Upload folder using huggingface_hub

.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/tokenizer.json filter=lfs diff=lfs merge=lfs -text

audio_token_detokenizer/config.json

@@ -0,0 +1,21 @@
+{
+  "_class_name": "AceStepAudioTokenDetokenizer",
+  "_diffusers_version": "0.39.0.dev0",
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "audio_acoustic_hidden_dim": 64,
+  "head_dim": 128,
+  "hidden_size": 2048,
+  "intermediate_size": 6144,
+  "layer_types": [
+    "sliding_attention",
+    "full_attention"
+  ],
+  "num_attention_heads": 16,
+  "num_attention_pooler_hidden_layers": 2,
+  "num_key_value_heads": 8,
+  "pool_window_size": 5,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000,
+  "sliding_window": 128
+}

audio_token_detokenizer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57f4bb761e6305efe4c28e9e7e7e0e353fffc5dec28af28a6a7d5429396c8edf
+size 210026424

audio_tokenizer/config.json

@@ -0,0 +1,31 @@
+{
+  "_class_name": "AceStepAudioTokenizer",
+  "_diffusers_version": "0.39.0.dev0",
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "audio_acoustic_hidden_dim": 64,
+  "fsq_dim": 2048,
+  "fsq_input_levels": [
+    8,
+    8,
+    8,
+    5,
+    5,
+    5
+  ],
+  "fsq_input_num_quantizers": 1,
+  "head_dim": 128,
+  "hidden_size": 2048,
+  "intermediate_size": 6144,
+  "layer_types": [
+    "sliding_attention",
+    "full_attention"
+  ],
+  "num_attention_heads": 16,
+  "num_attention_pooler_hidden_layers": 2,
+  "num_key_value_heads": 8,
+  "pool_window_size": 5,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000,
+  "sliding_window": 128
+}

audio_tokenizer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b6e89e32223dc1d91ad522550d6a2744abc9f8659879f154005703b2140d260
+size 210068124

condition_encoder/config.json

@@ -0,0 +1,19 @@
+{
+  "_class_name": "AceStepConditionEncoder",
+  "_diffusers_version": "0.39.0.dev0",
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "head_dim": 128,
+  "hidden_size": 2048,
+  "intermediate_size": 6144,
+  "layer_types": null,
+  "num_attention_heads": 16,
+  "num_key_value_heads": 8,
+  "num_lyric_encoder_hidden_layers": 8,
+  "num_timbre_encoder_hidden_layers": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000,
+  "sliding_window": 128,
+  "text_hidden_dim": 1024,
+  "timbre_hidden_dim": 64
+}

condition_encoder/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac9cf5e23bfeb2de0d0876ab5b836f5d05b4c8bd22455cc548bd2a4f56b49fab
+size 1218676312

model_index.json

@@ -0,0 +1,36 @@
+{
+  "_class_name": "AceStepPipeline",
+  "_diffusers_version": "0.39.0.dev0",
+  "audio_token_detokenizer": [
+    "ace_step",
+    "AceStepAudioTokenDetokenizer"
+  ],
+  "audio_tokenizer": [
+    "ace_step",
+    "AceStepAudioTokenizer"
+  ],
+  "condition_encoder": [
+    "ace_step",
+    "AceStepConditionEncoder"
+  ],
+  "scheduler": [
+    "diffusers",
+    "FlowMatchEulerDiscreteScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "Qwen3Model"
+  ],
+  "tokenizer": [
+    "transformers",
+    "Qwen2Tokenizer"
+  ],
+  "transformer": [
+    "diffusers",
+    "AceStepTransformer1DModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderOobleck"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "FlowMatchEulerDiscreteScheduler",
+  "_diffusers_version": "0.39.0.dev0",
+  "base_image_seq_len": 256,
+  "base_shift": 0.5,
+  "invert_sigmas": false,
+  "max_image_seq_len": 4096,
+  "max_shift": 1.15,
+  "num_train_timesteps": 1,
+  "shift": 1.0,
+  "shift_terminal": null,
+  "stochastic_sampling": false,
+  "time_shift_type": "exponential",
+  "use_beta_sigmas": false,
+  "use_dynamic_shifting": false,
+  "use_exponential_sigmas": false,
+  "use_karras_sigmas": false
+}

silence_latent.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a778e9dd942f5e8b2c09c55370782d318834432b03dabbcdf70e6ed49ad6358b
+size 3841215

text_encoder/config.json

@@ -0,0 +1,63 @@
+{
+  "architectures": [
+    "Qwen3Model"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": null,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.5.4",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151669
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0437e45c94563b09e13cb7a64478fc406947a93cb34a7e05870fc8dcd48e23fd
+size 1191586416

tokenizer/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- 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 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.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').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' }}
+        {{- message.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' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

tokenizer/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93623af029cdc69b87f2864d3b2cc2424fdf16684f15e139b5b9d08ec34ced91
+size 11423701

tokenizer/tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": true,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

transformer/config.json

@@ -0,0 +1,47 @@
+{
+  "_class_name": "AceStepTransformer1DModel",
+  "_diffusers_version": "0.39.0.dev0",
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "audio_acoustic_hidden_dim": 64,
+  "encoder_hidden_size": 2048,
+  "head_dim": 128,
+  "hidden_size": 2048,
+  "in_channels": 192,
+  "intermediate_size": 6144,
+  "is_turbo": false,
+  "layer_types": [
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "model_version": null,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 8,
+  "patch_size": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000,
+  "sliding_window": 128
+}

transformer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d19d04152d3e261d52d64c1b02cffe6eb0f0e585646ec8982bffd1bf3a57ba8
+size 3150968664

vae/config.json

@@ -0,0 +1,24 @@
+{
+  "_class_name": "AutoencoderOobleck",
+  "_diffusers_version": "0.39.0.dev0",
+  "_name_or_path": "train_model/huggingface/models--ACE-Step--Ace-Step1.5/snapshots/19671f406d603126926c1b7e2adc169acbcade22/vae",
+  "audio_channels": 2,
+  "channel_multiples": [
+    1,
+    2,
+    4,
+    8,
+    16
+  ],
+  "decoder_channels": 128,
+  "decoder_input_channels": 64,
+  "downsampling_ratios": [
+    2,
+    4,
+    4,
+    6,
+    10
+  ],
+  "encoder_hidden_size": 128,
+  "sampling_rate": 48000
+}

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da17edb604c40deaf09e9b24974e590d1ca83a374070e5d0884cfa4bed9a99b0
+size 337431388