Update tiny models for InklingModel

.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 +1,129 @@
+{%- set effort_map = {"none": 0.0, "minimal": 0.1, "low": 0.2, "medium": 0.7, "high": 0.9, "max": 0.99} -%}
+{%- set role_token = {"user": "<|message_user|>", "assistant": "<|message_model|>", "system": "<|message_system|>", "tool": "<|message_tool|>"} -%}
+
+{%- macro emit_thinking_effort() -%}
+    {%- set eff = reasoning_effort if reasoning_effort is defined and reasoning_effort is not none else 0.9 -%}
+    {%- if eff is string -%}
+        {%- set key = eff | trim -%}
+        {%- if key not in effort_map -%}
+            {{- raise_exception("Unknown reasoning_effort: " ~ eff) -}}
+        {%- endif -%}
+        {%- set num = effort_map[key] -%}
+    {%- else -%}
+        {%- set num = eff | float -%}
+    {%- endif -%}
+    {%- if num < 0.0 or num > 0.99 -%}
+        {{- raise_exception("reasoning_effort must be in [0.0, 0.99]") -}}
+    {%- endif -%}
+    {{- "<|message_system|><|content_text|>Thinking effort level: " -}}
+    {%- if num == 0.0 -%}0{%- else -%}{{ num }}{%- endif -%}
+    {{- "<|end_message|>" -}}
+{%- endmacro -%}
+
+{%- if tools -%}
+    {%- set tool_state = namespace(specs=[]) -%}
+    {%- for tool in tools -%}
+        {%- set fn = tool.function if tool.function is defined else tool -%}
+        {%- set spec = {
+            "description": (fn.description if fn.description is defined and fn.description else ""),
+            "name": fn.name,
+            "parameters": (fn.parameters if fn.parameters is defined and fn.parameters else {}),
+            "type": (tool.type if tool.type is defined and tool.type else "function"),
+        } -%}
+        {%- set tool_state.specs = tool_state.specs + [spec] -%}
+    {%- endfor -%}
+    {{- "<|message_system|>tool_declare<|content_xml|>" -}}
+    {{- tool_state.specs | tojson(sort_keys=true, separators=(",", ":")) -}}
+    {{- "<|end_message|>" -}}
+{%- endif -%}
+
+{%- set state = namespace(effort_emitted=false) -%}
+{%- for message in messages -%}
+    {%- if message.role not in role_token -%}
+        {{- raise_exception("Unknown message role: " ~ message.role) -}}
+    {%- endif -%}
+    {%- if not state.effort_emitted and message.role != "system" -%}
+        {{- emit_thinking_effort() -}}
+        {%- set state.effort_emitted = true -%}
+    {%- endif -%}
+
+    {%- set rtok = role_token[message.role] -%}
+
+    {%- if message.role == "tool" -%}
+        {%- set tool_name_state = namespace(name="") -%}
+        {%- if message.name is defined and message.name -%}
+            {%- set tool_name_state.name = message.name -%}
+        {%- elif message.tool_call_id is defined and message.tool_call_id -%}
+            {%- for prev in messages -%}
+                {%- if prev.role == "assistant" and prev.tool_calls -%}
+                    {%- for tc in prev.tool_calls -%}
+                        {%- if tc.id is defined and tc.id == message.tool_call_id and tc.function.name is defined -%}
+                            {%- set tool_name_state.name = tc.function.name -%}
+                        {%- endif -%}
+                    {%- endfor -%}
+                {%- endif -%}
+            {%- endfor -%}
+        {%- endif -%}
+        {{- rtok -}}
