add model

README.md

@@ -1,3 +1,46 @@
 ---
-license: afl-3.0
+tags:
+- generated_from_keras_callback
+model-index:
+- name: tmpq0jhm_jh
+  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. -->
+
+# tmpq0jhm_jh
+
+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 4.18.0
+- TensorFlow 2.4.1
+- Tokenizers 0.12.1

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "/content/drive/MyDrive/Colab Notebooks_b/modeliai/wiki_10_validate",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "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,
+  "transformers_version": "4.18.0",
+  "use_cache": true,
+  "vocab_size": 50000
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d3b8d4c8562897a7c776cd035ab3833aea8639c13fc758f77e8256489163c27
+size 497144144