Upload Muyan-TTS base model.

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 Muyan-TTS/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "saves/llama3.2-3b/full/pretrain-10wh/checkpoint-110000",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
+  "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": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "vocab_size": 129344
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.46.1"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eca8bc3e195817e3f470a839aa8cbcc4520da6e245700f51a86279ea90946e5a
+size 4972483768

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1466b06fdbd6a9741046987bf5aef5cb94f85646085e48bbdcc267a93640ff9f
+size 2254419664

model.safetensors.index.json

@@ -0,0 +1,262 @@
+{
+  "metadata": {
+    "total_size": 7226873856
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

sovits.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a926f836bbee2eb064b5249313d0ee79c71ce053f2e32db409e343dcdf4df9d0
+size 85007266

special_tokens_map.json

@@ -0,0 +1,1050 @@
+{
+  "additional_special_tokens": [
+    "<|audio_token_0|>",
+    "<|audio_token_1|>",
+    "<|audio_token_2|>",
+    "<|audio_token_3|>",
+    "<|audio_token_4|>",
+    "<|audio_token_5|>",
+    "<|audio_token_6|>",
+    "<|audio_token_7|>",
+    "<|audio_token_8|>",
+    "<|audio_token_9|>",
+    "<|audio_token_10|>",
+    "<|audio_token_11|>",
+    "<|audio_token_12|>",
+    "<|audio_token_13|>",
+    "<|audio_token_14|>",
+    "<|audio_token_15|>",
+    "<|audio_token_16|>",
+    "<|audio_token_17|>",
+    "<|audio_token_18|>",
+    "<|audio_token_19|>",
+    "<|audio_token_20|>",
+    "<|audio_token_21|>",
+    "<|audio_token_22|>",
+    "<|audio_token_23|>",
+    "<|audio_token_24|>",
+    "<|audio_token_25|>",
+    "<|audio_token_26|>",
+    "<|audio_token_27|>",
+    "<|audio_token_28|>",
+    "<|audio_token_29|>",
+    "<|audio_token_30|>",
+    "<|audio_token_31|>",
+    "<|audio_token_32|>",
+    "<|audio_token_33|>",
+    "<|audio_token_34|>",
+    "<|audio_token_35|>",
+    "<|audio_token_36|>",
+    "<|audio_token_37|>",
+    "<|audio_token_38|>",
+    "<|audio_token_39|>",
+    "<|audio_token_40|>",
+    "<|audio_token_41|>",
+    "<|audio_token_42|>",
+    "<|audio_token_43|>",
+    "<|audio_token_44|>",
+    "<|audio_token_45|>",
+    "<|audio_token_46|>",
+    "<|audio_token_47|>",
+    "<|audio_token_48|>",
+    "<|audio_token_49|>",
+    "<|audio_token_50|>",
+    "<|audio_token_51|>",
+    "<|audio_token_52|>",
+    "<|audio_token_53|>",
+    "<|audio_token_54|>",
+    "<|audio_token_55|>",
+    "<|audio_token_56|>",
+    "<|audio_token_57|>",
+    "<|audio_token_58|>",
+    "<|audio_token_59|>",
+    "<|audio_token_60|>",
+    "<|audio_token_61|>",
+    "<|audio_token_62|>",
+    "<|audio_token_63|>",
+    "<|audio_token_64|>",
+    "<|audio_token_65|>",
+    "<|audio_token_66|>",
+    "<|audio_token_67|>",
+    "<|audio_token_68|>",
+    "<|audio_token_69|>",
+    "<|audio_token_70|>",
+    "<|audio_token_71|>",
+    "<|audio_token_72|>",
+    "<|audio_token_73|>",
+    "<|audio_token_74|>",
+    "<|audio_token_75|>",
+    "<|audio_token_76|>",
+    "<|audio_token_77|>",
+    "<|audio_token_78|>",
+    "<|audio_token_79|>",
+    "<|audio_token_80|>",
+    "<|audio_token_81|>",
+    "<|audio_token_82|>",
+    "<|audio_token_83|>",
+    "<|audio_token_84|>",
+    "<|audio_token_85|>",
+    "<|audio_token_86|>",
+    "<|audio_token_87|>",
+    "<|audio_token_88|>",
+    "<|audio_token_89|>",
+    "<|audio_token_90|>",
+    "<|audio_token_91|>",
+    "<|audio_token_92|>",
+    "<|audio_token_93|>",
+    "<|audio_token_94|>",
+    "<|audio_token_95|>",
+    "<|audio_token_96|>",
+    "<|audio_token_97|>",
