Update tiny models for Kimi_K25VisionModel

.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 +1,112 @@
+{%- macro render_content(msg) -%}
+    {%- set c = msg.get('content') -%}
+    {%- if c is string -%}
+      {{ c }}
+    {%- elif c is not none -%}
+      {% for content in c -%}
+        {% if content['type'] == 'image' or content['type'] == 'image_url' -%}
+          <|media_begin|>image<|media_content|><|media_pad|><|media_end|>
+        {% elif content['type'] == 'video' or content['type']== 'video_url'-%}
+          <|kimi_k25_video_placeholder|>
+        {% else -%}
+          {{ content['text'] }}
+        {%- endif -%}
+      {%- endfor -%}
+    {%- endif -%}
+{%- endmacro -%}
+
+{% macro set_roles(message) -%}
+  {%- set role_name =  message.get('name') or  message['role'] -%}
+  {%- if message['role'] == 'user' -%}
+    <|im_user|>{{role_name}}<|im_middle|>
+  {%- elif message['role'] == 'assistant' -%}
+    <|im_assistant|>{{role_name}}<|im_middle|>
+  {%- else -%}
+    <|im_system|>{{role_name}}<|im_middle|>
+  {%- endif -%}
+{%- endmacro -%}
+
+
+{%- macro render_toolcalls(message) -%}
+  <|tool_calls_section_begin|>
+  {%- for tool_call in message['tool_calls'] -%}
+    {%- set formatted_id = tool_call['id'] -%}
+    <|tool_call_begin|>{{ formatted_id }}<|tool_call_argument_begin|>{% if tool_call['function']['arguments'] is string %}{{ tool_call['function']['arguments'] }}{% else %}{{ tool_call['function']['arguments'] | tojson }}{% endif %}<|tool_call_end|>
+  {%- endfor -%}
+  <|tool_calls_section_end|>
+{%- endmacro -%}
+
+
+{%- set preserve_thinking = preserve_thinking | default(false) -%}
+{# Find last non-tool-call assistant message. If preserve_thinking, keep -1 so hist is empty and all msgs use suffix (retain reasoning). #}
+{%- set ns = namespace(last_non_tool_call_assistant_msg=-1) -%}
+{%- if not preserve_thinking -%}
+{%- for idx in range(messages|length-1, -1, -1) -%}
+    {%- if messages[idx]['role'] == 'assistant' and not messages[idx].get('tool_calls') -%}
+        {%- set ns.last_non_tool_call_assistant_msg = idx -%}
+        {%- break -%}
+    {%- endif -%}
+{%- endfor -%}
+{%- endif -%}
+
+{# split all messages into history & suffix, reasoning_content in suffix should be reserved.#}
+{%- set hist_msgs = messages[:ns.last_non_tool_call_assistant_msg+1] -%}
+{%- set suffix_msgs = messages[ns.last_non_tool_call_assistant_msg+1:] -%}
+
+{%- if tools -%}
+  {%- if tools_ts_str -%}
+    <|im_system|>tool_declare<|im_middle|>{{ tools_ts_str }}<|im_end|>
+  {%- else -%}
+    <|im_system|>tool_declare<|im_middle|>{{ tools | tojson(separators=(',', ':')) }}<|im_end|>
+  {%- endif -%}
+{%- endif -%}
+
+  
+{%- for message in hist_msgs -%}
+  {{set_roles(message)}}
+  {%- if message['role'] == 'assistant' -%}
+    <think></think>{{render_content(message)}}
+    {%- if message.get('tool_calls') -%}
+      {{render_toolcalls(message)}}
+    {%- endif -%}
+  {%- elif message['role'] == 'tool' -%}
+    {%- set tool_call_id = message.tool_call_id -%}
+    ## Return of {{ tool_call_id }}
+{{render_content(message)}}
+  {%- elif message['content'] is not none -%}
+    {{render_content(message)}}
+  {%- endif -%}
+  <|im_end|>
+{%- endfor -%}
+
+{%- for message in suffix_msgs -%}
+  {{set_roles(message)}}
+  {%- if message['role'] == 'assistant' -%}
+    {%- if thinking is defined and thinking is false and preserve_thinking is false -%}
+    <think></think>{{render_content(message)}}
+    {%- else -%}
+    {%- set rc = message.get('reasoning', message.get('reasoning_content', '')) -%}
+    <think>{{rc}}</think>{{render_content(message)}}
+    {%- endif -%}
+    {%- if message.get('tool_calls') -%}
+     {{render_toolcalls(message)}}
+    {%- endif -%}
+  {%- elif message['role'] == 'tool' -%}
+    {%- set tool_call_id = message.tool_call_id -%}
+    ## Return of {{ tool_call_id }}
+{{render_content(message)}}
+  {%- elif message['content'] is not none -%}
+    {{render_content(message)}}
+  {%- endif -%}
+  <|im_end|>
+{%- endfor -%}
+
+
+{%- if add_generation_prompt -%}
+  <|im_assistant|>assistant<|im_middle|>
+  {%- if thinking is defined and thinking is false -%}
+  <think></think>
+  {%- else -%}
+  <think>
+  {%- endif -%}
+{%- endif -%}

