{ "component": "rvq_depth_decoder", "format": "mlx-minimax-music3-v1", "processed_source_files": [ "diffusion_pytorch_model.safetensors" ], "quantization": { "bits": 8, "group_size": 64, "mode": "affine" }, "shards": [ { "bytes": 757287056, "file": "model-00001.safetensors", "remote_revision": "80d742cb3ea7bbb48641cfdb50cb3896f29cf4d2", "remote_sha256": "2b2a7d6b19739452ee06c64cd174072cac756c3dd4fe766f6bea9c838593728d", "remote_verified": true, "sha256": "2b2a7d6b19739452ee06c64cd174072cac756c3dd4fe766f6bea9c838593728d", "tensors": [ "audio_embeddings.weight", "audio_heads.0.weight", "audio_heads.1.weight", "audio_heads.2.weight", "audio_heads.3.weight", "audio_heads.4.weight", "audio_heads.5.weight", "audio_heads.6.weight", "layers.0.attn.to_k.biases", "layers.0.attn.to_k.scales", "layers.0.attn.to_k.weight", "layers.0.attn.to_out.biases", "layers.0.attn.to_out.scales", "layers.0.attn.to_out.weight", "layers.0.attn.to_q.biases", "layers.0.attn.to_q.scales", "layers.0.attn.to_q.weight", "layers.0.attn.to_v.biases", "layers.0.attn.to_v.scales", "layers.0.attn.to_v.weight", "layers.0.down_proj.biases", "layers.0.down_proj.scales", "layers.0.down_proj.weight", "layers.0.gate_proj.biases", "layers.0.gate_proj.scales", "layers.0.gate_proj.weight", "layers.0.input_layernorm.weight", "layers.0.post_attention_layernorm.weight", "layers.0.up_proj.biases", "layers.0.up_proj.scales", "layers.0.up_proj.weight", "layers.1.attn.to_k.biases", "layers.1.attn.to_k.scales", "layers.1.attn.to_k.weight", "layers.1.attn.to_out.biases", "layers.1.attn.to_out.scales", "layers.1.attn.to_out.weight", "layers.1.attn.to_q.biases", "layers.1.attn.to_q.scales", "layers.1.attn.to_q.weight", "layers.1.attn.to_v.biases", "layers.1.attn.to_v.scales", "layers.1.attn.to_v.weight", "layers.1.down_proj.biases", "layers.1.down_proj.scales", "layers.1.down_proj.weight", "layers.1.gate_proj.biases", "layers.1.gate_proj.scales", "layers.1.gate_proj.weight", "layers.1.input_layernorm.weight", "layers.1.post_attention_layernorm.weight", "layers.1.up_proj.biases", "layers.1.up_proj.scales", "layers.1.up_proj.weight", "layers.2.attn.to_k.biases", "layers.2.attn.to_k.scales", "layers.2.attn.to_k.weight", "layers.2.attn.to_out.biases", "layers.2.attn.to_out.scales", "layers.2.attn.to_out.weight", "layers.2.attn.to_q.biases", "layers.2.attn.to_q.scales", "layers.2.attn.to_q.weight", "layers.2.attn.to_v.biases", "layers.2.attn.to_v.scales", "layers.2.attn.to_v.weight", "layers.2.down_proj.biases", "layers.2.down_proj.scales", "layers.2.down_proj.weight", "layers.2.gate_proj.biases", "layers.2.gate_proj.scales", "layers.2.gate_proj.weight", "layers.2.input_layernorm.weight", "layers.2.post_attention_layernorm.weight", "layers.2.up_proj.biases", "layers.2.up_proj.scales", "layers.2.up_proj.weight", "layers.3.attn.to_k.biases", "layers.3.attn.to_k.scales", "layers.3.attn.to_k.weight", "layers.3.attn.to_out.biases", "layers.3.attn.to_out.scales", "layers.3.attn.to_out.weight", "layers.3.attn.to_q.biases", "layers.3.attn.to_q.scales", "layers.3.attn.to_q.weight", "layers.3.attn.to_v.biases", "layers.3.attn.to_v.scales", "layers.3.attn.to_v.weight", "layers.3.down_proj.biases", "layers.3.down_proj.scales", "layers.3.down_proj.weight", "layers.3.gate_proj.biases", "layers.3.gate_proj.scales", "layers.3.gate_proj.weight", "layers.3.input_layernorm.weight", "layers.3.post_attention_layernorm.weight", "layers.3.up_proj.biases", "layers.3.up_proj.scales", "layers.3.up_proj.weight", "norm.weight", "pos_embedding.weight", "projection.weight" ] } ], "source_files": [ "diffusion_pytorch_model.safetensors" ], "status": "complete", "total_size": 757276672, "weight_map": { "audio_embeddings.weight": "model-00001.safetensors", "audio_heads.0.weight": "model-00001.safetensors", "audio_heads.1.weight": "model-00001.safetensors", "audio_heads.2.weight": "model-00001.safetensors", "audio_heads.3.weight": "model-00001.safetensors", "audio_heads.4.weight": "model-00001.safetensors", "audio_heads.5.weight": "model-00001.safetensors", "audio_heads.6.weight": "model-00001.safetensors", "layers.0.attn.to_k.biases": "model-00001.safetensors", "layers.0.attn.to_k.scales": "model-00001.safetensors", "layers.0.attn.to_k.weight": "model-00001.safetensors", "layers.0.attn.to_out.biases": "model-00001.safetensors", "layers.0.attn.to_out.scales": "model-00001.safetensors", "layers.0.attn.to_out.weight": "model-00001.safetensors", "layers.0.attn.to_q.biases": "model-00001.safetensors", "layers.0.attn.to_q.scales": "model-00001.safetensors", "layers.0.attn.to_q.weight": "model-00001.safetensors", "layers.0.attn.to_v.biases": "model-00001.safetensors", "layers.0.attn.to_v.scales": "model-00001.safetensors", "layers.0.attn.to_v.weight