Upload 7 files

Model fine tuned

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+assets/tokenizer/vocabulary.spm filter=lfs diff=lfs merge=lfs -text

assets/tokenizer/vocabulary.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

config.json

@@ -0,0 +1,25 @@
+{
+    "module": "keras_nlp.src.models.gemma.gemma_backbone",
+    "class_name": "GemmaBackbone",
+    "config": {
+        "name": "gemma_backbone",
+        "trainable": true,
+        "vocabulary_size": 256000,
+        "num_layers": 18,
+        "num_query_heads": 8,
+        "num_key_value_heads": 1,
+        "hidden_dim": 2048,
+        "intermediate_dim": 32768,
+        "head_dim": 256,
+        "layer_norm_epsilon": 1e-06,
+        "dropout": 0,
+        "query_head_dim_normalize": true,
+        "use_post_ffw_norm": false,
+        "use_post_attention_norm": false,
+        "final_logit_soft_cap": null,
+        "attention_logit_soft_cap": null,
+        "sliding_window_size": 4096,
+        "use_sliding_window_attention": false
+    },
+    "registered_name": "keras_nlp>GemmaBackbone"
+}

metadata.json

@@ -0,0 +1,6 @@
+{
+    "keras_version": "3.3.3",
+    "keras_nlp_version": "0.15.1",
+    "parameter_count": 2507536384,
+    "date_saved": "2024-11-25@13:18:03"
+}

model.weights.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f41765e2cc8777f68c3cf09987acdd2386c019aafe00ee4588fa107d0dba0a96
+size 10025240416

preprocessor.json

@@ -0,0 +1,27 @@
+{
+    "module": "keras_nlp.src.models.gemma.gemma_causal_lm_preprocessor",
+    "class_name": "GemmaCausalLMPreprocessor",
+    "config": {
+        "name": "gemma_causal_lm_preprocessor",
+        "trainable": true,
+        "dtype": "float32",
+        "tokenizer": {
+            "module": "keras_nlp.src.models.gemma.gemma_tokenizer",
+            "class_name": "GemmaTokenizer",
+            "config": {
+                "name": "gemma_tokenizer",
+                "trainable": true,
+                "dtype": "int32",
+                "proto": null,
+                "sequence_length": null,
+                "add_bos": false,
+                "add_eos": false
+            },
+            "registered_name": "keras_nlp>GemmaTokenizer"
+        },
+        "sequence_length": 512,
+        "add_start_token": true,
+        "add_end_token": true
+    },
+    "registered_name": "keras_nlp>GemmaCausalLMPreprocessor"
+}

task.json

@@ -0,0 +1,60 @@
+{
+    "module": "keras_nlp.src.models.gemma.gemma_causal_lm",
+    "class_name": "GemmaCausalLM",
+    "config": {
+        "backbone": {
+            "module": "keras_nlp.src.models.gemma.gemma_backbone",
+            "class_name": "GemmaBackbone",
+            "config": {
+                "name": "gemma_backbone",
+                "trainable": true,
+                "vocabulary_size": 256000,
+                "num_layers": 18,
+                "num_query_heads": 8,
+                "num_key_value_heads": 1,
+                "hidden_dim": 2048,
+                "intermediate_dim": 32768,
+                "head_dim": 256,
+                "layer_norm_epsilon": 1e-06,
+                "dropout": 0,
+                "query_head_dim_normalize": true,
+                "use_post_ffw_norm": false,
+                "use_post_attention_norm": false,
+                "final_logit_soft_cap": null,
+                "attention_logit_soft_cap": null,
+                "sliding_window_size": 4096,
+                "use_sliding_window_attention": false
+            },
+            "registered_name": "keras_nlp>GemmaBackbone"
+        },
+        "preprocessor": {
+            "module": "keras_nlp.src.models.gemma.gemma_causal_lm_preprocessor",
+            "class_name": "GemmaCausalLMPreprocessor",
+            "config": {
+                "name": "gemma_causal_lm_preprocessor",
+                "trainable": true,
+                "dtype": "float32",
+                "tokenizer": {
+                    "module": "keras_nlp.src.models.gemma.gemma_tokenizer",
+                    "class_name": "GemmaTokenizer",
+                    "config": {
+                        "name": "gemma_tokenizer",
+                        "trainable": true,
+                        "dtype": "int32",
+                        "proto": null,
+                        "sequence_length": null,
+                        "add_bos": false,
+                        "add_eos": false
+                    },
+                    "registered_name": "keras_nlp>GemmaTokenizer"
+                },
+                "sequence_length": 512,
+                "add_start_token": true,
+                "add_end_token": true
+            },
+            "registered_name": "keras_nlp>GemmaCausalLMPreprocessor"
+        },
+        "name": "gemma_causal_lm"
+    },
+    "registered_name": "keras_nlp>GemmaCausalLM"
+}

tokenizer.json

@@ -0,0 +1,14 @@
+{
+    "module": "keras_nlp.src.models.gemma.gemma_tokenizer",
+    "class_name": "GemmaTokenizer",
+    "config": {
+        "name": "gemma_tokenizer",
+        "trainable": true,
+        "dtype": "int32",
+        "proto": null,
+        "sequence_length": null,
+        "add_bos": false,
+        "add_eos": false
+    },
+    "registered_name": "keras_nlp>GemmaTokenizer"
+}