+    "<|audio_token_98|>",
+    "<|audio_token_99|>",
+    "<|audio_token_100|>",
+    "<|audio_token_101|>",
+    "<|audio_token_102|>",
+    "<|audio_token_103|>",
+    "<|audio_token_104|>",
+    "<|audio_token_105|>",
+    "<|audio_token_106|>",
+    "<|audio_token_107|>",
+    "<|audio_token_108|>",
+    "<|audio_token_109|>",
+    "<|audio_token_110|>",
+    "<|audio_token_111|>",
+    "<|audio_token_112|>",
+    "<|audio_token_113|>",
+    "<|audio_token_114|>",
+    "<|audio_token_115|>",
+    "<|audio_token_116|>",
+    "<|audio_token_117|>",
+    "<|audio_token_118|>",
+    "<|audio_token_119|>",
+    "<|audio_token_120|>",
+    "<|audio_token_121|>",
+    "<|audio_token_122|>",
+    "<|audio_token_123|>",
+    "<|audio_token_124|>",
+    "<|audio_token_125|>",
+    "<|audio_token_126|>",
+    "<|audio_token_127|>",
+    "<|audio_token_128|>",
+    "<|audio_token_129|>",
+    "<|audio_token_130|>",
+    "<|audio_token_131|>",
+    "<|audio_token_132|>",
+    "<|audio_token_133|>",
+    "<|audio_token_134|>",
+    "<|audio_token_135|>",
+    "<|audio_token_136|>",
+    "<|audio_token_137|>",
+    "<|audio_token_138|>",
+    "<|audio_token_139|>",
+    "<|audio_token_140|>",
+    "<|audio_token_141|>",
+    "<|audio_token_142|>",
+    "<|audio_token_143|>",
+    "<|audio_token_144|>",
+    "<|audio_token_145|>",
+    "<|audio_token_146|>",
+    "<|audio_token_147|>",
+    "<|audio_token_148|>",
+    "<|audio_token_149|>",
+    "<|audio_token_150|>",
+    "<|audio_token_151|>",
+    "<|audio_token_152|>",
+    "<|audio_token_153|>",
+    "<|audio_token_154|>",
+    "<|audio_token_155|>",
+    "<|audio_token_156|>",
+    "<|audio_token_157|>",
+    "<|audio_token_158|>",
+    "<|audio_token_159|>",
+    "<|audio_token_160|>",
+    "<|audio_token_161|>",
+    "<|audio_token_162|>",
+    "<|audio_token_163|>",
+    "<|audio_token_164|>",
+    "<|audio_token_165|>",
+    "<|audio_token_166|>",
+    "<|audio_token_167|>",
+    "<|audio_token_168|>",
+    "<|audio_token_169|>",
+    "<|audio_token_170|>",
+    "<|audio_token_171|>",
+    "<|audio_token_172|>",
+    "<|audio_token_173|>",
+    "<|audio_token_174|>",
+    "<|audio_token_175|>",
+    "<|audio_token_176|>",
+    "<|audio_token_177|>",
+    "<|audio_token_178|>",
+    "<|audio_token_179|>",
+    "<|audio_token_180|>",
+    "<|audio_token_181|>",
+    "<|audio_token_182|>",
+    "<|audio_token_183|>",
+    "<|audio_token_184|>",
+    "<|audio_token_185|>",
+    "<|audio_token_186|>",
+    "<|audio_token_187|>",
+    "<|audio_token_188|>",
+    "<|audio_token_189|>",
+    "<|audio_token_190|>",
+    "<|audio_token_191|>",
+    "<|audio_token_192|>",
+    "<|audio_token_193|>",
+    "<|audio_token_194|>",
+    "<|audio_token_195|>",
+    "<|audio_token_196|>",
+    "<|audio_token_197|>",
+    "<|audio_token_198|>",
+    "<|audio_token_199|>",
+    "<|audio_token_200|>",
+    "<|audio_token_201|>",
+    "<|audio_token_202|>",
+    "<|audio_token_203|>",
+    "<|audio_token_204|>",
+    "<|audio_token_205|>",
+    "<|audio_token_206|>",
+    "<|audio_token_207|>",
+    "<|audio_token_208|>",
+    "<|audio_token_209|>",
+    "<|audio_token_210|>",
+    "<|audio_token_211|>",
+    "<|audio_token_212|>",
+    "<|audio_token_213|>",
+    "<|audio_token_214|>",
+    "<|audio_token_215|>",
+    "<|audio_token_216|>",
+    "<|audio_token_217|>",
+    "<|audio_token_218|>",
+    "<|audio_token_219|>",
+    "<|audio_token_220|>",
+    "<|audio_token_221|>",
+    "<|audio_token_222|>",
+    "<|audio_token_223|>",
+    "<|audio_token_224|>",
+    "<|audio_token_225|>",
+    "<|audio_token_226|>",
+    "<|audio_token_227|>",
+    "<|audio_token_228|>",
+    "<|audio_token_229|>",
+    "<|audio_token_230|>",
