martin-gorner HF staff commited on
Commit
f420dad
1 Parent(s): 9834109

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ assets/tokenizer/vocabulary.spm filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: keras-nlp
3
+ pipeline_tag: text-generation
4
+ ---
5
+ This is a [`Gemma` model](https://keras.io/api/keras_nlp/models/gemma) uploaded using the KerasNLP library and can be used with JAX, TensorFlow, and PyTorch backends.
6
+ This model is related to a `CausalLM` task.
7
+
8
+ Model config:
9
+ * **name:** gemma_backbone
10
+ * **trainable:** True
11
+ * **vocabulary_size:** 256000
12
+ * **num_layers:** 28
13
+ * **num_query_heads:** 16
14
+ * **num_key_value_heads:** 16
15
+ * **hidden_dim:** 3072
16
+ * **intermediate_dim:** 49152
17
+ * **head_dim:** 256
18
+ * **layer_norm_epsilon:** 1e-06
19
+ * **dropout:** 0
20
+
21
+ 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/vocabulary.spm ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
3
+ size 4241003
config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "module": "keras_nlp.src.models.gemma.gemma_backbone",
3
+ "class_name": "GemmaBackbone",
4
+ "config": {
5
+ "name": "gemma_backbone",
6
+ "trainable": true,
7
+ "vocabulary_size": 256000,
8
+ "num_layers": 28,
9
+ "num_query_heads": 16,
10
+ "num_key_value_heads": 16,
11
+ "hidden_dim": 3072,
12
+ "intermediate_dim": 49152,
13
+ "head_dim": 256,
14
+ "layer_norm_epsilon": 1e-06,
15
+ "dropout": 0
16
+ },
17
+ "registered_name": "keras_nlp>GemmaBackbone"
18
+ }
metadata.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "keras_version": "3.1.1",
3
+ "keras_nlp_version": "0.10.0",
4
+ "parameter_count": 8559815680,
5
+ "date_saved": "2024-04-30@16:06:27"
6
+ }
model.weights.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80350917f176d758515dce9cf9f7aac2567de17bed2becfe24198846476cde96
3
+ size 17076221400
preprocessor.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "module": "keras_nlp.src.models.gemma.gemma_causal_lm_preprocessor",
3
+ "class_name": "GemmaCausalLMPreprocessor",
4
+ "config": {
5
+ "name": "gemma_causal_lm_preprocessor",
6
+ "trainable": true,
7
+ "dtype": "bfloat16",
8
+ "tokenizer": {
9
+ "module": "keras_nlp.src.models.gemma.gemma_tokenizer",
10
+ "class_name": "GemmaTokenizer",
11
+ "config": {
12
+ "name": "gemma_tokenizer",
13
+ "trainable": true,
14
+ "dtype": "int32",
15
+ "proto": null,
16
+ "sequence_length": null
17
+ },
18
+ "registered_name": "keras_nlp>GemmaTokenizer"
19
+ },
20
+ "sequence_length": 8192,
21
+ "add_start_token": true,
22
+ "add_end_token": true
23
+ },
24
+ "registered_name": "keras_nlp>GemmaCausalLMPreprocessor"
25
+ }
task.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "module": "keras_nlp.src.models.gemma.gemma_causal_lm",
3
+ "class_name": "GemmaCausalLM",
4
+ "config": {
5
+ "backbone": {
6
+ "module": "keras_nlp.src.models.gemma.gemma_backbone",
7
+ "class_name": "GemmaBackbone",
8
+ "config": {
9
+ "name": "gemma_backbone",
10
+ "trainable": true,
11
+ "vocabulary_size": 256000,
12
+ "num_layers": 28,
13
+ "num_query_heads": 16,
14
+ "num_key_value_heads": 16,
15
+ "hidden_dim": 3072,
16
+ "intermediate_dim": 49152,
17
+ "head_dim": 256,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "dropout": 0
20
+ },
21
+ "registered_name": "keras_nlp>GemmaBackbone"
22
+ },
23
+ "preprocessor": {
24
+ "module": "keras_nlp.src.models.gemma.gemma_causal_lm_preprocessor",
25
+ "class_name": "GemmaCausalLMPreprocessor",
26
+ "config": {
27
+ "name": "gemma_causal_lm_preprocessor",
28
+ "trainable": true,
29
+ "dtype": "bfloat16",
30
+ "tokenizer": {
31
+ "module": "keras_nlp.src.models.gemma.gemma_tokenizer",
32
+ "class_name": "GemmaTokenizer",
33
+ "config": {
34
+ "name": "gemma_tokenizer",
35
+ "trainable": true,
36
+ "dtype": "int32",
37
+ "proto": null,
38
+ "sequence_length": null
39
+ },
40
+ "registered_name": "keras_nlp>GemmaTokenizer"
41
+ },
42
+ "sequence_length": 8192,
43
+ "add_start_token": true,
44
+ "add_end_token": true
45
+ },
46
+ "registered_name": "keras_nlp>GemmaCausalLMPreprocessor"
47
+ },
48
+ "name": "gemma_causal_lm"
49
+ },
50
+ "registered_name": "keras_nlp>GemmaCausalLM"
51
+ }
tokenizer.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "module": "keras_nlp.src.models.gemma.gemma_tokenizer",
3
+ "class_name": "GemmaTokenizer",
4
+ "config": {
5
+ "name": "gemma_tokenizer",
6
+ "trainable": true,
7
+ "dtype": "int32",
8
+ "proto": null,
9
+ "sequence_length": null
10
+ },
11
+ "registered_name": "keras_nlp>GemmaTokenizer"
12
+ }