Add files using upload-large-folder tool

.gitattributes

@@ -34,3 +34,6 @@ saved_model/**/* 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
+model-00001-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text
+tokenizer.model filter=lfs diff=lfs merge=lfs -text

config.json

@@ -3,60 +3,36 @@
     "Gemma3ForConditionalGeneration"
   ],
   "boi_token_index": 255999,
-  "bos_token_id": 2,
   "eoi_token_index": 256000,
-  "eos_token_id": 106,
+  "eos_token_id": [
+    1,
+    106
+  ],
   "image_token_index": 262144,
   "initializer_range": 0.02,
   "mm_tokens_per_image": 256,
   "model_type": "gemma3",
-  "pad_token_id": 0,
   "text_config": {
-    "attention_bias": false,
-    "attention_dropout": 0.0,
-    "attn_logit_softcapping": null,
-    "cache_implementation": "hybrid",
-    "final_logit_softcapping": null,
-    "head_dim": 256,
-    "hidden_activation": "gelu_pytorch_tanh",
     "hidden_size": 2560,
-    "initializer_range": 0.02,
     "intermediate_size": 10240,
-    "max_position_embeddings": 131072,
     "model_type": "gemma3_text",
-    "num_attention_heads": 8,
     "num_hidden_layers": 34,
-    "num_key_value_heads": 4,
-    "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,
-    "sliding_window_pattern": 6,
-    "torch_dtype": "bfloat16",
-    "use_cache": true,
-    "vocab_size": 262208
+    "sliding_window": 1024
   },
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.51.0",
-  "unsloth_fixed": true,
+  "transformers_version": "4.50.0.dev0",
   "vision_config": {
-    "attention_dropout": 0.0,
-    "hidden_act": "gelu_pytorch_tanh",
     "hidden_size": 1152,
     "image_size": 896,
     "intermediate_size": 4304,
-    "layer_norm_eps": 1e-06,
     "model_type": "siglip_vision_model",
     "num_attention_heads": 16,
-    "num_channels": 3,
     "num_hidden_layers": 27,
     "patch_size": 14,
-    "torch_dtype": "bfloat16",
     "vision_use_head": false
   }
 }

generation_config.json

@@ -9,5 +9,5 @@
   "pad_token_id": 0,
   "top_k": 64,
   "top_p": 0.95,
-  "transformers_version": "4.51.0"
+  "transformers_version": "4.50.0.dev0"
 }

special_tokens_map.json

@@ -9,7 +9,7 @@
   },
   "eoi_token": "<end_of_image>",
   "eos_token": {
-    "content": "<end_of_turn>",
+    "content": "<eos>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -51328,16 +51328,15 @@
   "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": "<end_of_turn>",
+  "eos_token": "<eos>",
   "extra_special_tokens": {
     "boi_token": "<start_of_image>",
     "eoi_token": "<end_of_image>",
     "image_token": "<image_soft_token>"
   },
   "image_token": "<image_soft_token>",
-  "model_max_length": 131072,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
-  "padding_side": "left",
   "processor_class": "Gemma3Processor",
   "sp_model_kwargs": null,
   "spaces_between_special_tokens": false,