Text Generation
KerasHub
Keras
English
text-generation-inference
Divyasreepat commited on
Commit
b2c6cae
1 Parent(s): df687a3

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: keras-hub
3
+ ---
4
+ This is a [`Falcon` model](https://keras.io/api/keras_hub/models/falcon) uploaded using the KerasHub library and can be used with JAX, TensorFlow, and PyTorch backends.
5
+ Model config:
6
+ * **name:** falcon_backbone
7
+ * **trainable:** True
8
+ * **vocabulary_size:** 50304
9
+ * **num_layers:** 24
10
+ * **num_attention_heads:** 32
11
+ * **hidden_dim:** 2048
12
+ * **intermediate_dim:** 8192
13
+ * **attention_dropout_rate:** 0.0
14
+ * **feedforward_dropout_rate:** 0.0
15
+ * **layer_norm_epsilon:** 1e-05
16
+
17
+ 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 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "module": "keras_nlp.models.falcon.falcon_backbone",
3
+ "class_name": "FalconBackbone",
4
+ "config": {
5
+ "name": "falcon_backbone",
6
+ "trainable": true,
7
+ "vocabulary_size": 50304,
8
+ "num_layers": 24,
9
+ "num_attention_heads": 32,
10
+ "hidden_dim": 2048,
11
+ "intermediate_dim": 8192,
12
+ "attention_dropout_rate": 0.0,
13
+ "feedforward_dropout_rate": 0.0,
14
+ "layer_norm_epsilon": 1e-05
15
+ },
16
+ "registered_name": "keras_nlp>FalconBackbone",
17
+ "assets": [],
18
+ "weights": "model.weights.h5"
19
+ }
metadata.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "keras_version": "3.0.4",
3
+ "keras_nlp_version": "0.9.0",
4
+ "parameter_count": 1311625216,
5
+ "date_saved": "2024-03-07@02:26:48"
6
+ }
model.weights.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a327fbc25209580721cea8d0cc1fd2f04283d2526294f2268e488225d5430f8
3
+ size 5247273664
tokenizer.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "module": "keras_nlp.models.falcon.falcon_tokenizer",
3
+ "class_name": "FalconTokenizer",
4
+ "config": {
5
+ "name": "falcon_tokenizer",
6
+ "trainable": true,
7
+ "dtype": "int32",
8
+ "sequence_length": null,
9
+ "add_prefix_space": false
10
+ },
11
+ "registered_name": "keras_nlp>FalconTokenizer",
12
+ "assets": [
13
+ "assets/tokenizer/merges.txt",
14
+ "assets/tokenizer/vocabulary.json"
15
+ ],
16
+ "weights": null
17
+ }