+        {%- if tool_name_state.name -%}{{- tool_name_state.name -}}{%- endif -%}
+        {{- "<|content_text|>" -}}
+        {%- if message.content is string -%}{{- message.content -}}{%- endif -%}
+        {{- "<|end_message|>" -}}
+
+    {%- else -%}
+        {%- if message.role == "assistant" and message.reasoning_content is defined and message.reasoning_content -%}
+            {{- "<|message_model|><|content_thinking|>" ~ message.reasoning_content ~ "<|end_message|>" -}}
+        {%- endif -%}
+
+        {%- if message.content is string -%}
+            {{- rtok ~ "<|content_text|>" ~ message.content ~ "<|end_message|>" -}}
+        {%- elif message.content -%}
+            {%- for part in message.content -%}
+                {%- if part is string -%}
+                    {{- rtok ~ "<|content_text|>" ~ part ~ "<|end_message|>" -}}
+                {%- elif part.type is not defined or part.type in ("text", "input_text") -%}
+                    {%- set text_part = (part.text if part.text is defined and part.text is string else "") -%}
+                    {{- rtok ~ "<|content_text|>" ~ text_part ~ "<|end_message|>" -}}
+                {%- elif part.type in ("image", "input_image", "image_url") -%}
+                    {{- rtok ~ "<|content_image|><|unused_200054|><|end_message|>" -}}
+                {%- elif part.type in ("audio", "input_audio", "audio_url") -%}
+                    {{- rtok ~ "<|content_audio_input|><|unused_200053|><|audio_end|><|end_message|>" -}}
+                {%- else -%}
+                    {{- raise_exception("Unsupported content part type: " ~ part.type) -}}
+                {%- endif -%}
+            {%- endfor -%}
+        {%- endif -%}
+
+        {%- if message.role == "assistant" and message.tool_calls -%}
+            {%- for tc in message.tool_calls -%}
+                {%- set fn = tc.function -%}
+                {%- if fn.name is not defined or fn.name is not string -%}
+                    {{- raise_exception("tool call function name must be a string") -}}
+                {%- endif -%}
+                {%- set args = fn.arguments if fn.arguments is defined and fn.arguments else {} -%}
+                {%- if args is string -%}
+                    {{- raise_exception("tool call arguments must be a parsed object, not a JSON string; canonicalize upstream") -}}
+                {%- endif -%}
+                {%- if args is not mapping -%}
+                    {{- raise_exception("tool call arguments must be an object") -}}
+                {%- endif -%}
+                {{- "<|message_model|>" ~ fn.name ~ "<|content_invoke_tool_json|>" -}}
+                {{- '{"name":' ~ (fn.name | tojson(sort_keys=true, separators=(",", ":"))) ~ ',"args":' -}}
+                {{- (args | tojson(sort_keys=true, separators=(",", ":"))) -}}
+                {{- "}<|end_message|>" -}}
+            {%- endfor -%}
+        {%- endif -%}
+
+        {%- if message.role == "assistant" -%}
+            {{- "<|content_model_end_sampling|>" -}}
+        {%- endif -%}
+    {%- endif -%}
+{%- endfor -%}
+
+{%- if not state.effort_emitted -%}
+    {{- emit_thinking_effort() -}}
+{%- endif -%}
+
+{%- if add_generation_prompt -%}
+    {{- "<|message_model|>" -}}
+{%- endif -%}

