Upload folder using huggingface_hub

config.json

@@ -0,0 +1,55 @@
+{
+  "_name_or_path": "exp/omni_stage_one/checkpoint-5000",
+  "architectures": [
+    "OmniSpeech2SLlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "ctc_decoder_config": "(2,4096,32,11008)",
+  "ctc_loss_weight": 1.0,
+  "ctc_upsample_factor": 25,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "freeze_speech_projector": false,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "omni_speech2s_llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "speech_encoder": "models/speech_encoder/large-v3.pt",
+  "speech_encoder_ds_rate": 5,
+  "speech_encoder_hidden_size": 1280,
+  "speech_encoder_type": "whisper",
+  "speech_generator_type": "ctc",
+  "speech_normalize": false,
+  "speech_projector_lr": null,
+  "speech_projector_type": "linear",
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 2048,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.4",
+  "tune_speech_projector": false,
+  "unit_vocab_size": 1000,
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "attn_implementation": "flash_attention_2",
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.43.4"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc5bccee62b04d1b3057209fcbc9edd9a178582faa32661320586688cafebaea
+size 4976698672

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f1ffb5128a2d417b47dc9113a1de023cef81fec83ac85a6bcf9b75ae63f2111
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be92a8a682096958d7ed1c134e850940ba6035b8b434ff76406dc8fbc9abb71f
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5279044cf9532d2cdaf5c9f90127a49d96600f1e170a9c99c726fda15b9e43d5
+size 3336440482

