(Trained with Unsloth)

.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

chat_template.jinja

@@ -0,0 +1,8 @@
+{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{'<start_of_turn>user
+' + messages[0]['content'] | trim + ' ' + messages[1]['content'] | trim + '<end_of_turn>
+'}}{% set messages = messages[2:] %}{% endif %}{% for message in messages %}{% if message['role'] == 'user' %}{{'<start_of_turn>user
+' + message['content'] | trim + '<end_of_turn>
+'}}{% elif message['role'] == 'assistant' %}{{'<start_of_turn>model
+' + message['content'] | trim + '<end_of_turn>
+' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<start_of_turn>model
+' }}{% endif %}

config.json

@@ -0,0 +1,57 @@
+{
+    "_sliding_window_pattern": 6,
+    "architectures": [
+        "Gemma3ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_logit_softcapping": null,
+    "bos_token_id": 2,
+    "torch_dtype": "bfloat16",
+    "eos_token_id": 106,
+    "final_logit_softcapping": null,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 640,
+    "initializer_range": 0.02,
+    "intermediate_size": 2048,
+    "layer_types": [
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention"
+    ],
+    "max_position_embeddings": 32768,
+    "model_type": "gemma3_text",
+    "num_attention_heads": 4,
+    "num_hidden_layers": 18,
+    "num_key_value_heads": 1,
+    "pad_token_id": 0,
+    "query_pre_attn_scalar": 256,
+    "rms_norm_eps": 1e-06,
+    "rope_local_base_freq": 10000.0,
+    "rope_parameters": null,
+    "rope_scaling": null,
+    "rope_theta": 1000000.0,
+    "sliding_window": 512,
+    "transformers_version": "4.57.1",
+    "unsloth_fixed": true,
+    "unsloth_version": "2026.1.4",
+    "use_bidirectional_attention": false,
+    "use_cache": true,
+    "vocab_size": 262144
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<bos>",
+  "eos_token": "<end_of_turn>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6b09a0b4a803ad453063ca4bb49a784540e8120004e2450e025df2b27d41fb2
+size 33384899