Upload GPT2ForSequenceClassification

README.md

@@ -1,74 +1,42 @@
 ---
-license: mit
-base_model: openai-community/gpt2-large
 tags:
-- generated_from_trainer
+- adapter-transformers
+- gpt2
 datasets:
-- stanfordnlp/snli
-metrics:
-- accuracy
-model-index:
-- name: gpt2-large-bn-adapter-7.42M-snli-model2
-  results:
-  - task:
-      name: Text Classification
-      type: text-classification
-    dataset:
-      name: snli
-      type: stanfordnlp/snli
-    metrics:
-    - name: Accuracy
-      type: accuracy
-      value: 0.8996138996138996
+- snli
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
+# Adapter `varun-v-rao/gpt2-large-bn-adapter-7.42M-snli-model2` for openai-community/gpt2-large
 
-# gpt2-large-bn-adapter-7.42M-snli-model2
+An [adapter](https://adapterhub.ml) for the `openai-community/gpt2-large` model that was trained on the [snli](https://huggingface.co/datasets/snli/) dataset.
 
-This model is a fine-tuned version of [openai-community/gpt2-large](https://huggingface.co/openai-community/gpt2-large) on the snli dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.2746
-- Accuracy: 0.8996
+This adapter was created for usage with the **[Adapters](https://github.com/Adapter-Hub/adapters)** library.
 
-## Model description
+## Usage
 
-More information needed
+First, install `adapters`:
 
-## Intended uses & limitations
+```
+pip install -U adapters
+```
 
-More information needed
+Now, the adapter can be loaded and activated like this:
 
-## Training and evaluation data
+```python
+from adapters import AutoAdapterModel
 
-More information needed
+model = AutoAdapterModel.from_pretrained("openai-community/gpt2-large")
+adapter_name = model.load_adapter("varun-v-rao/gpt2-large-bn-adapter-7.42M-snli-model2", source="hf", set_active=True)
+```
 
-## Training procedure
+## Architecture & Training
 
-### Training hyperparameters
+<!-- Add some description here -->
 
-The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 32
-- eval_batch_size: 32
-- seed: 8
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- num_epochs: 3
+## Evaluation results
 
-### Training results
+<!-- Add some description here -->
 
-| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
-|:-------------:|:-----:|:-----:|:---------------:|:--------:|
-| 0.3612        | 1.0   | 17168 | 0.2979          | 0.8883   |
-| 0.3305        | 2.0   | 34336 | 0.2790          | 0.8971   |
-| 0.3089        | 3.0   | 51504 | 0.2746          | 0.8996   |
+## Citation
 
-
-### Framework versions
-
-- Transformers 4.35.2
-- Pytorch 2.1.1+cu121
-- Datasets 2.15.0
-- Tokenizers 0.15.0
+<!-- Add some description here -->

pytorch_adapter.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08023fa652d647c217646c583c93657bc7a9dd56241f92bfffa9c139ac587f03
+oid sha256:feb0594539dd83bd1053c797649e34345358178402727468489c3c49859e4381
 size 29739378

pytorch_model_head.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bc126484bd566e5083b7b3cbcc6ab37250d0d2c29000dc962da3e05d907b99e
+oid sha256:83ae65accbd77489310754f56d891179fac9cd0a0986fbae4ad30d35c84b5bf2
 size 16659