Upload 7 files

chat_template.jinja

@@ -1,9 +1,15 @@
-{%- macro format_parameters(properties, required) -%}
+{#
+  Template: Google Gemma 4 Canonical Chat Template
+  Author: Google Gemma Engineering Team
+  Published: 2026-07-09
+  Context: Fixed tool-calling loops, turn closures, and thinking content-ordering.
+#}
+{%- macro format_parameters(properties, required, filter_keys=false) -%}
     {%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}
     {%- set ns = namespace(found_first=false) -%}
     {%- for key, value in properties | dictsort -%}
         {%- set add_comma = false -%}
-        {%- if key not in standard_keys -%}
+        {%- if not filter_keys or key not in standard_keys -%}
             {%- if ns.found_first %},{% endif -%}
             {%- set ns.found_first = true -%}
             {{ key }}:{
@@ -65,7 +71,7 @@
                 {%- elif value is mapping -%}
                     {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
                     properties:{
-                    {{- format_parameters(value, value['required'] | default([])) -}}
+                    {{- format_parameters(value, value['required'] | default([]), filter_keys=true) -}}
                     }
                 {%- endif -%}
                 {%- if value['required'] -%}
@@ -116,7 +122,9 @@
     }
 {%- endmacro -%}
 {%- macro format_argument(argument, escape_keys=True) -%}
-    {%- if argument is string -%}
+    {%- if argument is none -%}
+        {{- 'null' -}}
+    {%- elif argument is string -%}
         {{- '<|"|>' + argument + '<|"|>' -}}
     {%- elif argument is boolean -%}
         {{- 'true' if argument else 'false' -}}
@@ -172,24 +180,30 @@
     {{- '<tool_response|>' -}}
 {%- endmacro -%}
 
-{%- set ns = namespace(prev_message_type=None) -%}
+{#- ===== SETUP ===== -#}
+{%- set ns = namespace(prev_message_type=None, prev_non_tool_role=None) -%}
 {%- set loop_messages = messages -%}
+{%- set enable_thinking = enable_thinking | default(false) -%}
+{%- set preserve_thinking = preserve_thinking | default(false) -%}
 {{- bos_token -}}
 {#- Handle System/Tool Definitions Block -#}
-{%- if (enable_thinking is defined and enable_thinking) or tools or messages[0]['role'] in ['system', 'developer'] -%}
+{%- if enable_thinking or tools or (messages and messages[0]['role'] in ['system', 'developer']) -%}
     {{- '<|turn>system\n' -}}
-
     {#- Inject Thinking token at the very top of the FIRST system turn -#}
-    {%- if enable_thinking is defined and enable_thinking -%}
+    {%- if enable_thinking -%}
         {{- '<|think|>\n' -}}
         {%- set ns.prev_message_type = 'think' -%}
     {%- endif -%}
-
-    {%- if messages[0]['role'] in ['system', 'developer'] -%}
-        {{- messages[0]['content'] | trim -}}
+    {%- if messages and messages[0]['role'] in ['system', 'developer'] -%}
+        {%- if messages[0]['content'] is string -%}
+            {{- messages[0]['content'] | trim -}}
+        {%- elif messages[0]['content'] is sequence -%}
+            {%- for item in messages[0]['content'] -%}
+                {{- item['text'] | trim + ' '-}}
+            {%- endfor -%}
+        {%- endif -%}
         {%- set loop_messages = messages[1:] -%}
     {%- endif -%}
-
     {%- if tools -%}
         {%- for tool in tools %}
             {{- '<|tool>' -}}
@@ -198,7 +212,6 @@
         {%- endfor %}
         {%- set ns.prev_message_type = 'tool' -%}
     {%- endif -%}
-
     {{- '<turn|>\n' -}}
 {%- endif %}
 
@@ -215,31 +228,21 @@
     {%- if message['role'] != 'tool' -%}
     {%- set ns.prev_message_type = None -%}
     {%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}
-    {#- Detect continuation: suppress duplicate <|turn>model when previous non-tool message was also assistant -#}
-    {%- set prev_nt = namespace(role=None, found=false) -%}
-    {%- if loop.index0 > 0 -%}
-        {%- for j in range(loop.index0 - 1, -1, -1) -%}
-            {%- if not prev_nt.found -%}
-                {%- if loop_messages[j]['role'] != 'tool' -%}
-                    {%- set prev_nt.role = loop_messages[j]['role'] -%}
-                    {%- set prev_nt.found = true -%}
-                {%- endif -%}
-            {%- endif -%}
-        {%- endfor -%}
-    {%- endif -%}
-    {%- set continue_same_model_turn = (role == 'model' and prev_nt.role == 'assistant') -%}
+    {#- Detect continuation using tracked state — O(1) instead of O(n) backward scan -#}
+    {%- set continue_same_model_turn = (role == 'model' and ns.prev_non_tool_role == 'assistant') -%}
     {%- if not continue_same_model_turn -%}
         {{- '<|turn>' + role + '\n' }}
     {%- endif -%}
 