model.safetensors.index.json

@@ -0,0 +1,811 @@
+{
+  "metadata": {
+    "total_size": 18228762578
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.0.attn.key.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.0.attn.out.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.0.attn.out.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.0.attn.query.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.0.attn.query.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.0.attn.value.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.0.attn.value.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.0.attn_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.0.attn_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.0.mlp.0.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.0.mlp.0.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.0.mlp.2.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.0.mlp.2.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.0.mlp_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.0.mlp_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.1.attn.key.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.1.attn.out.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.1.attn.out.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.1.attn.query.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.1.attn.query.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.1.attn.value.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.1.attn.value.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.1.attn_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.1.attn_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.1.mlp.0.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.1.mlp.0.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.1.mlp.2.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.1.mlp.2.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.1.mlp_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.1.mlp_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.10.attn.key.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.10.attn.out.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.10.attn.out.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.10.attn.query.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.10.attn.query.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.10.attn.value.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.10.attn.value.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.10.attn_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.10.attn_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.10.mlp.0.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.10.mlp.0.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.10.mlp.2.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.10.mlp.2.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.10.mlp_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.10.mlp_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.11.attn.key.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.11.attn.out.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.11.attn.out.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.11.attn.query.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.11.attn.query.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.11.attn.value.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.11.attn.value.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.11.attn_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.11.attn_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.11.mlp.0.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.11.mlp.0.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.11.mlp.2.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.11.mlp.2.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.11.mlp_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.11.mlp_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.12.attn.key.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.12.attn.out.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.12.attn.out.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.12.attn.query.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.12.attn.query.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.12.attn.value.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.12.attn.value.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.12.attn_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.12.attn_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.12.mlp.0.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.12.mlp.0.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.12.mlp.2.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.12.mlp.2.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.12.mlp_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.12.mlp_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.13.attn.key.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.13.attn.out.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.13.attn.out.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.13.attn.query.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.13.attn.query.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.13.attn.value.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.13.attn.value.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.13.attn_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.13.attn_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.13.mlp.0.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.13.mlp.0.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.13.mlp.2.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.13.mlp.2.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.13.mlp_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.13.mlp_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.14.attn.key.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.14.attn.out.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.14.attn.out.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.14.attn.query.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.14.attn.query.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.14.attn.value.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.14.attn.value.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.14.attn_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.14.attn_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.14.mlp.0.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.14.mlp.0.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.14.mlp.2.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.14.mlp.2.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.14.mlp_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.14.mlp_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.15.attn.key.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.15.attn.out.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.15.attn.out.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.15.attn.query.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.15.attn.query.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.15.attn.value.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.15.attn.value.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.15.attn_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.15.attn_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.15.mlp.0.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.15.mlp.0.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.15.mlp.2.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.15.mlp.2.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.15.mlp_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.15.mlp_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.16.attn.key.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.16.attn.out.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.16.attn.out.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.16.attn.query.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.16.attn.query.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.16.attn.value.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.16.attn.value.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.16.attn_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.16.attn_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.16.mlp.0.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.16.mlp.0.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.16.mlp.2.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.16.mlp.2.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.16.mlp_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.16.mlp_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.17.attn.key.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.17.attn.out.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.17.attn.out.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.17.attn.query.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.17.attn.query.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.17.attn.value.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.17.attn.value.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.17.attn_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.17.attn_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.17.mlp.0.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.17.mlp.0.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.17.mlp.2.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.17.mlp.2.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.17.mlp_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.17.mlp_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.18.attn.key.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.18.attn.out.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.18.attn.out.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.18.attn.query.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.18.attn.query.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.18.attn.value.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.18.attn.value.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.18.attn_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.18.attn_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.18.mlp.0.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.18.mlp.0.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.18.mlp.2.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.18.mlp.2.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.18.mlp_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.18.mlp_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.19.attn.key.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.19.attn.out.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.19.attn.out.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.19.attn.query.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.19.attn.query.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.19.attn.value.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.19.attn.value.