Add sentdex model and tokenizer

.gitattributes

@@ -15,3 +15,4 @@
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1 @@
+{"<|endoftext|>": 52000}

clone_sentdex_model_tokenizer.py

@@ -0,0 +1,9 @@
+#!/usr/bin/env python
+from transformers import AutoTokenizer, TFAutoModelForCausalLM
+import tensorflow as tf
+
+tokenizer = AutoTokenizer.from_pretrained("Sentdex/GPyT")
+model =  TFAutoModelForCausalLM.from_pretrained("Sentdex/GPyT", from_pt=True)
+
+tokenizer.save_pretrained(save_directory='./')
+model.save_pretrained(save_directory='./', saved_model=True)

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "Sentdex/GPyT",
+  "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,
+  "resid_pdrop": 0.1,
+  "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": "4.9.1",
+  "use_cache": true,
+  "vocab_size": 52000
+}

saved_model/1/keras_metadata.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d421caaf137a4c2050961971319ae0316e50664cfb590c7c5f444bb5d64b76d
+size 67064

saved_model/1/saved_model.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e949c88949ecccebec606466c6a09546d1142140ae8455c5571b9c4ac7db5efd
+size 5079982

saved_model/1/variables/variables.data-00000-of-00001

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:449d69e48d6fd879391fd8e811d76b6fe5a0a2ef3f9ec181d7266fdb829ffec1
+size 503191134

saved_model/1/variables/variables.index

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d770805de94ce9274fbc80084f94a83aaa950cac80934211ef5d6741cb326b5
+size 8900

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4afd368410a15f1aae0c996ce4b11fd1b6205147a659668064c09418f06f2cb5
+size 503289416

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "special_tokens_map_file": null, "name_or_path": "Sentdex/GPyT", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}