Upload talker checkpoint 9500 with inference config and tokenizer

.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

README.md

@@ -0,0 +1,46 @@
+---
+language:
+  - en
+  - zh
+tags:
+  - speech-to-speech
+  - full-duplex
+  - awaken-chat
+pipeline_tag: audio-to-audio
+---
+# Awaken Chat — talker checkpoint 9500
+
+Full-duplex speech-to-speech checkpoint from `podcast-talker-v3-micro-b64-2ep/checkpoint-9500`.
+Weights are the original checkpoint shards. A model-weight license has not been specified;
+the inference code repository's Apache-2.0 license does not establish the license of these weights.
+
+## Load with the inference repository
+
+Use [OpenmartAI/awake-audio-chat](https://github.com/OpenmartAI/awake-audio-chat),
+with its documented CUDA / PyTorch dependencies and Transformers 4.52.x:
+
+```python
+from awaken_chat import load_model
+
+loaded = load_model("openmartdev/awaken-full-duplex")
+```
+
+```bash
+awaken-server --model openmartdev/awaken-full-duplex --port 8998
+```
+
+The weights require `AwakenModel` from that repository. Generic Transformers
+`AutoModel.from_pretrained` is not a supported loading path for this prepared directory.
+The server separately downloads CosyVoice3 `flow.pt`, `hift.pt` and the ONNX estimator
+from `FunAudioLLM/Fun-CosyVoice3-0.5B-2512`; GPU-specific TensorRT plans are built locally.
+Optional voice prompts are distributed with the inference repository.
+
+## Contents and provenance
+
+Eight safetensors shards, their index, the tokenizer files, and the inference config are
+included. Config normalization selects `AwakenModel` and the duplex `add` fusion mode,
+matching `load_model`. Source weights and tokenizer are unchanged. See `provenance.json`.
+Training arguments, trainer logs, credentials, codec binaries and TensorRT plans are excluded.
+
+The `grpo-160` checkpoint used for initial service validation is a separate checkpoint;
+its results do not establish the speech quality of this talker checkpoint.

SHA256SUMS

@@ -0,0 +1,20 @@
+640ff085676e2299e365c88e1204fdd574ecdcbd318109c73958364036be613f  README.md
+0804bb76dd9f73fedd1cd3583c1a53046640c493fe5aaf6cf5cd8835118534e5  added_tokens.json
+40c21f34cf67d8c760ef72f8ad3ae5afad514299d4b06e91dd9a8d705af7b541  chat_template.jinja
+6eb285078bee24c37d21ea43df4cfe91187dad9eaf0c3015a6d3258edd981dc4  config.json
+8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5  merges.txt
+80afe4af73eff1a18e1b766d3fb5a1a34616fa823c550ce9cc1c691a1eced8f5  model-00001-of-00008.safetensors
+5f94b6f57b7fcb3cfd783604f452e4b3e6e1f82ff7ee6e5c746c86e746817639  model-00002-of-00008.safetensors
+8d909715b4b944153d80145695a1a182ba897512e8928d0ce18648e1542ed82d  model-00003-of-00008.safetensors
+3f6072a5c35a6e521e9c1c0d1b7beca7f64da8c0534accb0ec46a256e243efff  model-00004-of-00008.safetensors
+f7a3e8e642c27ab44978ae837ef73ceb3ee98c2241a479e8ab0b4bd16f7356d0  model-00005-of-00008.safetensors
+9755906addbfb718090621b60f782cc95556a9a181242f7ad9d1b385d3b45069  model-00006-of-00008.safetensors
+81aa33b8f6a9fe8959861652646dab16fb7bd4f31b21a31090fffe869a88faf0  model-00007-of-00008.safetensors
+f94a24caa08ccfaa103ae8566fc6d25e55d1029949a62272d96399b85013c3a4  model-00008-of-00008.safetensors
+4839ae2ed5ddf4d669ac07c3edc7df8e0d2c4dd5e7c5c0f05b75081b1076e5af  model.safetensors.index.json
+1384e936235c4fb9cd2be9f7e4e2070bccb4f7653a46109697d87f871552a2c8  preprocessor_config.json
+44e287ce1c17ed72eda382f1ea94320126d47d1ff64aca62146d8b65093c1691  provenance.json
+48db01c939e1bfde55b513e5c21f99372064755284d2f9ca16351c5a5ee5245f  special_tokens_map.json
+7a7d58d42d29ac0776a3d5a6e6746fb0fe79dfe65fafa947f3dd76da528a02fe  tokenizer.json
+6ca0f406138828fa8372b22f9df5788621cdd62c8030b0e7aac94645a153e47f  tokenizer_config.json
+ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910  vocab.json