config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "Kimi_K25VisionModel"
+  ],
+  "dtype": "float32",
+  "hidden_act": "silu",
+  "hidden_size": 32,
+  "intermediate_size": 32,
+  "max_position_embeddings": 512,
+  "merge_kernel_size": [
+    1,
+    1
+  ],
+  "model_type": "kimi_k25_vision",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "patch_size": 8,
+  "pos_emb_height": 4,
+  "pos_emb_time": 1,
+  "pos_emb_width": 4,
+  "rope_parameters": {
+    "rope_theta": 10000,
+    "rope_type": "default"
+  },
+  "transformers_version": "5.16.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f80b778402189fa868f786ed061a311a73029c13495c4ad2788f2e3acfc372e1
+size 81912

preprocessor_config.json

@@ -0,0 +1,54 @@
+{
+  "auto_map": {
+    "AutoImageProcessor": "kimi_k25_vision_processing.KimiK25VisionProcessor",
+    "AutoProcessor": "kimi_k25_processor.KimiK25Processor"
+  },
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Kimi_K25ImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "max_patches": 16384,
+  "media_proc_cfg": {
+    "config_type": "media_proc.processors.moonvit.MoonViTMediaProcessorConfig",
+    "fixed_output_tokens": null,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "in_patch_limit": 16384,
+    "in_patch_limit_each_frame": 4096,
+    "in_patch_limit_video": null,
+    "max_num_frames_each_video": null,
+    "merge_kernel_size": 2,
+    "patch_limit_on_one_side": 512,
+    "patch_size": 14,
+    "sample_fps": 2.0,
+    "temporal_merge_kernel_size": 4,
+    "timestamp_mode": "hh:mm:ss.fff"
+  },
+  "merge_size": 2,
+  "patch_size": 14,
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "max_height": 512,
+    "max_width": 512
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:261590fd5234433c558e867ea7d9b8d8a29ebc6bf51d9d43a9d714e4793db0e9
+size 19545255

tokenizer_config.json

@@ -0,0 +1,18 @@
+{
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_kimi.TikTokenTokenizer",
+      null
+    ]
+  },
+  "backend": "tokenizers",
+  "bos_token": "[BOS]",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "[EOS]",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "[UNK]"
+}

video_preprocessor_config.json

@@ -0,0 +1,58 @@
+{
+  "auto_map": {
+    "AutoImageProcessor": "kimi_k25_vision_processing.KimiK25VisionProcessor",
+    "AutoProcessor": "kimi_k25_processor.KimiK25Processor"
+  },
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_sample_frames": true,
+  "fps": 2,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "max_patches": 4096,
+  "media_proc_cfg": {
+    "config_type": "media_proc.processors.moonvit.MoonViTMediaProcessorConfig",
+    "fixed_output_tokens": null,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "in_patch_limit": 16384,
+    "in_patch_limit_each_frame": 4096,
+    "in_patch_limit_video": null,
+    "max_num_frames_each_video": null,
+    "merge_kernel_size": 2,
+    "patch_limit_on_one_side": 512,
+    "patch_size": 14,
+    "sample_fps": 2.0,
+    "temporal_merge_kernel_size": 4,
+    "timestamp_mode": "hh:mm:ss.fff"
+  },
+  "merge_size": 2,
+  "patch_size": 14,
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_metadata": false,
+  "size": {
+    "max_height": 512,
+    "max_width": 512
+  },
+  "temporal_patch_size": 4,
+  "video_processor_type": "Kimi_K25VideoProcessor"
+}