Upload model trained with Unsloth

Upload model trained with Unsloth 2x faster

config.json

@@ -0,0 +1,122 @@
+{
+  "architectures": [
+    "CsmForConditionalGeneration"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "audio_eos_token_id": 128003,
+  "audio_token_id": 128002,
+  "bos_token_id": 128000,
+  "codebook_eos_token_id": 0,
+  "codebook_pad_token_id": 2050,
+  "codec_config": {
+    "_name_or_path": "kyutai/mimi",
+    "architectures": [
+      "MimiModel"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "audio_channels": 1,
+    "codebook_dim": 256,
+    "codebook_size": 2048,
+    "compress": 2,
+    "dilation_growth_rate": 2,
+    "frame_rate": 12.5,
+    "head_dim": 64,
+    "hidden_act": "gelu",
+    "hidden_size": 512,
+    "initializer_range": 0.02,
+    "intermediate_size": 2048,
+    "kernel_size": 7,
+    "last_kernel_size": 3,
+    "layer_scale_initial_scale": 0.01,
+    "max_position_embeddings": 8000,
+    "model_type": "mimi",
+    "norm_eps": 1e-05,
+    "normalize": false,
+    "num_attention_heads": 8,
+    "num_filters": 64,
+    "num_hidden_layers": 8,
+    "num_key_value_heads": 8,
+    "num_quantizers": 32,
+    "num_residual_layers": 1,
+    "num_semantic_quantizers": 1,
+    "pad_mode": "constant",
+    "residual_kernel_size": 3,
+    "rope_theta": 10000.0,
+    "sampling_rate": 24000,
+    "sliding_window": 250,
+    "torch_dtype": "float16",
+    "trim_right_ratio": 1.0,
+    "upsample_groups": 512,
+    "upsampling_ratios": [
+      8,
+      6,
+      5,
+      4
+    ],
+    "use_cache": false,
+    "use_causal_conv": true,
+    "use_conv_shortcut": false,
+    "vector_quantization_hidden_dimension": 256
+  },
+  "depth_decoder_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "backbone_hidden_size": 2048,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 1024,
+    "initializer_range": 0.02,
+    "intermediate_size": 8192,
+    "max_position_embeddings": 33,
+    "mlp_bias": false,
+    "model_type": "csm_depth_decoder_model",
+    "num_attention_heads": 8,
+    "num_codebooks": 32,
+    "num_hidden_layers": 4,
+    "num_key_value_heads": 2,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": {
+      "factor": 32.0,
+      "high_freq_factor": 0.0078125,
+      "low_freq_factor": 0.001953125,
+      "original_max_position_embeddings": 16,
+      "rope_type": "llama3"
+    },
+    "rope_theta": 500000,
+    "torch_dtype": "float16",
+    "use_cache": true,
+    "vocab_size": 2051
+  },
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "csm",
+  "num_attention_heads": 32,
+  "num_codebooks": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128256,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 0.5,
+    "low_freq_factor": 0.125,
+    "original_max_position_embeddings": 1024,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000,
+  "text_vocab_size": 128256,
+  "tie_codebooks_embeddings": true,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.52.0.dev0",
+  "unsloth_version": "2025.5.6",
+  "use_cache": true,
+  "vocab_size": 2051
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "attn_implementation": "sdpa",
+  "bos_token_id": 128000,
+  "depth_decoder_do_sample": true,
+  "depth_decoder_max_new_tokens": 31,
+  "depth_decoder_min_new_tokens": 31,
+  "depth_decoder_temperature": 0.9,
+  "do_sample": true,
+  "max_length": 2048,
+  "max_new_tokens": 125,
+  "pad_token_id": 128256,
+  "temperature": 0.9,
+  "transformers_version": "4.52.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc17b09388b1765871f3abab5690f02d86a1d858717c0369553508f79f92894c
+size 4153376052