Divyasreepat commited on
Commit
5eee00d
1 Parent(s): 8f09106

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: keras-hub
3
+ ---
4
+ This is a [`GPT2` model](https://keras.io/api/keras_hub/models/gpt2) uploaded using the KerasHub library and can be used with JAX, TensorFlow, and PyTorch backends.
5
+ Model config:
6
+ * **name:** gpt2_backbone
7
+ * **trainable:** True
8
+ * **vocabulary_size:** 50257
9
+ * **num_layers:** 48
10
+ * **num_heads:** 25
11
+ * **hidden_dim:** 1600
12
+ * **intermediate_dim:** 6400
13
+ * **dropout:** 0.1
14
+ * **max_sequence_length:** 1024
15
+
16
+ This model card has been generated automatically and should be completed by the model author. See [Model Cards documentation](https://huggingface.co/docs/hub/model-cards) for more information.
assets/tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
assets/tokenizer/vocabulary.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "module": "keras_nlp.src.models.gpt2.gpt2_backbone",
3
+ "class_name": "GPT2Backbone",
4
+ "config": {
5
+ "name": "gpt2_backbone",
6
+ "trainable": true,
7
+ "vocabulary_size": 50257,
8
+ "num_layers": 48,
9
+ "num_heads": 25,
10
+ "hidden_dim": 1600,
11
+ "intermediate_dim": 6400,
12
+ "dropout": 0.1,
13
+ "max_sequence_length": 1024
14
+ },
15
+ "registered_name": "keras_nlp>GPT2Backbone",
16
+ "assets": [],
17
+ "weights": "model.weights.h5"
18
+ }
metadata.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "keras_version": "3.0.1",
3
+ "keras_nlp_version": "0.7.0",
4
+ "parameter_count": 1557611200,
5
+ "date_saved": "2023-12-27@02:11:27"
6
+ }
model.weights.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0e14a62d5b813798c2d1104de9216dba36f56c50e2ff90f36f449c6f41893a6
3
+ size 6231993336
tokenizer.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "module": "keras_nlp.src.models.gpt2.gpt2_tokenizer",
3
+ "class_name": "GPT2Tokenizer",
4
+ "config": {
5
+ "name": "gpt2_tokenizer",
6
+ "trainable": true,
7
+ "dtype": "int32",
8
+ "sequence_length": null,
9
+ "add_prefix_space": false
10
+ },
11
+ "registered_name": "keras_nlp>GPT2Tokenizer",
12
+ "assets": [
13
+ "assets/tokenizer/merges.txt",
14
+ "assets/tokenizer/vocabulary.json"
15
+ ],
16
+ "weights": null
17
+ }