config.json

@@ -0,0 +1,86 @@
+{
+  "architectures": [
+    "InklingModel"
+  ],
+  "audio_bos_token_id": 200020,
+  "audio_config": {
+    "initializer_range": 0.02,
+    "mel_vocab_size": 8,
+    "model_type": "inkling_audio",
+    "n_mel_bins": 4,
+    "rms_norm_eps": 1e-06,
+    "text_hidden_size": 32
+  },
+  "audio_token_id": 7,
+  "boi_token_id": 5,
+  "dtype": "float32",
+  "eoi_token_id": 6,
+  "image_bos_token_id": 200005,
+  "image_token_id": 4,
+  "model_type": "inkling_mm_model",
+  "num_hidden_layers": 2,
+  "text_config": {
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "chain_hidden_post_norm": false,
+    "conv_kernel_size": 4,
+    "d_rel": 16,
+    "eos_token_id": 2,
+    "head_dim": 16,
+    "hidden_act": "gelu",
+    "hidden_size": 32,
+    "initializer_range": 0.02,
+    "intermediate_size": 32,
+    "layer_types": [
+      "hybrid_sliding",
+      "hybrid"
+    ],
+    "local_layer_ids": null,
+    "log_scaling_alpha": 0.1,
+    "log_scaling_n_floor": null,
+    "logits_mup_width_multiplier": 24.0,
+    "max_position_embeddings": 512,
+    "mlp_layer_types": [
+      "dense",
+      "sparse"
+    ],
+    "model_type": "inkling_text",
+    "moe_intermediate_size": 16,
+    "mtp_hidden_states_first": true,
+    "mtp_local_layer_ids": null,
+    "n_routed_experts": 256,
+    "n_shared_experts": 2,
+    "num_attention_heads": 2,
+    "num_experts_per_tok": 2,
+    "num_hidden_layers": 2,
+    "num_key_value_heads": 2,
+    "num_mtp_layers": null,
+    "number_of_conv_states": 4,
+    "pad_token_id": 0,
+    "rel_extent": 1024,
+    "rms_norm_eps": 1e-06,
+    "rms_norm_eps_moe_gate": 1e-06,
+    "route_scale": 8.0,
+    "shared_expert_sink": true,
+    "sliding_window_size": 512,
+    "swa_head_dim": 16,
+    "swa_num_attention_heads": 2,
+    "swa_num_key_value_heads": 2,
+    "unpadded_vocab_size": null,
+    "vocab_size": 200058
+  },
+  "transformers_version": "5.16.0.dev0",
+  "video_token_id": 10,
+  "vision_config": {
+    "hidden_size": 1024,
+    "initializer_range": 0.02,
+    "model_type": "inkling_vision",
+    "n_layers": 2,
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "patch_size": 5,
+    "rms_norm_eps": 1e-06,
+    "temporal_patch_size": 2,
+    "text_hidden_size": 32
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c1089de7d662fcfa4e9755668680387b16a13787472f7e2c7d523f1038dc053
+size 27464520

preprocessor_config.json

@@ -0,0 +1,13 @@
+{
+  "audio_token_duration_s": 0.05,
+  "feature_extractor_type": "InklingFeatureExtractor",
+  "feature_size": 80,
+  "hop_length": 800,
+  "n_fft": 1600,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000,
+  "window_size": 1600,
+  "window_size_multiplier": 2.0
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c470271fb7649eef922e660e757b5f076e2a94adc20df7fad7df85c46bc48eac
+size 27875796

tokenizer_config.json

@@ -0,0 +1,47 @@
+{
+  "audio": "<|audio|>",
+  "audio_end": "<|audio_end|>",
+  "backend": "tokenizers",
+  "begin_of_text": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": false,
+  "content_audio_input": "<|content_audio_input|>",
+  "content_image": "<|content_image|>",
+  "content_invoke_tool_json": "<|content_invoke_tool_json|>",
+  "content_invoke_tool_text": "<|content_invoke_tool_text|>",
+  "content_model_end_sampling": "<|content_model_end_sampling|>",
+  "content_text": "<|content_text|>",
+  "content_thinking": "<|content_thinking|>",
+  "content_tool_error": "<|content_tool_error|>",
+  "content_xml": "<|content_xml|>",
+  "end_message": "<|end_message|>",
+  "endoftext": "<|endoftext|>",
+  "fix_mistral_regex": false,
+  "is_local": true,
+  "local_files_only": false,
+  "message_model": "<|message_model|>",
+  "message_system": "<|message_system|>",
+  "message_tool": "<|message_tool|>",
+  "message_user": "<|message_user|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "audio": "<|audio|>",
+    "audio_end": "<|audio_end|>",
+    "begin_of_text": "<|begin_of_text|>",
+    "content_audio_input": "<|content_audio_input|>",
+    "content_image": "<|content_image|>",
+    "content_invoke_tool_json": "<|content_invoke_tool_json|>",
+    "content_invoke_tool_text": "<|content_invoke_tool_text|>",
+    "content_model_end_sampling": "<|content_model_end_sampling|>",
+    "content_text": "<|content_text|>",
+    "content_thinking": "<|content_thinking|>",
+    "content_tool_error": "<|content_tool_error|>",
+    "content_xml": "<|content_xml|>",
+    "end_message": "<|end_message|>",
+    "endoftext": "<|endoftext|>",
+    "message_model": "<|message_model|>",
+    "message_system": "<|message_system|>",
+    "message_tool": "<|message_tool|>",
+    "message_user": "<|message_user|>"
+  },
+  "tokenizer_class": "TokenizersBackend"
+}