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.19.attn_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.19.attn_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.19.mlp.0.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.19.mlp.0.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.19.mlp.2.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.19.mlp.2.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.19.mlp_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.19.mlp_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.2.attn.key.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.2.attn.out.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.2.attn.out.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.2.attn.query.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.2.attn.query.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.2.attn.value.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.2.attn.value.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.2.attn_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.2.attn_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.2.mlp.0.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.2.mlp.0.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.2.mlp.2.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.2.mlp.2.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.2.mlp_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.2.mlp_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.20.attn.key.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.20.attn.out.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.20.attn.out.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.20.attn.query.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.20.attn.query.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.20.attn.value.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.20.attn.value.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.20.attn_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.20.attn_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.20.mlp.0.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.20.mlp.0.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.20.mlp.2.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.20.mlp.2.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.20.mlp_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.20.mlp_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.21.attn.key.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.21.attn.out.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.21.attn.out.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.21.attn.query.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.21.attn.query.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.21.attn.value.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.21.attn.value.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.21.attn_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.21.attn_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.21.mlp.0.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.21.mlp.0.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.21.mlp.2.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.21.mlp.2.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.21.mlp_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.21.mlp_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.22.attn.key.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.22.attn.out.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.22.attn.out.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.22.attn.query.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.22.attn.query.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.22.attn.value.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.22.attn.value.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.22.attn_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.22.attn_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.22.mlp.0.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.22.mlp.0.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.22.mlp.2.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.22.mlp.2.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.22.mlp_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.22.mlp_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.23.attn.key.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.23.attn.out.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.23.attn.out.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.23.attn.query.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.23.attn.query.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.23.attn.value.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.23.attn.value.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.23.attn_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.23.attn_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.23.mlp.0.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.23.mlp.0.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.23.mlp.2.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.23.mlp.2.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.23.mlp_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.23.mlp_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.24.attn.key.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.24.attn.out.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.24.attn.out.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.24.attn.query.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.24.attn.query.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.24.attn.value.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.24.attn.value.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.24.attn_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.24.attn_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.24.mlp.0.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.24.mlp.0.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.24.mlp.2.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.24.mlp.2.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.24.mlp_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.24.mlp_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.25.attn.key.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.25.attn.out.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.25.attn.out.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.25.attn.query.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.25.attn.query.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.25.attn.value.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.25.attn.value.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.25.attn_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.25.attn_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.25.mlp.0.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.25.mlp.0.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.25.mlp.2.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.25.mlp.2.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.25.mlp_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.25.mlp_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.26.attn.key.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.26.attn.out.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.26.attn.out.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.26.attn.query.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.26.attn.query.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.26.attn.value.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.26.attn.value.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.26.attn_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.26.attn_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.26.mlp.0.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.26.mlp.0.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.26.mlp.2.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.26.mlp.2.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.26.mlp_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.26.mlp_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.27.attn.key.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.27.attn.out.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.27.attn.out.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.27.attn.query.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.27.attn.query.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.27.attn.value.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.27.attn.value.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.27.attn_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.27.attn_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.27.mlp.0.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.27.mlp.0.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.27.mlp.2.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.27.mlp.2.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.27.mlp_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.27.mlp_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.28.attn.key.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.28.attn.out.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.28.attn.out.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.28.attn.query.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.28.attn.query.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.28.attn.value.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.28.attn.value.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.28.attn_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.28.attn_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.28.mlp.0.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.28.mlp.0.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.28.mlp.2.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.28.mlp.2.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.28.mlp_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.28.mlp_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.29.attn.key.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.29.attn.out.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.29.attn.out.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.29.attn.query.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.29.attn.query.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.29.attn.value.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.29.attn.value.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.29.attn_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.29.attn_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.29.mlp.0.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.29.mlp.0.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.29.mlp.2.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.29.mlp.2.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.29.mlp_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.29.mlp_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.3.attn.key.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.3.attn.out.