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
+Qwen3-Embedding-0.6B/tokenizer.json filter=lfs diff=lfs merge=lfs -text

Qwen3-Embedding-0.6B/config.json

@@ -0,0 +1,60 @@
+{
+  "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,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.0.dev0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151669
+}

Qwen3-Embedding-0.6B/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb6278953d320cdb12decef38ea11995e09a012240875135f25fedd8492ea914
+size 2383139199

Qwen3-Embedding-0.6B/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:def76fb086971c7867b829c23a26261e38d9d74e02139253b38aeb9df8b4b50a
+size 11423705

Qwen3-Embedding-0.6B/tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "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
+    }
+  },
+  "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|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

README.md

@@ -0,0 +1,62 @@
+---
+library_name: mlx
+tags:
+  - mlx
+  - music-generation
+  - ace-step
+  - audio
+  - text-to-music
+base_model: ACE-Step/ACE-Step1.5
+---
+
+# ACE-Step 1.5 MLX
+
+MLX-converted weights for [ACE-Step/ACE-Step1.5](https://huggingface.co/ACE-Step/ACE-Step1.5), a 3.5B parameter flow-matching music generation model.
+
+Converted using [mlx-audio](https://github.com/Blaizzy/mlx-audio).
+
+## Features
+
+- **Text-to-Music**: Generate music from text descriptions
+- **Vocals Support**: Generate songs with lyrics in multiple languages
+- **48kHz stereo** audio output
+- Optimized for **Apple Silicon**
+
+## Usage
+
+```python
+from mlx_audio.tts import load
+
+model = load("mlx-community/ACE-Step1.5-MLX")
+
+for result in model.generate(
+    text="upbeat electronic dance music with energetic synthesizers",
+    duration=30.0,
+):
+    audio = result.audio  # [samples, 2] stereo audio
+    sample_rate = result.sample_rate  # 48000
+```
+
+## With Vocals
+
+```python
+for result in model.generate(
+    text="upbeat pop song with female vocals",
+    lyrics="""[verse]
+Dance with me tonight
+Under the neon lights
+
+[chorus]
+Move your body, feel the groove
+""",
+    duration=60.0,
+    vocal_language="en",
+):
+    ...
+```
+
+See the [ACE-Step README](https://github.com/Blaizzy/mlx-audio/tree/main/mlx_audio/tts/models/ace_step) for full parameter documentation.
+
+## Original Model
+
+Refer to the [original model card](https://huggingface.co/ACE-Step/ACE-Step1.5) for more details.

config.json

@@ -0,0 +1,82 @@
+{
+    "architectures": [
+        "AceStepConditionGenerationModel"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "audio_acoustic_hidden_dim": 64,
+    "auto_map": {
+        "AutoConfig": "configuration_acestep_v15.AceStepConfig",
+        "AutoModel": "modeling_acestep_v15_turbo.AceStepConditionGenerationModel"
+    },
+    "data_proportion": 0.5,
+    "dtype": "bfloat16",
+    "fsq_dim": 2048,
+    "fsq_input_levels": [
+        8,
+        8,
+        8,
+        5,
+        5,
+        5
+    ],
+    "fsq_input_num_quantizers": 1,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 2048,
+    "in_channels": 192,
+    "initializer_range": 0.02,
+    "intermediate_size": 6144,
+    "is_turbo": true,
+    "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"
+    ],
+    "max_position_embeddings": 32768,
+    "model_type": "acestep",
+    "model_version": "turbo",
+    "num_attention_heads": 16,
+    "num_attention_pooler_hidden_layers": 2,
+    "num_audio_decoder_hidden_layers": 24,
+    "num_hidden_layers": 24,
+    "num_key_value_heads": 8,
+    "num_lyric_encoder_hidden_layers": 8,
+    "num_timbre_encoder_hidden_layers": 4,
+    "patch_size": 2,
+    "pool_window_size": 5,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": null,
+    "rope_theta": 1000000,
+    "sliding_window": 128,
+    "text_hidden_dim": 1024,
+    "timbre_fix_frame": 750,
+    "timbre_hidden_dim": 64,
+    "timestep_mu": -0.4,
+    "timestep_sigma": 1.0,
+    "transformers_version": "4.57.0.dev0",
+    "use_cache": true,
+    "use_sliding_window": true,
+    "vocab_size": 64003
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:855129c856f544c4e4e415cfa3496006ae12e6d40aee9f615e9b03097ab4abec
+size 9575570070

silence_latent.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9db4567c16ea0f603d0cd03ce8a4a89d22de914adeeefad0f3cf99a01083ef8f
+size 3840128

vae/config.json

@@ -0,0 +1,24 @@
+{
+  "_class_name": "AutoencoderOobleck",
+  "_diffusers_version": "0.34.0",
+  "_name_or_path": "/root/data/repo/gongjunmin/ACE-Step-1.5/checkpoints/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:c84ac17576b1c5b0a4da2af9ee165401cd1e9e76cbc7d85cf606a3bb0f4bbbf1
+size 674821537