Upload TFGPT2ForSequenceClassification

README.md

@@ -0,0 +1,55 @@
+---
+base_model: raygx/Nepali-DistilGPT2
+tags:
+- generated_from_keras_callback
+model-index:
+- name: distilGPT-NepSA
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information Keras had access to. You should
+probably proofread and complete it, then remove this comment. -->
+
+# distilGPT-NepSA
+
+This model is a fine-tuned version of [raygx/Nepali-DistilGPT2](https://huggingface.co/raygx/Nepali-DistilGPT2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 0.6059
+- Validation Loss: 0.6725
+- Epoch: 2
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.001}
+- training_precision: float32
+
+### Training results
+
+| Train Loss | Validation Loss | Epoch |
+|:----------:|:---------------:|:-----:|
+| 0.8286     | 0.7084          | 0     |
+| 0.6756     | 0.6550          | 1     |
+| 0.6059     | 0.6725          | 2     |
+
+
+### Framework versions
+
+- Transformers 4.31.0
+- TensorFlow 2.12.0
+- Datasets 2.14.4
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "raygx/Nepali-DistilGPT2",
+  "_num_labels": 1,
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2ForSequenceClassification"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "id2label": {
+    "0": "NEUTRAL",
+    "1": "POSITIVE",
+    "2": "NEGATIVE"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "NEGATIVE": 2,
+    "NEUTRAL": 0,
+    "POSITIVE": 1
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 6,
+  "n_inner": null,
+  "n_layer": 6,
+  "n_positions": 1024,
+  "pad_token_id": 3,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "transformers_version": "4.31.0",
+  "use_cache": true,
+  "vocab_size": 50000
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b5d636e8158f79a7a90b86c9e3728baf0ca21cd18d1a7f7a9a490fd5a28fc4b
+size 326968664