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.3.attn.out.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.3.attn.query.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.3.attn.query.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.3.attn.value.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.3.attn.value.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.3.attn_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.3.attn_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.3.mlp.0.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.3.mlp.0.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.3.mlp.2.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.3.mlp.2.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.3.mlp_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.3.mlp_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.30.attn.key.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.30.attn.out.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.30.attn.out.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.30.attn.query.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.30.attn.query.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.30.attn.value.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.30.attn.value.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.30.attn_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.30.attn_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.30.mlp.0.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.30.mlp.0.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.30.mlp.2.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.30.mlp.2.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.30.mlp_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.30.mlp_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.31.attn.key.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.31.attn.out.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.31.attn.out.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.31.attn.query.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.31.attn.query.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.31.attn.value.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.31.attn.value.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.31.attn_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.31.attn_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.31.mlp.0.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.31.mlp.0.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.31.mlp.2.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.31.mlp.2.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.31.mlp_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.31.mlp_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.4.attn.key.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.4.attn.out.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.4.attn.out.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.4.attn.query.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.4.attn.query.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.4.attn.value.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.4.attn.value.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.4.attn_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.4.attn_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.4.mlp.0.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.4.mlp.0.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.4.mlp.2.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.4.mlp.2.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.4.mlp_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.4.mlp_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.5.attn.key.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.5.attn.out.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.5.attn.out.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.5.attn.query.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.5.attn.query.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.5.attn.value.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.5.attn.value.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.5.attn_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.5.attn_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.5.mlp.0.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.5.mlp.0.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.5.mlp.2.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.5.mlp.2.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.5.mlp_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.5.mlp_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.6.attn.key.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.6.attn.out.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.6.attn.out.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.6.attn.query.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.6.attn.query.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.6.attn.value.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.6.attn.value.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.6.attn_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.6.attn_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.6.mlp.0.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.6.mlp.0.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.6.mlp.2.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.6.mlp.2.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.6.mlp_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.6.mlp_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.7.attn.key.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.7.attn.out.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.7.attn.out.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.7.attn.query.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.7.attn.query.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.7.attn.value.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.7.attn.value.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.7.attn_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.7.attn_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.7.mlp.0.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.7.mlp.0.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.7.mlp.2.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.7.mlp.2.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.7.mlp_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.7.mlp_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.8.attn.key.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.8.attn.out.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.8.attn.out.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.8.attn.query.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.8.attn.query.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.8.attn.value.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.8.attn.value.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.8.attn_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.8.attn_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.8.mlp.0.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.8.mlp.0.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.8.mlp.2.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.8.mlp.2.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.8.mlp_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.8.mlp_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.9.attn.key.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.9.attn.out.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.9.attn.out.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.9.attn.query.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.9.attn.query.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.9.attn.value.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.9.attn.value.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.9.attn_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.9.attn_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.9.mlp.0.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.9.mlp.0.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.9.mlp.2.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.9.mlp.2.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.9.mlp_ln.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.blocks.9.mlp_ln.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.conv1.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.conv1.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.conv2.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.conv2.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.ln_post.bias": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.ln_post.weight": "model-00004-of-00004.safetensors",
+    "model.speech_encoder.positional_embedding": "model-00004-of-00004.safetensors",
+    "model.speech_projector.linear1.bias": "model-00004-of-00004.safetensors",
+    "model.speech_projector.linear1.weight": "model-00004-of-00004.safetensors",
+    "model.speech_projector.linear2.bias": "model-00004-of-00004.safetensors",
+    "model.speech_projector.linear2.weight": "model-00004-of-00004.safetensors",
+    "speech_generator.input_proj.bias": "model-00004-of-00004.safetensors",
+    "speech_generator.input_proj.weight": "model-00004-of-00004.safetensors",
+    "speech_generator.layers.0.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "speech_generator.layers.0.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "speech_generator.layers.0.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "speech_generator.layers.0.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "speech_generator.layers.0.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "speech_generator.layers.0.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "speech_generator.layers.0.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "speech_generator.layers.0.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "speech_generator.layers.0.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "speech_generator.layers.1.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "speech_generator.layers.1.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "speech_generator.layers.1.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "speech_generator.layers.1.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "speech_generator.layers.1.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "speech_generator.layers.1.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "speech_generator.layers.1.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "speech_generator.layers.1.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "speech_generator.layers.1.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "speech_generator.output_proj.bias": "model-00004-of-00004.safetensors",
+    "speech_generator.output_proj.weight": "model-00004-of-00004.safetensors"
+  }
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a374ab360379d183782e173f56c6012072e6225661da133a61be1a17b3ec9a5
+size 1702615388