+    "<|audio_token_231|>",
+    "<|audio_token_232|>",
+    "<|audio_token_233|>",
+    "<|audio_token_234|>",
+    "<|audio_token_235|>",
+    "<|audio_token_236|>",
+    "<|audio_token_237|>",
+    "<|audio_token_238|>",
+    "<|audio_token_239|>",
+    "<|audio_token_240|>",
+    "<|audio_token_241|>",
+    "<|audio_token_242|>",
+    "<|audio_token_243|>",
+    "<|audio_token_244|>",
+    "<|audio_token_245|>",
+    "<|audio_token_246|>",
+    "<|audio_token_247|>",
+    "<|audio_token_248|>",
+    "<|audio_token_249|>",
+    "<|audio_token_250|>",
+    "<|audio_token_251|>",
+    "<|audio_token_252|>",
+    "<|audio_token_253|>",
+    "<|audio_token_254|>",
+    "<|audio_token_255|>",
+    "<|audio_token_256|>",
+    "<|audio_token_257|>",
+    "<|audio_token_258|>",
+    "<|audio_token_259|>",
+    "<|audio_token_260|>",
+    "<|audio_token_261|>",
+    "<|audio_token_262|>",
+    "<|audio_token_263|>",
+    "<|audio_token_264|>",
+    "<|audio_token_265|>",
+    "<|audio_token_266|>",
+    "<|audio_token_267|>",
+    "<|audio_token_268|>",
+    "<|audio_token_269|>",
+    "<|audio_token_270|>",
+    "<|audio_token_271|>",
+    "<|audio_token_272|>",
+    "<|audio_token_273|>",
+    "<|audio_token_274|>",
+    "<|audio_token_275|>",
+    "<|audio_token_276|>",
+    "<|audio_token_277|>",
+    "<|audio_token_278|>",
+    "<|audio_token_279|>",
+    "<|audio_token_280|>",
+    "<|audio_token_281|>",
+    "<|audio_token_282|>",
+    "<|audio_token_283|>",
+    "<|audio_token_284|>",
+    "<|audio_token_285|>",
+    "<|audio_token_286|>",
+    "<|audio_token_287|>",
+    "<|audio_token_288|>",
+    "<|audio_token_289|>",
+    "<|audio_token_290|>",
+    "<|audio_token_291|>",
+    "<|audio_token_292|>",
+    "<|audio_token_293|>",
+    "<|audio_token_294|>",
+    "<|audio_token_295|>",
+    "<|audio_token_296|>",
+    "<|audio_token_297|>",
+    "<|audio_token_298|>",
+    "<|audio_token_299|>",
+    "<|audio_token_300|>",
+    "<|audio_token_301|>",
+    "<|audio_token_302|>",
+    "<|audio_token_303|>",
+    "<|audio_token_304|>",
+    "<|audio_token_305|>",
+    "<|audio_token_306|>",
+    "<|audio_token_307|>",
+    "<|audio_token_308|>",
+    "<|audio_token_309|>",
+    "<|audio_token_310|>",
+    "<|audio_token_311|>",
+    "<|audio_token_312|>",
+    "<|audio_token_313|>",
+    "<|audio_token_314|>",
+    "<|audio_token_315|>",
+    "<|audio_token_316|>",
+    "<|audio_token_317|>",
+    "<|audio_token_318|>",
+    "<|audio_token_319|>",
+    "<|audio_token_320|>",
+    "<|audio_token_321|>",
+    "<|audio_token_322|>",
+    "<|audio_token_323|>",
+    "<|audio_token_324|>",
+    "<|audio_token_325|>",
+    "<|audio_token_326|>",
+    "<|audio_token_327|>",
+    "<|audio_token_328|>",
+    "<|audio_token_329|>",
+    "<|audio_token_330|>",
+    "<|audio_token_331|>",
+    "<|audio_token_332|>",
+    "<|audio_token_333|>",
+    "<|audio_token_334|>",
+    "<|audio_token_335|>",
+    "<|audio_token_336|>",
+    "<|audio_token_337|>",
+    "<|audio_token_338|>",
+    "<|audio_token_339|>",
+    "<|audio_token_340|>",
+    "<|audio_token_341|>",
+    "<|audio_token_342|>",
+    "<|audio_token_343|>",
+    "<|audio_token_344|>",
+    "<|audio_token_345|>",
+    "<|audio_token_346|>",
+    "<|audio_token_347|>",
+    "<|audio_token_348|>",
+    "<|audio_token_349|>",
+    "<|audio_token_350|>",
+    "<|audio_token_351|>",
+    "<|audio_token_352|>",
+    "<|audio_token_353|>",
+    "<|audio_token_354|>",
+    "<|audio_token_355|>",
+    "<|audio_token_356|>",
+    "<|audio_token_357|>",
+    "<|audio_token_358|>",
+    "<|audio_token_359|>",
+    "<|audio_token_360|>",
+    "<|audio_token_361|>",
+    "<|audio_token_362|>",
+    "<|audio_token_363|>",
