Add fine-tuned weights

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 +1,28 @@
+{
+  "_name_or_path": "/mnt/batch/tasks/shared/LS_root/mounts/clusters/test5/code/Users/filip.trhlik/Fairness-NC-main/ase/model_save/babylm_debiased_augmented_final",
+  "architectures": [
+    "LtgBertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "auto_map": {
+    "AutoConfig": "configuration_ltgbert.LtgBertConfig",
+    "AutoModelForMaskedLM": "ltg/ltg-bert-babylm--modeling_ltgbert.LtgBertForMaskedLM",
+    "AutoModelForSequenceClassification": "ltg/ltg-bert-babylm--modeling_ltgbert.LtgBertForSequenceClassification"
+  },
+  "classifier_dropout": 0.2,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "intermediate_size": 2048,
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "model_type": "ltgbert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_all_encoded_layers": true,
+  "output_hidden_states": true,
+  "pad_token_id": 4,
+  "position_bucket_size": 32,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0",
+  "vocab_size": 16384
+}

configuration_ltgbert.py

@@ -0,0 +1,107 @@
+# coding=utf-8
+# Copyright 2023 Language Technology Group from University of Oslo and The HuggingFace Inc. team.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+""" LTG-BERT configutation """
+
+
+from transformers.configuration_utils import PretrainedConfig
+
+
+LTG_BERT_PRETRAINED_CONFIG_ARCHIVE_MAP = {
+    "bnc-bert-span": "https://huggingface.co/ltg/bnc-bert-span",
+    "bnc-bert-span-2x": "https://huggingface.co/ltg/bnc-bert-span-2x",
+    "bnc-bert-span-0.5x": "https://huggingface.co/ltg/bnc-bert-span-0.5x",
+    "bnc-bert-span-0.25x": "https://huggingface.co/ltg/bnc-bert-span-0.25x",
+    "bnc-bert-span-order": "https://huggingface.co/ltg/bnc-bert-span-order",
+    "bnc-bert-span-document": "https://huggingface.co/ltg/bnc-bert-span-document",
+    "bnc-bert-span-word": "https://huggingface.co/ltg/bnc-bert-span-word",
+    "bnc-bert-span-subword": "https://huggingface.co/ltg/bnc-bert-span-subword",
+
+    "norbert3-xs": "https://huggingface.co/ltg/norbert3-xs/config.json",
+    "norbert3-small": "https://huggingface.co/ltg/norbert3-small/config.json",
+    "norbert3-base": "https://huggingface.co/ltg/norbert3-base/config.json",
+    "norbert3-large": "https://huggingface.co/ltg/norbert3-large/config.json",
+
+    "norbert3-oversampled-base": "https://huggingface.co/ltg/norbert3-oversampled-base/config.json",
+    "norbert3-ncc-base": "https://huggingface.co/ltg/norbert3-ncc-base/config.json",
+    "norbert3-nak-base": "https://huggingface.co/ltg/norbert3-nak-base/config.json",
+    "norbert3-nb-base": "https://huggingface.co/ltg/norbert3-nb-base/config.json",
+    "norbert3-wiki-base": "https://huggingface.co/ltg/norbert3-wiki-base/config.json",
+    "norbert3-c4-base": "https://huggingface.co/ltg/norbert3-c4-base/config.json"
+}
+
+
+class LtgBertConfig(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`LtgBertModel`]. It is used to
+    instantiate an LTG-BERT model according to the specified arguments, defining the model architecture.
+    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
+    documentation from [`PretrainedConfig`] for more information.
+    Args:
+        vocab_size (`int`, *optional*, defaults to 16384):
+            Vocabulary size of the LTG-BERT model. Defines the number of different tokens that can be represented by the
+            `inputs_ids` passed when calling [`LtgBertModel`].
+        hidden_size (`int`, *optional*, defaults to 768):
+            Dimensionality of the encoder layers and the pooler layer.
+        num_hidden_layers (`int`, *optional*, defaults to 12):
+            Number of hidden layers in the Transformer encoder.
+        num_attention_heads (`int`, *optional*, defaults to 12):
+            Number of attention heads for each attention layer in the Transformer encoder.
+        intermediate_size (`int`, *optional*, defaults to 2048):
+            Dimensionality of the "intermediate" (often named feed-forward) layer in the Transformer encoder.
+        hidden_dropout_prob (`float`, *optional*, defaults to 0.1):
+            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
+        attention_probs_dropout_prob (`float`, *optional*, defaults to 0.1):
+            The dropout ratio for the attention probabilities.
+        max_position_embeddings (`int`, *optional*, defaults to 512):
+            The maximum sequence length that this model might ever be used with. Typically set this to something large
+            just in case (e.g., 512 or 1024 or 2048).
+        layer_norm_eps (`float`, *optional*, defaults to 1e-12):
+            The epsilon used by the layer normalization layers.
+        classifier_dropout (`float`, *optional*):
+            The dropout ratio for the classification head.
+    """
+    model_type = "ltgbert"
+    def __init__(
+        self,
+        vocab_size=16384,
+        attention_probs_dropout_prob=0.1,
+        hidden_dropout_prob=0.1,
+        hidden_size=768,
+        intermediate_size=2048,
+        max_position_embeddings=512,
+        position_bucket_size=32,
+        num_attention_heads=12,
+        num_hidden_layers=12,
+        layer_norm_eps=1.0e-7,
+        pad_token_id=4,
+        output_all_encoded_layers=True,
+        classifier_dropout=None,
+        **kwargs,
+    ):
+        super().__init__(pad_token_id=pad_token_id, **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_dropout_prob = hidden_dropout_prob
+        self.attention_probs_dropout_prob = attention_probs_dropout_prob
+        self.max_position_embeddings = max_position_embeddings
+        self.output_all_encoded_layers = output_all_encoded_layers
+        self.position_bucket_size = position_bucket_size
+        self.layer_norm_eps = layer_norm_eps
+        self.classifier_dropout = classifier_dropout

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9dac29cf79580d88c17827a7fcad2dda13cdcf0348318f3406b4d6f471e5286
+size 443265688