Update code

config.json

@@ -1,78 +1 @@
-{
-  "_name_or_path": "/Users/zhuang/repos/ultravox-omni/artifacts/model-zhuang.2025-01-08-v0_5.llama3_2-1b-4a.246352f:v8",
-  "architectures": [
-    "UltravoxModel"
-  ],
-  "audio_config": {
-    "_name_or_path": "openai/whisper-large-v3-turbo",
-    "activation_dropout": 0.0,
-    "activation_function": "gelu",
-    "apply_spec_augment": false,
-    "architectures": [
-      "WhisperForConditionalGeneration"
-    ],
-    "attention_dropout": 0.0,
-    "begin_suppress_tokens": [
-      220,
-      50256
-    ],
-    "bos_token_id": 50257,
-    "d_model": 1280,
-    "decoder_attention_heads": 20,
-    "decoder_ffn_dim": 5120,
-    "decoder_layerdrop": 0.0,
-    "decoder_layers": 4,
-    "decoder_start_token_id": 50258,
-    "dropout": 0.0,
-    "encoder_attention_heads": 20,
-    "encoder_ffn_dim": 5120,
-    "encoder_layerdrop": 0.0,
-    "encoder_layers": 32,
-    "eos_token_id": 50257,
-    "init_std": 0.02,
-    "is_encoder_decoder": true,
-    "max_source_positions": 1500,
-    "max_target_positions": 448,
-    "median_filter_width": 7,
-    "model_type": "whisper",
-    "num_hidden_layers": 32,
-    "num_mel_bins": 128,
-    "pad_token_id": 50257,
-    "scale_embedding": false,
-    "torch_dtype": "float16",
-    "use_cache": true,
-    "vocab_size": 51866
-  },
-  "audio_latency_block_size": null,
-  "audio_model_id": null,
-  "auto_map": {
-    "AutoConfig": "ultravox_config.UltravoxConfig",
-    "AutoModel": "ultravox_model.UltravoxModel",
-    "AutoProcessor": "ultravox_processing.UltravoxProcessor"
-  },
-  "custom_pipelines": {
-    "ultravox-pipeline": {
-      "impl": "ultravox_pipeline.UltravoxPipeline",
-      "pt": [
-        "AutoModel"
-      ],
-      "tf": [],
-      "type": "multimodal"
-    }
-  },
-  "hidden_size": 4096,
-  "ignore_index": -100,
-  "initializer_range": 0.02,
-  "model_type": "ultravox",
-  "norm_init": 0.4,
-  "pad_token_id": 128009,
-  "projector_act": "swiglu",
-  "projector_ln_mid": true,
-  "stack_factor": 8,
-  "text_model_id": "meta-llama/Llama-3.2-1B-Instruct",
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.48.1",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 16,
-  "vocab_size": 128256
-}
+{"_name_or_path": "/Users/zhuang/repos/ultravox-omni/artifacts/model-zhuang.2025-01-08-v0_5.llama3_2-1b-4a.246352f:v8", "architectures": ["UltravoxModel"], "audio_config": {"_name_or_path": "openai/whisper-large-v3-turbo", "activation_dropout": 0.0, "activation_function": "gelu", "apply_spec_augment": false, "architectures": ["WhisperForConditionalGeneration"], "attention_dropout": 0.0, "begin_suppress_tokens": [220, 50256], "bos_token_id": 50257, "d_model": 1280, "decoder_attention_heads": 20, "decoder_ffn_dim": 5120, "decoder_layerdrop": 0.0, "decoder_layers": 4, "decoder_start_token_id": 50258, "dropout": 0.0, "encoder_attention_heads": 20, "encoder_ffn_dim": 5120, "encoder_layerdrop": 0.0, "encoder_layers": 32, "eos_token_id": 50257, "init_std": 0.02, "is_encoder_decoder": true, "max_source_positions": 1500, "max_target_positions": 448, "median_filter_width": 7, "model_type": "whisper", "num_hidden_layers": 32, "num_mel_bins": 128, "pad_token_id": 50257, "scale_embedding": false, "torch_dtype": "float16", "use_cache": true, "vocab_size": 51866}, "audio_latency_block_size": null, "audio_model_id": null, "auto_map": {"AutoConfig": "ultravox_config.UltravoxConfig", "AutoModel": "ultravox_model.UltravoxModel", "AutoProcessor": "ultravox_processing.UltravoxProcessor"}, "custom_pipelines": {"ultravox-pipeline": {"impl": "ultravox_pipeline.UltravoxPipeline", "pt": ["AutoModel"], "tf": [], "type": "multimodal"}}, "hidden_size": 4096, "ignore_index": -100, "initializer_range": 0.02, "model_type": "ultravox", "norm_init": 0.4, "pad_token_id": 128009, "projector_act": "swiglu", "projector_ln_mid": true, "stack_factor": 8, "text_model_id": "meta-llama/Llama-3.2-1B-Instruct", "torch_dtype": "bfloat16", "transformers_version": "4.48.1", "num_attention_heads": 32, "num_hidden_layers": 16, "vocab_size": 128256, "audio_token_index": 128256}

special_tokens_map.json

@@ -1,4 +1,13 @@
 {
+  "additional_special_tokens": [
+    {
+      "content": "<|audio|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
   "bos_token": {
     "content": "<|begin_of_text|>",
     "lstrip": false,
@@ -13,5 +22,11 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|eot_id|>"
+  "pad_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
-size 17209920
+oid sha256:e87771bfea74770d36a1432b5f9ba6d7f611d33fb63681d10c2479540c1591f8
+size 17210106

tokenizer_config.json

@@ -2047,8 +2047,19 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "128256": {
+      "content": "<|audio|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
+  "additional_special_tokens": [
+    "<|audio|>"
+  ],
   "bos_token": "<|begin_of_text|>",
   "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- if strftime_now is defined %}\n        {%- set date_string = strftime_now(\"%d %b %Y\") %}\n    {%- else %}\n        {%- set date_string = \"26 Jul 2024\" %}\n    {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n    {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n        {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n        {{- '\"parameters\": ' }}\n        {{- tool_call.arguments | tojson }}\n        {{- \"}\" }}\n        {{- \"<|eot_id|>\" }}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
   "clean_up_tokenization_spaces": true,
@@ -2060,5 +2071,5 @@
   ],
   "model_max_length": 131072,
   "pad_token": "<|eot_id|>",
-  "tokenizer_class": "PreTrainedTokenizerFast"
+  "tokenizer_class": "PreTrainedTokenizer"
 }