Upload folder using huggingface_hub

.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

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

chat_template.jinja

@@ -0,0 +1,143 @@
+{#- Begin-of-sequence token to start the model prompt -#}
+{{ bos_token }}
+{#- Extracts the system message. Gemma does not support system messages so it will be prepended to first user message. -#}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set system_message = messages[0]['content'] -%}
+    {%- else -%}
+        {%- set system_message = messages[0]['content'][0]['text'] -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set system_message = "You are a helpful assistant Zero-Gemma made by ZeroAgency company from Russia. You must be helpful, harmless, and honest." -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+
+{%- if enable_thinking is defined and enable_thinking is true -%}
+    {%- set system_message = system_message + "\nFirst, think through the reasoning internally, then present the reasoning within <think>...</think>. After thinking, clearly state a response that addresses the user's request and aligns with their preferences, not just providing a direct answer." -%}
+{%- endif -%}
+
+{%- set system_message = system_message + '\n\n' -%}
+{#- Set tools to none if not defined for this ChatCompletion request (helps avoid errors later) -#}
+{%- if not tools is defined -%}
+    {%- set tools = none -%}
+{%- endif -%}
+
+{#- First - system message -#}
+
+{{ '<start_of_turn>system\n' -}}
+{{ system_message }}
+{#- Append system message with tool information if using tools in message request. -#}
+{%- if tools is not none -%}
+    {{- "Tools (functions) are available. If you decide to invoke one or more of the tools, you must respond with a python list of the function calls.\n" -}}
+    {{- "Example Format: [func_name1(params_name1=params_value1, params_name2=params_value2...), func_name2(params)] \n" -}}
+    {{- "Do not use variables. DO NOT USE MARKDOWN SYNTAX. You SHOULD NOT include any other text in the response if you call a function. If none of the functions can be used, point it out. If you lack the parameters required by the function, also point it out.\n" -}}
+    {{- "Here is a list of functions in JSON format that you can invoke.\n" -}}
+    {{- tools | tojson(indent=4) -}}
+    {{- "\n\n" -}}
+{%- endif -%}
+{{ '<end_of_turn>\n' }}
+
+{#- Main loop over all messages in the conversation history -#}
+{%- for message in loop_messages if message['role'] != 'system' -%}
+    {#- Normalize roles for model prompt formatting -#}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- elif (message['role'] == 'tool') -%}
+        {%- set role = "user" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {#- Mark the start of a message block with the appropriate role -#}
+    {{ '<start_of_turn>' + role + '\n' -}}
+
+    {#- Format model tool calls (turns where model indicates they want to call a tool) -#}
+    {%- if 'tool_calls' in message -%}
+        {%- if message['content'] is string -%}
+            {%- set content = message['content'] -%}
+            {%- if '</think>' in content -%}
+            {{- content | trim -}}
+            {{- "\n" -}}
+            {%- endif -%}
+        {%- endif -%}
+        {#- Opening bracket for tool call list. -#}
+        {{- '[' -}}
+        {#- For each tool call -#}
+        {%- for tool_call in message.tool_calls -%}
+            {#- Function name & opening parenthesis. -#}
+            {%- if tool_call.function is defined -%}
+                {%- set tool_call = tool_call.function -%}
+            {%- endif -%}
+            {{- tool_call.name + '(' -}}
+
+            {#-- Handle arguments as list (positional) or dict (named) --#}
+            {#-- Named arguments (dict) --#}
+            {%- if tool_call.arguments is iterable and tool_call.arguments is mapping -%}
+                {%- set first = true -%}
+                {%- for key, val in tool_call.arguments.items() -%}
+                    {%- if not first %}, {% endif -%}
+                    {{ key }}={{ val | tojson }}
+                    {%- set first = false -%}
+                {%- endfor -%}
+            {#-- Positional arguments (list) --#}
+            {%- elif tool_call.arguments is iterable -%}
+                {{- tool_call.arguments | map('tojson') | join(', ') -}}
+            {#-- Fallback: single positional value --#}
+            {%- else -%}
+                {{- tool_call.arguments | tojson -}}
+            {#-- Closing parenthesis. --#}
+            {%- endif -%}
+                {{- ')' -}}
+            {#-- If more than one tool call, place comma and move to formatting next tool call --#}
+            {%- if not loop.last -%}{{- "," -}}{%- endif -%}
+        {%- endfor -%}
+        {#- Closing bracket for tool call list. -#}
+        {{- ']' -}}
+    {%- endif -%}
+    
+    {#- Tool response start tag (for messages from a tool) -#}
+    {%- if (message['role'] == 'tool') -%}
+        {{- '<tool_response>\n' -}}
+    {%- endif -%}
+
+    {#- Render the message content: handle plain string or multimodal content like image/text -#}
+    {%- if not 'tool_calls' in message and message['content'] -%}
+        {%- if message['content'] is string -%}
+            {%- set content = message['content'] -%}
+            {# {%- if '</think>' in content -%}
+                {%- set content = content.split('</think>')[-1] -%}
+            {%- endif -%} #}
+            {{- content | trim -}}
+        {%- elif message['content'] is iterable -%}
+            {%- for item in message['content'] -%}
+                {%- if item['type'] == 'image' -%}
+                    {{ '<start_of_image>' }}
+                {%- elif item['type'] == 'text' -%}
+                    {%- set content = item['text'] -%}
+                    {%- if '</think>' in content -%}
+                        {%- set content = content.split('</think>')[-1] -%}
+                    {%- endif -%}
+                    {{ content | trim }}
+                {%- endif -%}
+            {%- endfor -%}
+        {%- else -%}
+            {{ raise_exception("Invalid content type:"+ message|tojson) }}
+        {%- endif -%}
+    {%- endif -%}
+
+    {#- Tool response end tag -#}
+    {%- if (message['role'] == 'tool') -%}
+        {{ '</tool_response>' -}}
+    {%- endif -%}
+
+    {#- Mark end of a single turn -#}
+    {{ '<end_of_turn>\n' }}
+{%- endfor -%}
+
+{#- If generation is to be triggered, add model prompt prefix -#}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model\n'}}
+    {%- if enable_thinking is defined and enable_thinking is true -%}
+        {{- '<think>' -}}
+    {%- endif %}
+{%- endif -%}

config.json

@@ -0,0 +1,60 @@
+{
+  "architectures": [
+    "Gemma3ForConditionalGeneration"
+  ],
+  "boi_token_index": 255999,
+  "eoi_token_index": 256000,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "image_token_index": 262144,
+  "initializer_range": 0.02,
+  "mm_tokens_per_image": 256,
+  "model_type": "gemma3",
+  "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": 3840,
+    "initializer_range": 0.02,
+    "intermediate_size": 15360,
+    "max_position_embeddings": 131072,
+    "model_type": "gemma3_text",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 48,
+    "num_key_value_heads": 8,
+    "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,
+    "use_cache": true,
+    "vocab_size": 262208
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "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,
+    "vision_use_head": false
+  }
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "pad_token_id": 0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "4.51.3"
+}

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4847447e92599833e8dbaa3067cd201c3bb5c052efa91f11ba891e43234f7832
+size 4979902192

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:891bd54eed03cba9ee1e705533a02a8217fcc29f356e4a1f53e5fd0d178883ad
+size 4931296592

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cee411d9d57324e50ce064a192cc5a858276d508611b12fc599e0c9767112e0
+size 4931296656

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bc75a29a730c9e743cad013feda3b0991a913fafe787c58a1c6e20afad97723
+size 4931296656

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed14bd4908c98fed9f61e8cd410167e0846de9abd78e0452ab092072e5d9252d
+size 4601000928

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074