Upload model

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]

config.json

@@ -0,0 +1,14 @@
+{
+  "architectures": [
+    "LeafModel"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_leaf.LeafConfig",
+    "AutoModel": "modeling_leaf.LeafModel"
+  },
+  "model_name": "sentence-transformers/distiluse-base-multilingual-cased-v2",
+  "model_type": "leaf",
+  "num_classes": 2097,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3"
+}

configuration_leaf.py

@@ -0,0 +1,17 @@
+from typing import Literal
+
+from transformers import PretrainedConfig
+
+
+class LeafConfig(PretrainedConfig):
+    model_type = "leaf"
+
+    def __init__(
+            self,
+            num_classes: int = 2097,
+            model_name: str = Literal["BAAI/bge-m3", "sentence-transformers/distiluse-base-multilingual-cased-v2"],
+            **kwargs,
+    ):
+        self.num_classes = num_classes
+        self.model_name = model_name
+        super().__init__(**kwargs)

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96c22f12d5eb2e765ec33a881aa53861cb35689cc43120810250bb7e3f61c91d
+size 545399172

modeling_leaf.py

@@ -0,0 +1,70 @@
+from typing import Optional
+
+import torch
+import torch.nn.functional as F
+from torch import nn
+from transformers import AutoModel
+from transformers import PreTrainedModel
+
+from .configuration_leaf import LeafConfig
+from .mappings import idx_to_ef, idx_to_classname
+
+
+class LeafModel(PreTrainedModel):
+    """
+    LEAF model for text classification.
+    """
+    config_class = LeafConfig
+
+    def __init__(self, config: LeafConfig):
+        super().__init__(config)
+        self._base_model = AutoModel.from_pretrained(config.model_name)
+        self._device = "cuda" if torch.cuda.is_available() else "cpu"
+
+        hidden_dim = self._base_model.config.hidden_size
+        self.head = ClassificationHead(hidden_dim=hidden_dim, num_classes=2097,
+                                       idx_to_ef=idx_to_ef, idx_to_classname=idx_to_classname,
+                                       device=self._device)
+
+    def forward(self, input_ids, attention_mask, **kwargs) -> dict:
+        if "classes" not in kwargs:
+            kwargs["classes"] = None
+        outputs = self._base_model(input_ids=input_ids, attention_mask=attention_mask).last_hidden_state
+        attention_mask = attention_mask.unsqueeze(-1)
+        masked_outputs = outputs * attention_mask.type_as(outputs)
+        nom = masked_outputs.sum(dim=1)
+        denom = attention_mask.sum(dim=1)
+        denom = denom.masked_fill(denom == 0, 1)
+        return self.head(nom / denom, **kwargs)
+
+
+class ClassificationHead(nn.Module):
+    """
+    Model head to predict a categorical target variable.
+    """
+
+    def __init__(self, hidden_dim: int, num_classes: int, idx_to_ef: dict, idx_to_classname: Optional[dict],
+                 device: str):
+        super().__init__()
+        self.linear = nn.Linear(in_features=hidden_dim, out_features=num_classes)
+        self.loss = nn.CrossEntropyLoss()
+
+        # Turn dict into lookup table
+        self.idx_to_ef = torch.Tensor([idx_to_ef[k] for k in sorted(idx_to_ef.keys())]).to(device)
+        self.idx_to_ef.requires_grad = False
+        self.idx_to_classname = idx_to_classname
+
+    def __call__(self, activations: torch.Tensor, classes: Optional[torch.Tensor], **kwargs) -> dict:
+        return_dict = {}
+        logits = self.linear(activations)
+        return_dict["logits"] = logits
+        if classes:
+            loss = self.loss(logits, classes)
+            return_dict["loss"] = loss
+        _, predicted_classes = torch.max(F.softmax(logits, dim=1), dim=1)
+        return_dict["class_idx"] = predicted_classes
+        return_dict["ef_score"] = self.idx_to_ef[predicted_classes]
+        if self.idx_to_classname:
+            return_dict["class"] = [self.idx_to_classname[str(c)] for c in
+                                    predicted_classes.cpu().numpy()]
+        return return_dict