(Trained with Unsloth)

config.json

@@ -0,0 +1,36 @@
+{
+    "architectures": [
+        "Gemma3ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_logit_softcapping": null,
+    "bos_token_id": 2,
+    "cache_implementation": "hybrid",
+    "eos_token_id": 106,
+    "final_logit_softcapping": null,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "initializer_range": 0.02,
+    "intermediate_size": 6912,
+    "max_position_embeddings": 32768,
+    "model_type": "gemma3_text",
+    "num_attention_heads": 4,
+    "num_hidden_layers": 26,
+    "num_key_value_heads": 1,
+    "pad_token_id": 0,
+    "query_pre_attn_scalar": 256,
+    "rms_norm_eps": 1e-06,
+    "rope_local_base_freq": 10000,
+    "rope_scaling": null,
+    "rope_theta": 1000000,
+    "sliding_window": 512,
+    "sliding_window_pattern": 6,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.51.3",
+    "unsloth_fixed": true,
+    "unsloth_version": "2025.4.4",
+    "use_cache": true,
+    "vocab_size": 262144
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "max_length": 32768,
+  "pad_token_id": 0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "4.51.3"
+}