+    "<|audio_token_364|>",
+    "<|audio_token_365|>",
+    "<|audio_token_366|>",
+    "<|audio_token_367|>",
+    "<|audio_token_368|>",
+    "<|audio_token_369|>",
+    "<|audio_token_370|>",
+    "<|audio_token_371|>",
+    "<|audio_token_372|>",
+    "<|audio_token_373|>",
+    "<|audio_token_374|>",
+    "<|audio_token_375|>",
+    "<|audio_token_376|>",
+    "<|audio_token_377|>",
+    "<|audio_token_378|>",
+    "<|audio_token_379|>",
+    "<|audio_token_380|>",
+    "<|audio_token_381|>",
+    "<|audio_token_382|>",
+    "<|audio_token_383|>",
+    "<|audio_token_384|>",
+    "<|audio_token_385|>",
+    "<|audio_token_386|>",
+    "<|audio_token_387|>",
+    "<|audio_token_388|>",
+    "<|audio_token_389|>",
+    "<|audio_token_390|>",
+    "<|audio_token_391|>",
+    "<|audio_token_392|>",
+    "<|audio_token_393|>",
+    "<|audio_token_394|>",
+    "<|audio_token_395|>",
+    "<|audio_token_396|>",
+    "<|audio_token_397|>",
+    "<|audio_token_398|>",
+    "<|audio_token_399|>",
+    "<|audio_token_400|>",
+    "<|audio_token_401|>",
+    "<|audio_token_402|>",
+    "<|audio_token_403|>",
+    "<|audio_token_404|>",
+    "<|audio_token_405|>",
+    "<|audio_token_406|>",
+    "<|audio_token_407|>",
+    "<|audio_token_408|>",
+    "<|audio_token_409|>",
+    "<|audio_token_410|>",
+    "<|audio_token_411|>",
+    "<|audio_token_412|>",
+    "<|audio_token_413|>",
+    "<|audio_token_414|>",
+    "<|audio_token_415|>",
+    "<|audio_token_416|>",
+    "<|audio_token_417|>",
+    "<|audio_token_418|>",
+    "<|audio_token_419|>",
+    "<|audio_token_420|>",
+    "<|audio_token_421|>",
+    "<|audio_token_422|>",
+    "<|audio_token_423|>",
+    "<|audio_token_424|>",
+    "<|audio_token_425|>",
+    "<|audio_token_426|>",
+    "<|audio_token_427|>",
+    "<|audio_token_428|>",
+    "<|audio_token_429|>",
+    "<|audio_token_430|>",
+    "<|audio_token_431|>",
+    "<|audio_token_432|>",
+    "<|audio_token_433|>",
+    "<|audio_token_434|>",
+    "<|audio_token_435|>",
+    "<|audio_token_436|>",
+    "<|audio_token_437|>",
+    "<|audio_token_438|>",
+    "<|audio_token_439|>",
+    "<|audio_token_440|>",
+    "<|audio_token_441|>",
+    "<|audio_token_442|>",
+    "<|audio_token_443|>",
+    "<|audio_token_444|>",
+    "<|audio_token_445|>",
+    "<|audio_token_446|>",
+    "<|audio_token_447|>",
+    "<|audio_token_448|>",
+    "<|audio_token_449|>",
+    "<|audio_token_450|>",
+    "<|audio_token_451|>",
+    "<|audio_token_452|>",
+    "<|audio_token_453|>",
+    "<|audio_token_454|>",
+    "<|audio_token_455|>",
+    "<|audio_token_456|>",
+    "<|audio_token_457|>",
+    "<|audio_token_458|>",
+    "<|audio_token_459|>",
+    "<|audio_token_460|>",
+    "<|audio_token_461|>",
+    "<|audio_token_462|>",
+    "<|audio_token_463|>",
+    "<|audio_token_464|>",
+    "<|audio_token_465|>",
+    "<|audio_token_466|>",
+    "<|audio_token_467|>",
+    "<|audio_token_468|>",
+    "<|audio_token_469|>",
+    "<|audio_token_470|>",
+    "<|audio_token_471|>",
+    "<|audio_token_472|>",
+    "<|audio_token_473|>",
+    "<|audio_token_474|>",
+    "<|audio_token_475|>",
+    "<|audio_token_476|>",
+    "<|audio_token_477|>",
+    "<|audio_token_478|>",
+    "<|audio_token_479|>",
+    "<|audio_token_480|>",
+    "<|audio_token_481|>",
+    "<|audio_token_482|>",
+    "<|audio_token_483|>",
+    "<|audio_token_484|>",
+    "<|audio_token_485|>",
+    "<|audio_token_486|>",
+    "<|audio_token_487|>",
+    "<|audio_token_488|>",
+    "<|audio_token_489|>",
+    "<|audio_token_490|>",
+    "<|audio_token_491|>",
+    "<|audio_token_492|>",
+    "<|audio_token_493|>",
+    "<|audio_token_494|>",
+    "<|audio_token_495|>",
+    "<|audio_token_496|>",
+    "<|audio_token_497|>",