added_tokens.json

@@ -0,0 +1,33 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|AUDIO|>": 151669,
+  "<|audio_bos|>": 151670,
+  "<|audio_eos|>": 151671,
+  "<|audio_pad|>": 151672,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|sil|>": 151673,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,86 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,89 @@
+{
+  "architectures": [
+    "AwakenModel"
+  ],
+  "audio_config": {
+    "activation_function": "gelu",
+    "bos_token_id": 6561,
+    "codebook_size": 6565,
+    "continuous_features_mode": "add",
+    "crq_transformer_config": {
+      "architectures": [
+        "Qwen3ForCausalLM"
+      ],
+      "attention_bias": false,
+      "attention_dropout": 0.0,
+      "bos_token_id": 151643,
+      "eos_token_id": 151643,
+      "head_dim": 128,
+      "hidden_act": "silu",
+      "hidden_size": 1024,
+      "initializer_range": 0.02,
+      "intermediate_size": 3072,
+      "max_position_embeddings": 32768,
+      "max_window_layers": 28,
+      "model_type": "qwen3",
+      "num_attention_heads": 16,
+      "num_hidden_layers": 28,
+      "num_key_value_heads": 8,
+      "rms_norm_eps": 1e-06,
+      "rope_scaling": null,
+      "rope_theta": 1000000,
+      "sliding_window": null,
+      "tie_word_embeddings": true,
+      "torch_dtype": "bfloat16",
+      "transformers_version": "4.51.0",
+      "use_cache": true,
+      "use_sliding_window": false,
+      "vocab_size": 151936
+    },
+    "d_model": 1280,
+    "encoder_attention_heads": 20,
+    "encoder_ffn_dim": 5120,
+    "encoder_layers": 32,
+    "eos_token_id": 6562,
+    "group_size": 5,
+    "max_source_positions": 1500,
+    "model_type": "awaken_chat_audio",
+    "num_mel_bins": 128,
+    "output_dim": 4096,
+    "pad_token_id": 6563,
+    "torch_dtype": "float32"
+  },
+  "hidden_size": 4096,
+  "model_type": "awaken_chat",
+  "text_config": {
+    "architectures": [
+      "Qwen3ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "audio_bos_index": 151670,
+    "audio_eos_index": 151671,
+    "bos_token_id": 151643,
+    "eos_token_id": 151643,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 12288,
+    "max_position_embeddings": 262144,
+    "max_window_layers": 28,
+    "model_type": "qwen3",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 36,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": null,
+    "rope_theta": 5000000,
+    "sil_index": 151673,
+    "sliding_window": null,
+    "torch_dtype": "float32",
+    "use_cache": false,
+    "use_sliding_window": false,
+    "vocab_size": 151936
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "use_cache": false
+}

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80afe4af73eff1a18e1b766d3fb5a1a34616fa823c550ce9cc1c691a1eced8f5
+size 4934152408

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f94b6f57b7fcb3cfd783604f452e4b3e6e1f82ff7ee6e5c746c86e746817639
+size 4972454976

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d909715b4b944153d80145695a1a182ba897512e8928d0ce18648e1542ed82d
+size 4832049608

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f6072a5c35a6e521e9c1c0d1b7beca7f64da8c0534accb0ec46a256e243efff
+size 4832049656

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7a3e8e642c27ab44978ae837ef73ceb3ee98c2241a479e8ab0b4bd16f7356d0
+size 4999856656

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9755906addbfb718090621b60f782cc95556a9a181242f7ad9d1b385d3b45069
+size 4832049680

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81aa33b8f6a9fe8959861652646dab16fb7bd4f31b21a31090fffe869a88faf0
+size 4832049672

