Upload Gemma3ForConditionalGeneration

config.json

@@ -1,35 +1,64 @@
 {
   "architectures": [
-    "Gemma2ForCausalLM"
+    "Gemma3ForConditionalGeneration"
   ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "attn_logit_softcapping": 50.0,
-  "bos_token_id": 2,
-  "cache_implementation": "hybrid",
+  "boi_token_index": 255999,
+  "eoi_token_index": 256000,
   "eos_token_id": [
     1,
-    107
+    106
   ],
-  "final_logit_softcapping": 30.0,
-  "head_dim": 256,
-  "hidden_act": "gelu_pytorch_tanh",
-  "hidden_activation": "gelu_pytorch_tanh",
-  "hidden_size": 2304,
+  "hidden_size": 3840,
+  "image_token_index": 262144,
   "initializer_range": 0.02,
-  "intermediate_size": 9216,
-  "max_position_embeddings": 8192,
-  "model_type": "gemma2",
-  "num_attention_heads": 8,
-  "num_hidden_layers": 26,
-  "num_key_value_heads": 4,
-  "pad_token_id": 0,
-  "query_pre_attn_scalar": 256,
-  "rms_norm_eps": 1e-06,
-  "rope_theta": 10000.0,
-  "sliding_window": 4096,
+  "mm_tokens_per_image": 256,
+  "model_type": "gemma3",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_logit_softcapping": null,
+    "cache_implementation": "hybrid",
+    "final_logit_softcapping": null,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 3840,
+    "initializer_range": 0.02,
+    "intermediate_size": 15360,
+    "max_position_embeddings": 131072,
+    "model_type": "gemma3_text",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 48,
+    "num_key_value_heads": 8,
+    "query_pre_attn_scalar": 256,
+    "rms_norm_eps": 1e-06,
+    "rope_local_base_freq": 10000.0,
+    "rope_scaling": {
+      "factor": 8.0,
+      "rope_type": "linear"
+    },
+    "rope_theta": 1000000.0,
+    "sliding_window": 1024,
+    "sliding_window_pattern": 6,
+    "torch_dtype": "bfloat16",
+    "use_cache": true,
+    "vocab_size": 262208
+  },
   "torch_dtype": "bfloat16",
   "transformers_version": "4.51.3",
   "use_cache": true,
-  "vocab_size": 256000
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "image_size": 896,
+    "intermediate_size": 4304,
+    "layer_norm_eps": 1e-06,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 27,
+    "patch_size": 14,
+    "torch_dtype": "bfloat16",
+    "vision_use_head": false
+  }
 }

generation_config.json

@@ -1,11 +1,13 @@
 {
-  "_from_model_config": true,
   "bos_token_id": 2,
   "cache_implementation": "hybrid",
+  "do_sample": true,
   "eos_token_id": [
     1,
-    107
+    106
   ],
   "pad_token_id": 0,
+  "top_k": 64,
+  "top_p": 0.95,
   "transformers_version": "4.51.3"
 }

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4847447e92599833e8dbaa3067cd201c3bb5c052efa91f11ba891e43234f7832
+size 4979902192

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:891bd54eed03cba9ee1e705533a02a8217fcc29f356e4a1f53e5fd0d178883ad
+size 4931296592

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cee411d9d57324e50ce064a192cc5a858276d508611b12fc599e0c9767112e0
+size 4931296656

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bc75a29a730c9e743cad013feda3b0991a913fafe787c58a1c6e20afad97723
+size 4931296656

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed14bd4908c98fed9f61e8cd410167e0846de9abd78e0452ab092072e5d9252d
+size 4601000928