+    "<|audio_token_498|>",
+    "<|audio_token_499|>",
+    "<|audio_token_500|>",
+    "<|audio_token_501|>",
+    "<|audio_token_502|>",
+    "<|audio_token_503|>",
+    "<|audio_token_504|>",
+    "<|audio_token_505|>",
+    "<|audio_token_506|>",
+    "<|audio_token_507|>",
+    "<|audio_token_508|>",
+    "<|audio_token_509|>",
+    "<|audio_token_510|>",
+    "<|audio_token_511|>",
+    "<|audio_token_512|>",
+    "<|audio_token_513|>",
+    "<|audio_token_514|>",
+    "<|audio_token_515|>",
+    "<|audio_token_516|>",
+    "<|audio_token_517|>",
+    "<|audio_token_518|>",
+    "<|audio_token_519|>",
+    "<|audio_token_520|>",
+    "<|audio_token_521|>",
+    "<|audio_token_522|>",
+    "<|audio_token_523|>",
+    "<|audio_token_524|>",
+    "<|audio_token_525|>",
+    "<|audio_token_526|>",
+    "<|audio_token_527|>",
+    "<|audio_token_528|>",
+    "<|audio_token_529|>",
+    "<|audio_token_530|>",
+    "<|audio_token_531|>",
+    "<|audio_token_532|>",
+    "<|audio_token_533|>",
+    "<|audio_token_534|>",
+    "<|audio_token_535|>",
+    "<|audio_token_536|>",
+    "<|audio_token_537|>",
+    "<|audio_token_538|>",
+    "<|audio_token_539|>",
+    "<|audio_token_540|>",
+    "<|audio_token_541|>",
+    "<|audio_token_542|>",
+    "<|audio_token_543|>",
+    "<|audio_token_544|>",
+    "<|audio_token_545|>",
+    "<|audio_token_546|>",
+    "<|audio_token_547|>",
+    "<|audio_token_548|>",
+    "<|audio_token_549|>",
+    "<|audio_token_550|>",
+    "<|audio_token_551|>",
+    "<|audio_token_552|>",
+    "<|audio_token_553|>",
+    "<|audio_token_554|>",
+    "<|audio_token_555|>",
+    "<|audio_token_556|>",
+    "<|audio_token_557|>",
+    "<|audio_token_558|>",
+    "<|audio_token_559|>",
+    "<|audio_token_560|>",
+    "<|audio_token_561|>",
+    "<|audio_token_562|>",
+    "<|audio_token_563|>",
+    "<|audio_token_564|>",
+    "<|audio_token_565|>",
+    "<|audio_token_566|>",
+    "<|audio_token_567|>",
+    "<|audio_token_568|>",
+    "<|audio_token_569|>",
+    "<|audio_token_570|>",
+    "<|audio_token_571|>",
+    "<|audio_token_572|>",
+    "<|audio_token_573|>",
+    "<|audio_token_574|>",
+    "<|audio_token_575|>",
+    "<|audio_token_576|>",
+    "<|audio_token_577|>",
+    "<|audio_token_578|>",
+    "<|audio_token_579|>",
+    "<|audio_token_580|>",
+    "<|audio_token_581|>",
+    "<|audio_token_582|>",
+    "<|audio_token_583|>",
+    "<|audio_token_584|>",
+    "<|audio_token_585|>",
+    "<|audio_token_586|>",
+    "<|audio_token_587|>",
+    "<|audio_token_588|>",
+    "<|audio_token_589|>",
+    "<|audio_token_590|>",
+    "<|audio_token_591|>",
+    "<|audio_token_592|>",
+    "<|audio_token_593|>",
+    "<|audio_token_594|>",
+    "<|audio_token_595|>",
+    "<|audio_token_596|>",
+    "<|audio_token_597|>",
+    "<|audio_token_598|>",
+    "<|audio_token_599|>",
+    "<|audio_token_600|>",
+    "<|audio_token_601|>",
+    "<|audio_token_602|>",
+    "<|audio_token_603|>",
+    "<|audio_token_604|>",
+    "<|audio_token_605|>",
+    "<|audio_token_606|>",
+    "<|audio_token_607|>",
+    "<|audio_token_608|>",
+    "<|audio_token_609|>",
+    "<|audio_token_610|>",
+    "<|audio_token_611|>",
+    "<|audio_token_612|>",
+    "<|audio_token_613|>",
+    "<|audio_token_614|>",
+    "<|audio_token_615|>",
+    "<|audio_token_616|>",
+    "<|audio_token_617|>",
+    "<|audio_token_618|>",
+    "<|audio_token_619|>",
+    "<|audio_token_620|>",
+    "<|audio_token_621|>",
+    "<|audio_token_622|>",
+    "<|audio_token_623|>",
+    "<|audio_token_624|>",
+    "<|audio_token_625|>",
+    "<|audio_token_626|>",
+    "<|audio_token_627|>",
+    "<|audio_token_628|>",
+    "<|audio_token_629|>",
+    "<|audio_token_630|>",