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f94a24caa08ccfaa103ae8566fc6d25e55d1029949a62272d96399b85013c3a4
+size 3462482968

preprocessor_config.json

@@ -0,0 +1,14 @@
+{
+  "chunk_length": 300,
+  "dither": 0.0,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 128,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 4800000,
+  "nb_max_frames": 30000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

provenance.json

@@ -0,0 +1,50 @@
+{
+  "checkpoint": "podcast-talker-v3-micro-b64-2ep/checkpoint-9500",
+  "source": "s3://avera-podcasts-data/paper_pack_20261102/ckpts/podcast-talker-v3-micro-b64-2ep__checkpoint-9500.tar",
+  "source_archive_sha256": "bc7c9e14e670220d0baadfa996f8d26209a1e2085a1d4388369059b641f5b13d",
+  "source_config_sha256": "1d2a003ad72a278be77d5f4006c61b5ed537164fc582a02243e45420f8208d2c",
+  "weights": "Unmodified source checkpoint shards (hard links in this local staging tree).",
+  "inference_repository": {
+    "repository": "https://github.com/OpenmartAI/awake-audio-chat",
+    "pr": "https://github.com/OpenmartAI/awake-audio-chat/pull/1",
+    "head_sha": "3b3e7886864912a9095b1832ea86128aa6c45dae",
+    "branch": "feat/web-client"
+  },
+  "config_changes": {
+    "model_type": "awaken_chat",
+    "architectures": [
+      "AwakenModel"
+    ],
+    "audio_config.model_type": "awaken_chat_audio",
+    "audio_config.continuous_features_mode": "add",
+    "normalization": "Serialized by the inference repository AwakenConfig; training-only fields removed."
+  },
+  "codec": {
+    "repo_id": "FunAudioLLM/Fun-CosyVoice3-0.5B-2512",
+    "revision": "29e01c4e8d000f4bcd70751be16fa94bf3d85a18",
+    "files": [
+      {
+        "name": "README.md",
+        "size": 11982,
+        "sha256": null
+      },
+      {
+        "name": "flow.decoder.estimator.fp32.onnx",
+        "size": 1326216933,
+        "sha256": "9b51b9533a55937762b262bf2cf9c6220ce40760f76d6532cb16a6a6d84059a8"
+      },
+      {
+        "name": "flow.pt",
+        "size": 1329116148,
+        "sha256": "a6fab32a7825e5b0bc855ddd948f8db9370b0a786fbc249caa4595e95b608e4b"
+      },
+      {
+        "name": "hift.pt",
+        "size": 83202622,
+        "sha256": "b279d7641eb97ae55b3b540cfba4f953c26492a2df758328a89a4d007ab87a65"
+      }
+    ]
+  },
+  "release_status": "Uploaded to https://huggingface.co/openmartdev/awaken-full-duplex",
+  "hub_repository": "openmartdev/awaken-full-duplex"
+}

special_tokens_map.json

@@ -0,0 +1,41 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>",
+    "<|AUDIO|>",
+    "<|audio_bos|>",
+    "<|audio_eos|>",
+    "<|audio_pad|>",
+    "<|sil|>"
+  ],
+  "audio_bos_token": "<|audio_bos|>",
+  "audio_eos_token": "<|audio_eos|>",
+  "audio_pad_token": "<|audio_pad|>",
+  "audio_token": "<|AUDIO|>",
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "text_sil_token": "<|sil|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a7d58d42d29ac0776a3d5a6e6746fb0fe79dfe65fafa947f3dd76da528a02fe
+size 11423594

tokenizer_config.json

@@ -0,0 +1,296 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151669": {
+      "content": "<|AUDIO|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151670": {
+      "content": "<|audio_bos|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151671": {
+      "content": "<|audio_eos|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151672": {
+      "content": "<|audio_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151673": {
+      "content": "<|sil|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>",
+    "<|AUDIO|>",
+    "<|audio_bos|>",
+    "<|audio_eos|>",
+    "<|audio_pad|>",
+    "<|sil|>"
+  ],
+  "audio_bos_token": "<|audio_bos|>",
+  "audio_eos_token": "<|audio_eos|>",
+  "audio_pad_token": "<|audio_pad|>",
+  "audio_token": "<|AUDIO|>",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {
+    "audio_bos_token": "<|audio_bos|>",
+    "audio_eos_token": "<|audio_eos|>",
+    "audio_pad_token": "<|audio_pad|>",
+    "audio_token": "<|AUDIO|>",
+    "text_sil_token": "<|sil|>"
+  },
+  "model_max_length": 1010000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "text_sil_token": "<|sil|>",
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}