     {#- Render reasoning/reasoning_content as thinking channel -#}
     {%- set thinking_text = message.get('reasoning') or message.get('reasoning_content') -%}
-    {%- if thinking_text and loop.index0 > ns_turn.last_user_idx and message.get('tool_calls') -%}
+    {%- set thinking_gate = (loop.index0 > ns_turn.last_user_idx) or (preserve_thinking and message.get('tool_calls')) -%}
+    {%- if thinking_text and thinking_gate -%}
         {{- '<|channel>thought\n' + thinking_text + '\n<channel|>' -}}
     {%- endif -%}
 
-            {%- if message['tool_calls'] -%}
-                {%- for tool_call in message['tool_calls'] -%}
+            {%- if message.get('tool_calls') -%}
+                {%- for tool_call in message.get('tool_calls') -%}
                     {%- set function = tool_call['function'] -%}
                     {{- '<|tool_call>call:' + function['name'] + '{' -}}
                     {%- if function['arguments'] is mapping -%}
@@ -249,8 +252,13 @@
                             {%- set ns_args.found_first = true -%}
                             {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
                         {%- endfor -%}
-                    {%- elif function['arguments'] is string -%}
-                        {{- function['arguments'] -}}
+                    {%- elif function['arguments'] is none -%}
+                    {%- else -%}
+                        {{- raise_exception(
+                            "chat_template: tool_calls[].function.arguments must be a "
+                            "JSON object (mapping), not a string. Deserialize arguments "
+                            "before passing to the template."
+                        ) -}}
                     {%- endif -%}
                     {{- '}<tool_call|>' -}}
                 {%- endfor -%}
@@ -260,8 +268,8 @@
             {%- set ns_tr_out = namespace(flag=false) -%}
             {%- if message.get('tool_responses') -%}
                 {#- Legacy: tool_responses embedded on the assistant message (Google/Gemma native) -#}
-                {%- for tool_response in message['tool_responses'] -%}
-                    {{- format_tool_response_block(tool_response['name'] | default('unknown'), tool_response['response']) -}}
+                {%- for tool_response in message.get('tool_responses') -%}
+                    {{- format_tool_response_block(tool_response['name'] | default('unknown', true), tool_response['response']) -}}
                     {%- set ns_tr_out.flag = true -%}
                     {%- set ns.prev_message_type = 'tool_response' -%}
                 {%- endfor -%}
@@ -275,8 +283,8 @@
                     {%- else -%}
                         {%- set follow = loop_messages[k] -%}
                         {#- Resolve tool_call_id to function name -#}
-                        {%- set ns_tname = namespace(name=follow.get('name') | default('unknown')) -%}
-                        {%- for tc in message['tool_calls'] -%}
+                        {%- set ns_tname = namespace(name=follow.get('name') or 'unknown') -%}
+                        {%- for tc in message.get('tool_calls') -%}
                             {%- if tc.get('id') == follow.get('tool_call_id') -%}
                                 {%- set ns_tname.name = tc['function']['name'] -%}
                             {%- endif -%}
@@ -293,6 +301,15 @@
                                 {%- endif -%}
                             {%- endfor -%}
                             {{- format_tool_response_block(ns_tname.name, ns_txt.s) -}}
+                            {%- for part in tool_body -%}
+                                {%- if part.get('type') in ['image', 'image_url'] -%}
+                                    {{- '<|image|>' -}}
+                                {%- elif part.get('type') in ['audio', 'input_audio'] -%}
+                                    {{- '<|audio|>' -}}
+                                {%- elif part.get('type') == 'video' -%}
+                                    {{- '<|video|>' -}}
+                                {%- endif -%}
+                            {%- endfor -%}
                         {%- else -%}
                             {{- format_tool_response_block(ns_tname.name, tool_body) -}}
                         {%- endif -%}
@@ -302,43 +319,68 @@
                 {%- endfor -%}
             {%- endif -%}
 