+    "<|audio_token_631|>",
+    "<|audio_token_632|>",
+    "<|audio_token_633|>",
+    "<|audio_token_634|>",
+    "<|audio_token_635|>",
+    "<|audio_token_636|>",
+    "<|audio_token_637|>",
+    "<|audio_token_638|>",
+    "<|audio_token_639|>",
+    "<|audio_token_640|>",
+    "<|audio_token_641|>",
+    "<|audio_token_642|>",
+    "<|audio_token_643|>",
+    "<|audio_token_644|>",
+    "<|audio_token_645|>",
+    "<|audio_token_646|>",
+    "<|audio_token_647|>",
+    "<|audio_token_648|>",
+    "<|audio_token_649|>",
+    "<|audio_token_650|>",
+    "<|audio_token_651|>",
+    "<|audio_token_652|>",
+    "<|audio_token_653|>",
+    "<|audio_token_654|>",
+    "<|audio_token_655|>",
+    "<|audio_token_656|>",
+    "<|audio_token_657|>",
+    "<|audio_token_658|>",
+    "<|audio_token_659|>",
+    "<|audio_token_660|>",
+    "<|audio_token_661|>",
+    "<|audio_token_662|>",
+    "<|audio_token_663|>",
+    "<|audio_token_664|>",
+    "<|audio_token_665|>",
+    "<|audio_token_666|>",
+    "<|audio_token_667|>",
+    "<|audio_token_668|>",
+    "<|audio_token_669|>",
+    "<|audio_token_670|>",
+    "<|audio_token_671|>",
+    "<|audio_token_672|>",
+    "<|audio_token_673|>",
+    "<|audio_token_674|>",
+    "<|audio_token_675|>",
+    "<|audio_token_676|>",
+    "<|audio_token_677|>",
+    "<|audio_token_678|>",
+    "<|audio_token_679|>",
+    "<|audio_token_680|>",
+    "<|audio_token_681|>",
+    "<|audio_token_682|>",
+    "<|audio_token_683|>",
+    "<|audio_token_684|>",
+    "<|audio_token_685|>",
+    "<|audio_token_686|>",
+    "<|audio_token_687|>",
+    "<|audio_token_688|>",
+    "<|audio_token_689|>",
+    "<|audio_token_690|>",
+    "<|audio_token_691|>",
+    "<|audio_token_692|>",
+    "<|audio_token_693|>",
+    "<|audio_token_694|>",
+    "<|audio_token_695|>",
+    "<|audio_token_696|>",
+    "<|audio_token_697|>",
+    "<|audio_token_698|>",
+    "<|audio_token_699|>",
+    "<|audio_token_700|>",
+    "<|audio_token_701|>",
+    "<|audio_token_702|>",
+    "<|audio_token_703|>",
+    "<|audio_token_704|>",
+    "<|audio_token_705|>",
+    "<|audio_token_706|>",
+    "<|audio_token_707|>",
+    "<|audio_token_708|>",
+    "<|audio_token_709|>",
+    "<|audio_token_710|>",
+    "<|audio_token_711|>",
+    "<|audio_token_712|>",
+    "<|audio_token_713|>",
+    "<|audio_token_714|>",
+    "<|audio_token_715|>",
+    "<|audio_token_716|>",
+    "<|audio_token_717|>",
+    "<|audio_token_718|>",
+    "<|audio_token_719|>",
+    "<|audio_token_720|>",
+    "<|audio_token_721|>",
+    "<|audio_token_722|>",
+    "<|audio_token_723|>",
+    "<|audio_token_724|>",
+    "<|audio_token_725|>",
+    "<|audio_token_726|>",
+    "<|audio_token_727|>",
+    "<|audio_token_728|>",
+    "<|audio_token_729|>",
+    "<|audio_token_730|>",
+    "<|audio_token_731|>",
+    "<|audio_token_732|>",
+    "<|audio_token_733|>",
+    "<|audio_token_734|>",
+    "<|audio_token_735|>",
+    "<|audio_token_736|>",
+    "<|audio_token_737|>",
+    "<|audio_token_738|>",
+    "<|audio_token_739|>",
+    "<|audio_token_740|>",
+    "<|audio_token_741|>",
+    "<|audio_token_742|>",
+    "<|audio_token_743|>",
+    "<|audio_token_744|>",
+    "<|audio_token_745|>",
+    "<|audio_token_746|>",
+    "<|audio_token_747|>",
+    "<|audio_token_748|>",
+    "<|audio_token_749|>",
+    "<|audio_token_750|>",
+    "<|audio_token_751|>",
+    "<|audio_token_752|>",
+    "<|audio_token_753|>",
+    "<|audio_token_754|>",
+    "<|audio_token_755|>",
+    "<|audio_token_756|>",
+    "<|audio_token_757|>",
+    "<|audio_token_758|>",
+    "<|audio_token_759|>",
+    "<|audio_token_760|>",
+    "<|audio_token_761|>",
+    "<|audio_token_762|>",
+    "<|audio_token_763|>",
