Divyasreepat
commited on
Commit
•
899cfeb
1
Parent(s):
6605c1d
Upload folder using huggingface_hub
Browse files- README.md +14 -0
- assets/tokenizer/merges.txt +0 -0
- assets/tokenizer/vocabulary.json +0 -0
- config.json +16 -0
- metadata.json +6 -0
- model.weights.h5 +3 -0
- tokenizer.json +17 -0
README.md
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: keras-hub
|
3 |
+
---
|
4 |
+
This is a [`OPT` model](https://keras.io/api/keras_hub/models/opt) uploaded using the KerasHub library and can be used with JAX, TensorFlow, and PyTorch backends.
|
5 |
+
Model config:
|
6 |
+
* **vocabulary_size:** 50272
|
7 |
+
* **num_layers:** 32
|
8 |
+
* **num_heads:** 32
|
9 |
+
* **hidden_dim:** 4096
|
10 |
+
* **intermediate_dim:** 16384
|
11 |
+
* **dropout:** 0.1
|
12 |
+
* **max_sequence_length:** 2048
|
13 |
+
|
14 |
+
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 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"module": "keras_nlp.src.models.opt.opt_backbone",
|
3 |
+
"class_name": "OPTBackbone",
|
4 |
+
"config": {
|
5 |
+
"vocabulary_size": 50272,
|
6 |
+
"num_layers": 32,
|
7 |
+
"num_heads": 32,
|
8 |
+
"hidden_dim": 4096,
|
9 |
+
"intermediate_dim": 16384,
|
10 |
+
"dropout": 0.1,
|
11 |
+
"max_sequence_length": 2048
|
12 |
+
},
|
13 |
+
"registered_name": "keras_nlp>OPTBackbone",
|
14 |
+
"assets": [],
|
15 |
+
"weights": "model.weights.h5"
|
16 |
+
}
|
metadata.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"keras_version": "3.0.1",
|
3 |
+
"keras_nlp_version": "0.7.0",
|
4 |
+
"parameter_count": 6658465792,
|
5 |
+
"date_saved": "2023-12-27@02:22:41"
|
6 |
+
}
|
model.weights.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d0f5018c453aa0f5c50ddc256c3e2edea2bf2b5676a18e48700d1d83d6b6805
|
3 |
+
size 26634899856
|
tokenizer.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"module": "keras_nlp.src.models.opt.opt_tokenizer",
|
3 |
+
"class_name": "OPTTokenizer",
|
4 |
+
"config": {
|
5 |
+
"name": "opt_tokenizer",
|
6 |
+
"trainable": true,
|
7 |
+
"dtype": "int32",
|
8 |
+
"sequence_length": null,
|
9 |
+
"add_prefix_space": false
|
10 |
+
},
|
11 |
+
"registered_name": "keras_nlp>OPTTokenizer",
|
12 |
+
"assets": [
|
13 |
+
"assets/tokenizer/merges.txt",
|
14 |
+
"assets/tokenizer/vocabulary.json"
|
15 |
+
],
|
16 |
+
"weights": null
|
17 |
+
}
|