Upload Gemma3ForCausalLM

config.json

@@ -5,9 +5,9 @@
   "attention_bias": false,
   "attention_dropout": 0.0,
   "attn_logit_softcapping": null,
-  "bos_token_id": 262145,
+  "bos_token_id": 2,
   "cache_implementation": "hybrid",
-  "eos_token_id": 262146,
+  "eos_token_id": 1,
   "final_logit_softcapping": null,
   "head_dim": 256,
   "hidden_activation": "gelu_pytorch_tanh",
@@ -19,7 +19,7 @@
   "num_attention_heads": 4,
   "num_hidden_layers": 26,
   "num_key_value_heads": 1,
-  "pad_token_id": 262146,
+  "pad_token_id": 0,
   "query_pre_attn_scalar": 256,
   "rms_norm_eps": 1e-06,
   "rope_local_base_freq": 10000,
@@ -28,7 +28,7 @@
   "sliding_window": 512,
   "sliding_window_pattern": 6,
   "torch_dtype": "float32",
-  "transformers_version": "4.50.3",
+  "transformers_version": "4.51.0",
   "use_cache": true,
-  "vocab_size": 262147
+  "vocab_size": 262144
 }

generation_config.json

@@ -1,10 +1,13 @@
 {
-  "bos_token_id": 262145,
+  "bos_token_id": 2,
   "cache_implementation": "hybrid",
   "do_sample": true,
-  "eos_token_id": 262146,
-  "pad_token_id": 262146,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "pad_token_id": 0,
   "top_k": 64,
   "top_p": 0.95,
-  "transformers_version": "4.50.3"
+  "transformers_version": "4.51.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b76bf11e62ac968c448bc63f3069faacf260fe413dceb16f4350437cad3b521
-size 3999596784
+oid sha256:d17bde89fd755a4fd2899bce87189a9a76ddce663f58452f1b0b0084f772d891
+size 3999582960