+    "<|audio_token_764|>",
+    "<|audio_token_765|>",
+    "<|audio_token_766|>",
+    "<|audio_token_767|>",
+    "<|audio_token_768|>",
+    "<|audio_token_769|>",
+    "<|audio_token_770|>",
+    "<|audio_token_771|>",
+    "<|audio_token_772|>",
+    "<|audio_token_773|>",
+    "<|audio_token_774|>",
+    "<|audio_token_775|>",
+    "<|audio_token_776|>",
+    "<|audio_token_777|>",
+    "<|audio_token_778|>",
+    "<|audio_token_779|>",
+    "<|audio_token_780|>",
+    "<|audio_token_781|>",
+    "<|audio_token_782|>",
+    "<|audio_token_783|>",
+    "<|audio_token_784|>",
+    "<|audio_token_785|>",
+    "<|audio_token_786|>",
+    "<|audio_token_787|>",
+    "<|audio_token_788|>",
+    "<|audio_token_789|>",
+    "<|audio_token_790|>",
+    "<|audio_token_791|>",
+    "<|audio_token_792|>",
+    "<|audio_token_793|>",
+    "<|audio_token_794|>",
+    "<|audio_token_795|>",
+    "<|audio_token_796|>",
+    "<|audio_token_797|>",
+    "<|audio_token_798|>",
+    "<|audio_token_799|>",
+    "<|audio_token_800|>",
+    "<|audio_token_801|>",
+    "<|audio_token_802|>",
+    "<|audio_token_803|>",
+    "<|audio_token_804|>",
+    "<|audio_token_805|>",
+    "<|audio_token_806|>",
+    "<|audio_token_807|>",
+    "<|audio_token_808|>",
+    "<|audio_token_809|>",
+    "<|audio_token_810|>",
+    "<|audio_token_811|>",
+    "<|audio_token_812|>",
+    "<|audio_token_813|>",
+    "<|audio_token_814|>",
+    "<|audio_token_815|>",
+    "<|audio_token_816|>",
+    "<|audio_token_817|>",
+    "<|audio_token_818|>",
+    "<|audio_token_819|>",
+    "<|audio_token_820|>",
+    "<|audio_token_821|>",
+    "<|audio_token_822|>",
+    "<|audio_token_823|>",
+    "<|audio_token_824|>",
+    "<|audio_token_825|>",
+    "<|audio_token_826|>",
+    "<|audio_token_827|>",
+    "<|audio_token_828|>",
+    "<|audio_token_829|>",
+    "<|audio_token_830|>",
+    "<|audio_token_831|>",
+    "<|audio_token_832|>",
+    "<|audio_token_833|>",
+    "<|audio_token_834|>",
+    "<|audio_token_835|>",
+    "<|audio_token_836|>",
+    "<|audio_token_837|>",
+    "<|audio_token_838|>",
+    "<|audio_token_839|>",
+    "<|audio_token_840|>",
+    "<|audio_token_841|>",
+    "<|audio_token_842|>",
+    "<|audio_token_843|>",
+    "<|audio_token_844|>",
+    "<|audio_token_845|>",
+    "<|audio_token_846|>",
+    "<|audio_token_847|>",
+    "<|audio_token_848|>",
+    "<|audio_token_849|>",
+    "<|audio_token_850|>",
+    "<|audio_token_851|>",
+    "<|audio_token_852|>",
+    "<|audio_token_853|>",
+    "<|audio_token_854|>",
+    "<|audio_token_855|>",
+    "<|audio_token_856|>",
+    "<|audio_token_857|>",
+    "<|audio_token_858|>",
+    "<|audio_token_859|>",
+    "<|audio_token_860|>",
+    "<|audio_token_861|>",
+    "<|audio_token_862|>",
+    "<|audio_token_863|>",
+    "<|audio_token_864|>",
+    "<|audio_token_865|>",
+    "<|audio_token_866|>",
+    "<|audio_token_867|>",
+    "<|audio_token_868|>",
+    "<|audio_token_869|>",
+    "<|audio_token_870|>",
+    "<|audio_token_871|>",
+    "<|audio_token_872|>",
+    "<|audio_token_873|>",
+    "<|audio_token_874|>",
+    "<|audio_token_875|>",
+    "<|audio_token_876|>",
+    "<|audio_token_877|>",
+    "<|audio_token_878|>",
+    "<|audio_token_879|>",
+    "<|audio_token_880|>",
+    "<|audio_token_881|>",
+    "<|audio_token_882|>",
+    "<|audio_token_883|>",
+    "<|audio_token_884|>",
+    "<|audio_token_885|>",
+    "<|audio_token_886|>",
+    "<|audio_token_887|>",
+    "<|audio_token_888|>",
+    "<|audio_token_889|>",
+    "<|audio_token_890|>",
+    "<|audio_token_891|>",
+    "<|audio_token_892|>",
+    "<|audio_token_893|>",
+    "<|audio_token_894|>",
+    "<|audio_token_895|>",
+    "<|audio_token_896|>",
