Upload folder using huggingface_hub

config.json

@@ -0,0 +1,78 @@
+{
+  "architectures": [
+    "ConversationalSpeechModelForCausalLM"
+  ],
+  "backbone_config": {
+    "_attn_implementation_autoset": true,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "codebook_pad_token_id": 2050,
+    "codebook_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": "conversational_speech_model_backbone",
+    "num_attention_heads": 32,
+    "num_codebooks": 32,
+    "num_hidden_layers": 16,
+    "num_key_value_heads": 8,
+    "pretraining_tp": 1,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": {
+      "factor": 32.0,
+      "high_freq_factor": 4.0,
+      "low_freq_factor": 1.0,
+      "original_max_position_embeddings": 8192,
+      "rope_type": "llama3"
+    },
+    "rope_theta": 500000,
+    "use_cache": true,
+    "vocab_size": 128256,
+    "_attn_implementation": "sdpa"
+  },
+  "depth_decoder_config": {
+    "_attn_implementation_autoset": true,
+    "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": 32,
+    "mlp_bias": false,
+    "model_type": "conversational_speech_model_depth_decoder",
+    "num_attention_heads": 8,
+    "num_codebooks": 32,
+    "num_hidden_layers": 4,
+    "num_key_value_heads": 2,
+    "pretraining_tp": 1,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": {
+      "factor": 32.0,
+      "high_freq_factor": 4.0,
+      "low_freq_factor": 1.0,
+      "original_max_position_embeddings": 8192,
+      "rope_type": "llama3"
+    },
+    "rope_theta": 500000,
+    "use_cache": true,
+    "vocab_size": 2051,
+    "_attn_implementation": "sdpa"
+  },
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 2048,
+  "model_type": "conversational_speech_model",
+  "num_codebooks": 32,
+  "tie_codebook_embeddings": true,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.0.dev0",
+  "vocab_size": 2051
+}

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.50.0.dev0"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a21bbbe74c6a9d4181c6057ea9d7b59f3291af2d49b15e53f02359f75f278ae6
+size 4978703104

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29a47bc58bc7b74dd21dde527914ee47f4fcc41f3567d694235fdc65d41f38e7
+size 1770143784

model.safetensors.index.json

@@ -0,0 +1,195 @@
+{
+  "metadata": {
+    "total_size": 6748823552
+  },
+  "weight_map": {
+    "backbone_model.embed_tokens.embed_audio_tokens.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.embed_tokens.embed_text_tokens.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.10.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.12.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.12.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone_model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone_model.norm.weight": "model-00002-of-00002.safetensors",
+    "depth_decoder.codebooks_head.weight": "model-00001-of-00002.safetensors",
+    "depth_decoder.model.embed_tokens.embed_audio_tokens.weight": "model-00001-of-00002.safetensors",
+    "depth_decoder.model.inputs_embeds_projector.weight": "model-00001-of-00002.safetensors",
+    "depth_decoder.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "depth_decoder.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "depth_decoder.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "depth_decoder.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "depth_decoder.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "depth_decoder.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "depth_decoder.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "depth_decoder.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "depth_decoder.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "depth_decoder.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "depth_decoder.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "depth_decoder.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "depth_decoder.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "depth_decoder.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "depth_decoder.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "depth_decoder.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "depth_decoder.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "depth_decoder.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "depth_decoder.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "depth_decoder.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "depth_decoder.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "depth_decoder.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "depth_decoder.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "depth_decoder.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "depth_decoder.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "depth_decoder.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "depth_decoder.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "depth_decoder.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "depth_decoder.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "depth_decoder.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "depth_decoder.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "depth_decoder.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "depth_decoder.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "depth_decoder.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "depth_decoder.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "depth_decoder.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "depth_decoder.model.norm.weight": "model-00001-of-00002.safetensors",
+    "lm_head.weight": "model-00001-of-00002.safetensors"
+  }
+}