-            {%- if message['content'] is string -%}
+            {%- set captured_content -%}
+            {%- if message.get('content') is string -%}
                 {%- if role == 'model' -%}
                     {{- strip_thinking(message['content']) -}}
                 {%- else -%}
                     {{- message['content'] | trim -}}
                 {%- endif -%}
-            {%- elif message['content'] is sequence -%}
+            {%- elif message.get('content') is sequence -%}
                 {%- for item in message['content'] -%}
-                    {%- if item['type'] == 'text' -%}
+                    {%- if item.get('type') == 'text' -%}
                         {%- if role == 'model' -%}
                             {{- strip_thinking(item['text']) -}}
                         {%- else -%}
                             {{- item['text'] | trim -}}
                         {%- endif -%}
-                    {%- elif item['type'] == 'image' -%}
+                    {%- elif item.get('type') in ['image', 'image_url'] -%}
                         {{- '<|image|>' -}}
-                        {%- set ns.prev_message_type = 'image' -%}
-                    {%- elif item['type'] == 'audio' -%}
+                    {%- elif item.get('type') in ['audio', 'input_audio'] -%}
                         {{- '<|audio|>' -}}
-                        {%- set ns.prev_message_type = 'audio' -%}
-                    {%- elif item['type'] == 'video' -%}
+                    {%- elif item.get('type') == 'video' -%}
                         {{- '<|video|>' -}}
-                        {%- set ns.prev_message_type = 'video' -%}
                     {%- endif -%}
                 {%- endfor -%}
             {%- endif -%}
+            {%- endset -%}
+
+            {{- captured_content -}}
+            {%- set has_content = captured_content | trim | length > 0 -%}
+
+        {#- Forward-scan: find next non-tool message role for continuation detection -#}
+        {%- set next_nt = namespace(role=None, found=false) -%}
+        {%- for j in range(loop.index0 + 1, loop_messages | length) -%}
+            {%- if not next_nt.found -%}
+                {%- if loop_messages[j]['role'] != 'tool' -%}
+                    {%- set next_nt.role = loop_messages[j]['role'] -%}
+                    {%- set next_nt.found = true -%}
+                {%- endif -%}
+            {%- endif -%}
+        {%- endfor -%}
+
+        {%- set continues_into_next = (
+            role == 'model'
+            and next_nt.role == 'assistant'
+            and (not message.get('tool_calls') or ns_tr_out.flag)
+        ) -%}
 
         {%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}
             {{- '<|tool_response>' -}}
-        {%- elif not (ns_tr_out.flag and not message.get('content')) -%}
+        {%- elif continues_into_next -%}
+        {%- elif not (ns_tr_out.flag and not has_content and not next_nt.found) -%}
             {{- '<turn|>\n' -}}
         {%- endif -%}
+
+    {#- Track previous non-tool role for next iteration (avoids O(n) backward scan) -#}
+    {%- set ns.prev_non_tool_role = message['role'] -%}
     {%- endif -%}
 {%- endfor -%}
 
 {%- if add_generation_prompt -%}
     {%- if ns.prev_message_type != 'tool_response' and ns.prev_message_type != 'tool_call' -%}
         {{- '<|turn>model\n' -}}
+    {%- elif ns.prev_message_type == 'tool_response' and enable_thinking -%}
+        {{- '<|channel>thought\n' -}}
     {%- endif -%}
-{%- endif -%}
+{%- endif -%}

config.json

@@ -12,10 +12,10 @@
     "attention_logit_cap": 50.0,
     "chunk_size_feed_forward": 0,
     "conv_kernel_size": 5,
-    "dtype": "bfloat16",
+    "dtype": "float32",
     "gradient_clipping": 10000000000.0,
     "hidden_act": "silu",
-    "hidden_size": 8,
+    "hidden_size": 32,
     "id2label": {
       "0": "LABEL_0",
       "1": "LABEL_1"
@@ -27,11 +27,11 @@
       "LABEL_1": 1
     },
     "model_type": "gemma4_audio",
-    "num_attention_heads": 2,
+    "num_attention_heads": 4,
     "num_hidden_layers": 1,
     "output_attentions": false,
     "output_hidden_states": false,
-    "output_proj_dims": 8,
+    "output_proj_dims": 32,
     "problem_type": null,
     "residual_weight": 0.5,
     "return_dict": true,
@@ -66,13 +66,13 @@
     "eos_token_id": 1,
     "expert_intermediate_size": null,
     "final_logit_softcapping": 30.0,
-    "global_head_dim": 4,
-    "head_dim": 4,
+    "global_head_dim": 8,
+    "head_dim": 8,
     "hidden_activation": "gelu_pytorch_tanh",
-    "hidden_size": 8,
+    "hidden_size": 32,
     "hidden_size_per_layer_input": 1,
     "initializer_range": 0.02,
-    "intermediate_size": 32,
+    "intermediate_size": 64,
     "layer_types": [
       "sliding_attention",
       "full_attention",
@@ -81,11 +81,11 @@
     "max_position_embeddings": 131072,
     "model_type": "gemma4_text",
     "moe_intermediate_size": null,
-    "num_attention_heads": 2,
+    "num_attention_heads": 4,
     "num_experts": null,
     "num_global_key_value_heads": null,
     "num_hidden_layers": 3,
-    "num_key_value_heads": 1,
+    "num_key_value_heads": 2,
     "num_kv_shared_layers": 1,
     "pad_token_id": 0,
     "rms_norm_eps": 1e-06,
@@ -119,17 +119,17 @@
     "attention_dropout": 0.0,
     "chunk_size_feed_forward": 0,
     "default_output_length": 70,
-    "dtype": "bfloat16",
+    "dtype": "float32",
     "global_head_dim": 64,
-    "head_dim": 4,
+    "head_dim": 8,
     "hidden_activation": "gelu_pytorch_tanh",
-    "hidden_size": 8,
+    "hidden_size": 32,
     "id2label": {
       "0": "LABEL_0",
       "1": "LABEL_1"
     },
     "initializer_range": 0.02,
-    "intermediate_size": 32,
+    "intermediate_size": 64,
     "is_encoder_decoder": false,
     "label2id": {
       "LABEL_0": 0,
@@ -137,12 +137,12 @@
     },
     "max_position_embeddings": 131072,
     "model_type": "gemma4_vision",
-    "num_attention_heads": 2,
+    "num_attention_heads": 4,
     "num_hidden_layers": 1,
-    "num_key_value_heads": 2,
+    "num_key_value_heads": 4,
     "output_attentions": false,
     "output_hidden_states": false,
-    "patch_size": 2,
+    "patch_size": 16,
     "pooling_kernel_size": 3,
     "position_embedding_size": 10240,
     "problem_type": null,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:feaf3cfe37e063524c5a46b94a145b50aeb7ea07d6b983070dda965ed0248c86
-size 11997808
+oid sha256:c2645ac53c3989c11a75141407c3016e1c732a38eb306ea75fb9b53d7b64b191
+size 40017352

