Upload model

README.md

@@ -0,0 +1,46 @@
+---
+tags:
+- generated_from_keras_callback
+model-index:
+- name: mGPT_base
+  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. -->
+
+# mGPT_base
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+
+
+## 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: None
+- training_precision: float32
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.23.1
+- TensorFlow 2.9.2
+- Tokenizers 0.13.1

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "mGPT-base",
+  "afn": "gelu",
+  "architectures": [
+    "OpenAIGPTModel"
+  ],
+  "attn_pdrop": 0.1,
+  "embd_pdrop": 0.1,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-12,
+  "model_type": "openai-gpt",
+  "n_ctx": 512,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_layer": 12,
+  "n_positions": 512,
+  "n_special": 0,
+  "predict_special_tokens": true,
+  "resid_pdrop": 0.1,
+  "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": "4.23.1",
+  "vocab_size": 119547
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9944360654b0eb5bbbc9aae52305d5c47772db77665fd0f4b8c313bbbb609da6
+size 709213544