Upload Gemma3ForCausalLM

config.json

@@ -0,0 +1,38 @@
+{
+  "_sliding_window_pattern": 6,
+  "architectures": [
+    "Gemma3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 2,
+  "dtype": "float32",
+  "eos_token_id": 1,
+  "final_logit_softcapping": null,
+  "head_dim": 8,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 32,
+  "initializer_range": 0.02,
+  "intermediate_size": 64,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention"
+  ],
+  "max_position_embeddings": 512,
+  "model_type": "gemma3_text",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 2,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_local_base_freq": 10000.0,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "sliding_window": 128,
+  "transformers_version": "4.57.3",
+  "use_bidirectional_attention": false,
+  "use_cache": true,
+  "vocab_size": 1024
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.57.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f334c4e5ee4382b76ffdd06be522387b70349bbaba83163c1bdb99e369add258
+size 208984