processor_config.json

@@ -13,7 +13,7 @@
     "max_frequency": 8000.0,
     "mel_floor": 0.001,
     "min_frequency": 0.0,
-    "padding_side": "right",
+    "padding_side": "left",
     "padding_value": 0.0,
     "per_bin_mean": null,
     "per_bin_stddev": null,
@@ -33,23 +33,19 @@
       0.0
     ],
     "image_processor_type": "Gemma4ImageProcessor",
-    "image_seq_length": 70,
+    "image_seq_length": 280,
     "image_std": [
       1.0,
       1.0,
       1.0
     ],
-    "max_soft_tokens": 70,
-    "patch_size": 2,
+    "max_soft_tokens": 280,
+    "patch_size": 16,
     "pooling_kernel_size": 3,
     "resample": 3,
-    "rescale_factor": 0.00392156862745098,
-    "size": {
-      "height": 32,
-      "width": 32
-    }
+    "rescale_factor": 0.00392156862745098
   },
-  "image_seq_length": 70,
+  "image_seq_length": 280,
   "processor_class": "Gemma4Processor",
   "video_processor": {
     "do_convert_rgb": true,
@@ -69,7 +65,7 @@
     ],
     "max_soft_tokens": 70,
     "num_frames": 32,
-    "patch_size": 2,
+    "patch_size": 16,
     "pooling_kernel_size": 3,
     "resample": 3,
     "rescale_factor": 0.00392156862745098,

tokenizer_config.json

@@ -84,6 +84,52 @@
     "type": "object",
     "x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?P<content>(?:(?!\\<turn\\|\\>)(?!\\<\\|tool_response\\>).)+)?(?:\\<turn\\|\\>|\\<\\|tool_response\\>)?"
   },
+  "response_template": {
+    "defaults": {
+      "role": "assistant"
+    },
+    "fields": {
+      "content": {
+        "close": [
+          "<turn|>",
+          "<|tool_response>",
+          "<eos>"
+        ],
+        "content": "text"
+      },
+      "thinking": {
+        "close": "<channel|>",
+        "content": "text",
+        "open": "<|channel>thought\n"
+      },
+      "tool_calls": {
+        "close": "<tool_call|>",
+        "content": "json",
+        "content_args": {
+          "string_delims": [
+            [
+              "<|\"|>",
+              "<|\"|>"
+            ]
+          ],
+          "unquoted_keys": true
+        },
+        "open_pattern": "<\\|tool_call>call:(?P<name>\\w+)",
+        "repeats": true,
+        "transform": {
+          "function": {
+            "arguments": "{content}",
+            "name": "{name}"
+          },
+          "type": "function"
+        }
+      }
+    },
+    "start_anchor": [
+      "<|turn>model\n",
+      "<tool_response|>"
+    ]
+  },
   "soc_token": "<|channel>",
   "sot_token": "<|turn>",
   "stc_token": "<|tool_call>",
@@ -91,5 +137,6 @@
   "str_token": "<|tool_response>",
   "think_token": "<|think|>",
   "tokenizer_class": "GemmaTokenizer",
+  "truncation_side": "left",
   "unk_token": "<unk>"
 }