self.__entities = pd.Series(self.config.entities)
+        return self.__entities
+
+    def forward(
+        self,
+        input_ids: torch.Tensor,
+        attention_mask: torch.Tensor,
+        labels: Iterable[int] | None = None,
+        output_hidden_states: bool = False,
+        output_attentions: bool = False,
+    ) -> TokenClassifierOutput:
+        assert not nn.parameter.is_lazy(self.classifier_head), (
+            "Run init_classifier to initialise weights"
+        )
+        base_model_output = self.BaseModel(
+            input_ids,
+            attention_mask,
+            output_hidden_states=output_hidden_states,
+            output_attentions=output_attentions,
+        )
+        token_vectors = base_model_output.last_hidden_state[:, 0]
+        logits = torch.einsum("ij,kj->ik", token_vectors, self.classifier_head) + self.bias
+
+        return TokenClassifierOutput(
+            logits=logits,
+            loss=self.loss(logits, labels) if labels is not None else None,
+            hidden_states=base_model_output.hidden_states if output_hidden_states else None,
+            attentions=base_model_output.attentions if output_attentions else None,
+        )

README.md

@@ -0,0 +1,199 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd52b8610f651671c24de12bd3ddca728e2a1e2c2d84c83e1801b68e3153e499
+size 957996876