Add files using upload-large-folder tool

config.json

@@ -7,31 +7,31 @@
   "attn_logit_softcapping": null,
   "bos_token_id": 2,
   "cache_implementation": "hybrid",
-  "eos_token_id": 1,
+  "eos_token_id": [
+    1,
+    106
+  ],
   "final_logit_softcapping": null,
-  "head_dim": 128,
+  "head_dim": 256,
   "hidden_activation": "gelu_pytorch_tanh",
-  "hidden_size": 5376,
+  "hidden_size": 1152,
   "initializer_range": 0.02,
-  "intermediate_size": 21504,
-  "max_position_embeddings": 131072,
+  "intermediate_size": 6912,
+  "max_position_embeddings": 32768,
   "model_type": "gemma3_text",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 62,
-  "num_key_value_heads": 16,
+  "num_attention_heads": 4,
+  "num_hidden_layers": 26,
+  "num_key_value_heads": 1,
   "pad_token_id": 0,
-  "query_pre_attn_scalar": 168,
+  "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,
+  "rope_local_base_freq": 10000,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": 512,
   "sliding_window_pattern": 6,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.50.0",
   "use_cache": true,
-  "vocab_size": 262208
+  "vocab_size": 262144
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f746440bb93c56f741df4ca19eaa2ba9f3944e527990571150ab19bb9b78c26
+size 1999811208

tokenizer_config.json

@@ -51325,6 +51325,7 @@
   },
   "boi_token": "<start_of_image>",
   "bos_token": "<bos>",
+  "chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n    {%- if messages[0]['content'] is string -%}\n        {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n    {%- else -%}\n        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n    {%- endif -%}\n    {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n    {%- set first_user_prefix = \"\" -%}\n    {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n        {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n    {%- endif -%}\n    {%- if (message['role'] == 'assistant') -%}\n        {%- set role = \"model\" -%}\n    {%- else -%}\n        {%- set role = message['role'] -%}\n    {%- endif -%}\n    {{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n    {%- if message['content'] is string -%}\n        {{ message['content'] | trim }}\n    {%- elif message['content'] is iterable -%}\n        {%- for item in message['content'] -%}\n            {%- if item['type'] == 'image' -%}\n                {{ '<start_of_image>' }}\n            {%- elif item['type'] == 'text' -%}\n                {{ item['text'] | trim }}\n            {%- endif -%}\n        {%- endfor -%}\n    {%- else -%}\n        {{ raise_exception(\"Invalid content type\") }}\n    {%- endif -%}\n    {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n    {{'<start_of_turn>model\n'}}\n{%- endif -%}\n",
   "clean_up_tokenization_spaces": false,
   "eoi_token": "<end_of_image>",
   "eos_token": "<eos>",