": "model-00001.safetensors", "layers.0.down_proj.biases": "model-00001.safetensors", "layers.0.down_proj.scales": "model-00001.safetensors", "layers.0.down_proj.weight": "model-00001.safetensors", "layers.0.gate_proj.biases": "model-00001.safetensors", "layers.0.gate_proj.scales": "model-00001.safetensors", "layers.0.gate_proj.weight": "model-00001.safetensors", "layers.0.input_layernorm.weight": "model-00001.safetensors", "layers.0.post_attention_layernorm.weight": "model-00001.safetensors", "layers.0.up_proj.biases": "model-00001.safetensors", "layers.0.up_proj.scales": "model-00001.safetensors", "layers.0.up_proj.weight": "model-00001.safetensors", "layers.1.attn.to_k.biases": "model-00001.safetensors", "layers.1.attn.to_k.scales": "model-00001.safetensors", "layers.1.attn.to_k.weight": "model-00001.safetensors", "layers.1.attn.to_out.biases": "model-00001.safetensors", "layers.1.attn.to_out.scales": "model-00001.safetensors", "layers.1.attn.to_out.weight": "model-00001.safetensors", "layers.1.attn.to_q.biases": "model-00001.safetensors", "layers.1.attn.to_q.scales": "model-00001.safetensors", "layers.1.attn.to_q.weight": "model-00001.safetensors", "layers.1.attn.to_v.biases": "model-00001.safetensors", "layers.1.attn.to_v.scales": "model-00001.safetensors", "layers.1.attn.to_v.weight": "model-00001.safetensors", "layers.1.down_proj.biases": "model-00001.safetensors", "layers.1.down_proj.scales": "model-00001.safetensors", "layers.1.down_proj.weight": "model-00001.safetensors", "layers.1.gate_proj.biases": "model-00001.safetensors", "layers.1.gate_proj.scales": "model-00001.safetensors", "layers.1.gate_proj.weight": "model-00001.safetensors", "layers.1.input_layernorm.weight": "model-00001.safetensors", "layers.1.post_attention_layernorm.weight": "model-00001.safetensors", "layers.1.up_proj.biases": "model-00001.safetensors", "layers.1.up_proj.scales": "model-00001.safetensors", "layers.1.up_proj.weight": "model-00001.safetensors", "layers.2.attn.to_k.biases": "model-00001.safetensors", "layers.2.attn.to_k.scales": "model-00001.safetensors", "layers.2.attn.to_k.weight": "model-00001.safetensors", "layers.2.attn.to_out.biases": "model-00001.safetensors", "layers.2.attn.to_out.scales": "model-00001.safetensors", "layers.2.attn.to_out.weight": "model-00001.safetensors", "layers.2.attn.to_q.biases": "model-00001.safetensors", "layers.2.attn.to_q.scales": "model-00001.safetensors", "layers.2.attn.to_q.weight": "model-00001.safetensors", "layers.2.attn.to_v.biases": "model-00001.safetensors", "layers.2.attn.to_v.scales": "model-00001.safetensors", "layers.2.attn.to_v.weight": "model-00001.safetensors", "layers.2.down_proj.biases": "model-00001.safetensors", "layers.2.down_proj.scales": "model-00001.safetensors", "layers.2.down_proj.weight": "model-00001.safetensors", "layers.2.gate_proj.biases": "model-00001.safetensors", "layers.2.gate_proj.scales": "model-00001.safetensors", "layers.2.gate_proj.weight": "model-00001.safetensors", "layers.2.input_layernorm.weight": "model-00001.safetensors", "layers.2.post_attention_layernorm.weight": "model-00001.safetensors", "layers.2.up_proj.biases": "model-00001.safetensors", "layers.2.up_proj.scales": "model-00001.safetensors", "layers.2.up_proj.weight": "model-00001.safetensors", "layers.3.attn.to_k.biases": "model-00001.safetensors", "layers.3.attn.to_k.scales": "model-00001.safetensors", "layers.3.attn.to_k.weight": "model-00001.safetensors", "layers.3.attn.to_out.biases": "model-00001.safetensors", "layers.3.attn.to_out.scales": "model-00001.safetensors", "layers.3.attn.to_out.weight": "model-00001.safetensors", "layers.3.attn.to_q.biases": "model-00001.safetensors", "layers.3.attn.to_q.scales": "model-00001.safetensors", "layers.3.attn.to_q.weight": "model-00001.safetensors", "layers.3.attn.to_v.biases": "model-00001.safetensors", "layers.3.attn.to_v.scales": "model-00001.safetensors", "layers.3.attn.to_v.weight": "model-00001.safetensors", "layers.3.down_proj.biases": "model-00001.safetensors", "layers.3.down_proj.scales": "model-00001.safetensors", "layers.3.down_proj.weight": "model-00001.safetensors", "layers.3.gate_proj.biases": "model-00001.safetensors", "layers.3.gate_proj.scales": "model-00001.safetensors", "layers.3.gate_proj.weight": "model-00001.safetensors", "layers.3.input_layernorm.weight": "model-00001.safetensors", "layers.3.post_attention_layernorm.weight": "model-00001.safetensors", "layers.3.up_proj.biases": "model-00001.safetensors", "layers.3.up_proj.scales": "model-00001.safetensors", "layers.3.up_proj.weight": "model-00001.safetensors", "norm.weight": "model-00001.safetensors", "pos_embedding.weight": "model-00001.safetensors", "projection.weight": "model-00001.safetensors" } }