Add tiny MiniMax Music 3 modular fixtures

.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

condition_encoder/config.json

@@ -0,0 +1,11 @@
+{
+  "_class_name": "MiniMaxMusic3ConditionEncoder",
+  "_diffusers_version": "0.40.0.dev0",
+  "condition_hidden_dim": 16,
+  "input_hop_length": 960,
+  "input_sampling_rate": 24000,
+  "num_condition_layers": 8,
+  "out_dim": 16,
+  "output_hop_length": 512,
+  "output_sampling_rate": 44100
+}

condition_encoder/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2b3f5931885597a2128694ae01ecbd632ec89cc605fb8c0dcce8aa062d7ba35
+size 3492

language_model/config.json

@@ -0,0 +1,37 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "head_dim": 8,
+  "hidden_act": "silu",
+  "hidden_size": 16,
+  "initializer_range": 0.02,
+  "intermediate_size": 32,
+  "layer_types": [
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 512,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 1,
+  "pad_token_id": null,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.13.0.dev0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 168059
+}

language_model/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "transformers_version": "5.13.0.dev0",
+  "use_cache": true
+}

language_model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9147f3d89ff7b5a9676a3b696d7f3cb8fadf8929bdabb98207e2b10b64b6ef6
+size 21533072

modular_model_index.json

@@ -0,0 +1,103 @@
+{
+  "_blocks_class_name": "MiniMaxMusic3Blocks",
+  "_class_name": "MiniMaxMusic3ModularPipeline",
+  "_diffusers_version": "0.40.0.dev0",
+  "condition_encoder": [
+    "diffusers",
+    "MiniMaxMusic3ConditionEncoder",
+    {
+      "pretrained_model_name_or_path": "hf-internal-testing/tiny-minimax-music3-modular-pipe",
+      "revision": null,
+      "subfolder": "condition_encoder",
+      "type_hint": [
+        "diffusers",
+        "MiniMaxMusic3ConditionEncoder"
+      ],
+      "variant": null
+    }
+  ],
+  "language_model": [
+    "transformers",
+    "Qwen3ForCausalLM",
+    {
+      "pretrained_model_name_or_path": "hf-internal-testing/tiny-minimax-music3-modular-pipe",
+      "revision": null,
+      "subfolder": "language_model",
+      "type_hint": [
+        "transformers",
+        "Qwen3ForCausalLM"
+      ],
+      "variant": null
+    }
+  ],
+  "rvq_depth_decoder": [
+    "diffusers",
+    "MiniMaxMusic3RVQDepthDecoder",
+    {
+      "pretrained_model_name_or_path": "hf-internal-testing/tiny-minimax-music3-modular-pipe",
+      "revision": null,
+      "subfolder": "rvq_depth_decoder",
+      "type_hint": [
+        "diffusers",
+        "MiniMaxMusic3RVQDepthDecoder"
+      ],
+      "variant": null
+    }
+  ],
+  "scheduler": [
+    "diffusers",
+    "FlowMatchEulerDiscreteScheduler",
+    {
+      "pretrained_model_name_or_path": "hf-internal-testing/tiny-minimax-music3-modular-pipe",
+      "revision": null,
+      "subfolder": "scheduler",
+      "type_hint": [
+        "diffusers",
+        "FlowMatchEulerDiscreteScheduler"
+      ],
+      "variant": null
+    }
+  ],
+  "tokenizer": [
+    "transformers",
+    "Qwen2Tokenizer",
+    {
+      "pretrained_model_name_or_path": "hf-internal-testing/tiny-minimax-music3-modular-pipe",
+      "revision": null,
+      "subfolder": "tokenizer",
+      "type_hint": [
+        "transformers",
+        "Qwen2Tokenizer"
+      ],
+      "variant": null
+    }
+  ],
+  "transformer": [
+    "diffusers",
+    "MiniMaxMusic3Transformer1DModel",
+    {
+      "pretrained_model_name_or_path": "hf-internal-testing/tiny-minimax-music3-modular-pipe",
+      "revision": null,
+      "subfolder": "transformer",
+      "type_hint": [
+        "diffusers",
+        "MiniMaxMusic3Transformer1DModel"
+      ],
+      "variant": null
+    }
+  ],
+  "vocoder": [
+    "diffusers",
+    "MiniMaxMusic3Vocoder",
+    {
+      "pretrained_model_name_or_path": "hf-internal-testing/tiny-minimax-music3-modular-pipe",
+      "revision": null,
+      "subfolder": "vocoder",
+      "type_hint": [
+        "diffusers",
+        "MiniMaxMusic3Vocoder"
+      ],
+      "variant": null
+    }
+  ]
+}

rvq_depth_decoder/config.json

@@ -0,0 +1,11 @@
+{
+  "_class_name": "MiniMaxMusic3RVQDepthDecoder",
+  "_diffusers_version": "0.40.0.dev0",
+  "audio_vocab_size": 8,
+  "hidden_size": 16,
+  "intermediate_size": 32,
+  "max_position_embeddings": 16,
+  "num_attention_heads": 2,
+  "num_codebooks": 8,
+  "num_layers": 1
+}

rvq_depth_decoder/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14def4ef335b56e8a8d1270a41243bb27a8b0bb37ae06e09eefcb2d9c3b32c34
+size 21392

scheduler/scheduler_config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "FlowMatchEulerDiscreteScheduler",
+  "_diffusers_version": "0.40.0.dev0",
+  "base_image_seq_len": 256,
+  "base_shift": 0.5,
+  "invert_sigmas": true,
+  "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
+}

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 +1,15 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

transformer/config.json

@@ -0,0 +1,12 @@
+{
+  "_class_name": "MiniMaxMusic3Transformer1DModel",
+  "_diffusers_version": "0.40.0.dev0",
+  "attention_head_dim": 8,
+  "condition_dim": 16,
+  "ff_inner_dim": 32,
+  "fourier_embedding_dim": 8,
+  "in_channels": 8,
+  "num_attention_heads": 2,
+  "num_layers": 2,
+  "rotary_dim": 4
+}

transformer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f64a7159bad770566d091d02235e84d9b971d6e0d2544247e7186a69b50afba1
+size 33320

vocoder/config.json

@@ -0,0 +1,12 @@
+{
+  "_class_name": "MiniMaxMusic3Vocoder",
+  "_diffusers_version": "0.40.0.dev0",
+  "decoder_hidden_dim": 8,
+  "decoder_input_dim": 8,
+  "latent_channels": 8,
+  "sampling_rate": 44100,
+  "upsampling_ratios": [
+    2,
+    2
+  ]
+}

vocoder/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d479a6a24d746a3cadd0d46b4606bdfbf98bc8d0440b774ece8bdc3c6e95077e
+size 11024