+    "<|audio_token_897|>",
+    "<|audio_token_898|>",
+    "<|audio_token_899|>",
+    "<|audio_token_900|>",
+    "<|audio_token_901|>",
+    "<|audio_token_902|>",
+    "<|audio_token_903|>",
+    "<|audio_token_904|>",
+    "<|audio_token_905|>",
+    "<|audio_token_906|>",
+    "<|audio_token_907|>",
+    "<|audio_token_908|>",
+    "<|audio_token_909|>",
+    "<|audio_token_910|>",
+    "<|audio_token_911|>",
+    "<|audio_token_912|>",
+    "<|audio_token_913|>",
+    "<|audio_token_914|>",
+    "<|audio_token_915|>",
+    "<|audio_token_916|>",
+    "<|audio_token_917|>",
+    "<|audio_token_918|>",
+    "<|audio_token_919|>",
+    "<|audio_token_920|>",
+    "<|audio_token_921|>",
+    "<|audio_token_922|>",
+    "<|audio_token_923|>",
+    "<|audio_token_924|>",
+    "<|audio_token_925|>",
+    "<|audio_token_926|>",
+    "<|audio_token_927|>",
+    "<|audio_token_928|>",
+    "<|audio_token_929|>",
+    "<|audio_token_930|>",
+    "<|audio_token_931|>",
+    "<|audio_token_932|>",
+    "<|audio_token_933|>",
+    "<|audio_token_934|>",
+    "<|audio_token_935|>",
+    "<|audio_token_936|>",
+    "<|audio_token_937|>",
+    "<|audio_token_938|>",
+    "<|audio_token_939|>",
+    "<|audio_token_940|>",
+    "<|audio_token_941|>",
+    "<|audio_token_942|>",
+    "<|audio_token_943|>",
+    "<|audio_token_944|>",
+    "<|audio_token_945|>",
+    "<|audio_token_946|>",
+    "<|audio_token_947|>",
+    "<|audio_token_948|>",
+    "<|audio_token_949|>",
+    "<|audio_token_950|>",
+    "<|audio_token_951|>",
+    "<|audio_token_952|>",
+    "<|audio_token_953|>",
+    "<|audio_token_954|>",
+    "<|audio_token_955|>",
+    "<|audio_token_956|>",
+    "<|audio_token_957|>",
+    "<|audio_token_958|>",
+    "<|audio_token_959|>",
+    "<|audio_token_960|>",
+    "<|audio_token_961|>",
+    "<|audio_token_962|>",
+    "<|audio_token_963|>",
+    "<|audio_token_964|>",
+    "<|audio_token_965|>",
+    "<|audio_token_966|>",
+    "<|audio_token_967|>",
+    "<|audio_token_968|>",
+    "<|audio_token_969|>",
+    "<|audio_token_970|>",
+    "<|audio_token_971|>",
+    "<|audio_token_972|>",
+    "<|audio_token_973|>",
+    "<|audio_token_974|>",
+    "<|audio_token_975|>",
+    "<|audio_token_976|>",
+    "<|audio_token_977|>",
+    "<|audio_token_978|>",
+    "<|audio_token_979|>",
+    "<|audio_token_980|>",
+    "<|audio_token_981|>",
+    "<|audio_token_982|>",
+    "<|audio_token_983|>",
+    "<|audio_token_984|>",
+    "<|audio_token_985|>",
+    "<|audio_token_986|>",
+    "<|audio_token_987|>",
+    "<|audio_token_988|>",
+    "<|audio_token_989|>",
+    "<|audio_token_990|>",
+    "<|audio_token_991|>",
+    "<|audio_token_992|>",
+    "<|audio_token_993|>",
+    "<|audio_token_994|>",
+    "<|audio_token_995|>",
+    "<|audio_token_996|>",
+    "<|audio_token_997|>",
+    "<|audio_token_998|>",
+    "<|audio_token_999|>",
+    "<|audio_token_1000|>",
+    "<|audio_token_1001|>",
+    "<|audio_token_1002|>",
+    "<|audio_token_1003|>",
+    "<|audio_token_1004|>",
+    "<|audio_token_1005|>",
+    "<|audio_token_1006|>",
+    "<|audio_token_1007|>",
+    "<|audio_token_1008|>",
+    "<|audio_token_1009|>",
+    "<|audio_token_1010|>",
+    "<|audio_token_1011|>",
+    "<|audio_token_1012|>",
+    "<|audio_token_1013|>",
+    "<|audio_token_1014|>",
+    "<|audio_token_1015|>",
+    "<|audio_token_1016|>",
+    "<|audio_token_1017|>",
+    "<|audio_token_1018|>",
+    "<|audio_token_1019|>",
+    "<|audio_token_1020|>",
+    "<|audio_token_1021|>",
+    "<|audio_token_1022|>",
+    "<|audio_token_1023|>",
+    "<|audio_token_end|>"
+  ],
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63073cea824329b6a7c8735dd147d86e5655bcef2b1dda93c034d1709560f565
+size 17410734