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd48ca851da3b9968ab595a899ed04e6155409b6a04dba466a80def8c1865a90
+size 14960

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5163f01b3663509877285450560f031095e1f576469aaf8c388ef4971fc9273f
+size 14960

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2eada62bc7b1d2913cae299b55164e3b8ebfe509d6b9fbc781534b94bcabde33
+size 14960

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3ce657a6f44cc3affe6592ef2f1142d06809f2a796cbf83973dfdafa940bce8
+size 14960

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cf2fb2f5acd035e47dec2811c3b19bb005fa796ba6776bd84d9eb2858012bcd
+size 1000

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "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": "<|eot_id|>"
+}

tokenizer_config.json

@@ -0,0 +1,2065 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 2048,
+  "pad_token": "<|eot_id|>",
+  "padding": true,
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

trainer_state.json

@@ -0,0 +1,841 @@
+{
+  "best_metric": 0.5067562460899353,
+  "best_model_checkpoint": "/scratch/mriyadh/llama_omni_asr_tts/exp/omni_stage_two_full/checkpoint-300",
+  "epoch": 59.171597633136095,
+  "eval_steps": 300,
+  "global_step": 20000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8875739644970414,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.6641,
+      "eval_samples_per_second": 36.821,
+      "eval_steps_per_second": 2.318,
+      "step": 300
+    },
+    {
+      "epoch": 1.4792899408284024,
+      "grad_norm": 86.5,
+      "learning_rate": 0.0001666666666666667,
+      "loss": 11.072,
+      "step": 500
+    },
+    {
+      "epoch": 1.7751479289940828,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.8455,
+      "eval_samples_per_second": 36.64,
+      "eval_steps_per_second": 2.307,
+      "step": 600
+    },
+    {
+      "epoch": 2.662721893491124,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.7706,
+      "eval_samples_per_second": 36.714,
+      "eval_steps_per_second": 2.312,
+      "step": 900
+    },
+    {
+      "epoch": 2.9585798816568047,
+      "grad_norm": 32.75,
+      "learning_rate": 0.00019979028262377118,
+      "loss": 5.0622,
+      "step": 1000
+    },
+    {
+      "epoch": 3.5502958579881656,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.9679,
+      "eval_samples_per_second": 36.518,
+      "eval_steps_per_second": 2.299,
+      "step": 1200
+    },
+    {
+      "epoch": 4.437869822485207,
+      "grad_norm": 31.0,
+      "learning_rate": 0.00019893981312363562,
+      "loss": 3.234,
+      "step": 1500
+    },
+    {
+      "epoch": 4.437869822485207,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.907,
+      "eval_samples_per_second": 36.578,
+      "eval_steps_per_second": 2.303,
+      "step": 1500
+    },
+    {
+      "epoch": 5.325443786982248,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.8765,
+      "eval_samples_per_second": 36.609,
+      "eval_steps_per_second": 2.305,
+      "step": 1800
+    },
+    {
+      "epoch": 5.9171597633136095,
+      "grad_norm": 6.96875,
+      "learning_rate": 0.00019744105246469263,
+      "loss": 2.5031,
+      "step": 2000
+    },
+    {
+      "epoch": 6.21301775147929,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.7905,
+      "eval_samples_per_second": 36.694,
+      "eval_steps_per_second": 2.31,
+      "step": 2100
+    },
+    {
+      "epoch": 7.100591715976331,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.8163,
+      "eval_samples_per_second": 36.669,
+      "eval_steps_per_second": 2.309,
+      "step": 2400
+    },
+    {
+      "epoch": 7.396449704142012,
+      "grad_norm": 6.5625,
+      "learning_rate": 0.0001953038210948861,
+      "loss": 2.0242,
+      "step": 2500
+    },
+    {
+      "epoch": 7.988165680473373,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.9078,
+      "eval_samples_per_second": 36.578,
+      "eval_steps_per_second": 2.303,
+      "step": 2700
+    },
+    {
+      "epoch": 8.875739644970414,
+      "grad_norm": 10.875,
+      "learning_rate": 0.00019254212296427044,
+      "loss": 1.7989,
+      "step": 3000
+    },
+    {
+      "epoch": 8.875739644970414,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.9591,
+      "eval_samples_per_second": 36.527,
+      "eval_steps_per_second": 2.3,
+      "step": 3000
+    },
+    {
+      "epoch": 9.763313609467456,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.8178,
+      "eval_samples_per_second": 36.667,
+      "eval_steps_per_second": 2.309,
+      "step": 3300
+    },
+    {
+      "epoch": 10.355029585798816,
+      "grad_norm": 9.375,
+      "learning_rate": 0.00018917405376582145,
+      "loss": 1.5521,
+      "step": 3500
+    },
+    {
+      "epoch": 10.650887573964496,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.5472,
+      "eval_samples_per_second": 36.939,
+      "eval_steps_per_second": 2.326,
+      "step": 3600
+    },
+    {
+      "epoch": 11.538461538461538,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.7909,
+      "eval_samples_per_second": 36.694,
+      "eval_steps_per_second": 2.31,
+      "step": 3900
+    },
+    {
+      "epoch": 11.834319526627219,
+      "grad_norm": 5.875,
+      "learning_rate": 0.00018522168236559695,
+      "loss": 1.3787,
+      "step": 4000
+    },
+    {
+      "epoch": 12.42603550295858,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.9259,
+      "eval_samples_per_second": 36.56,
+      "eval_steps_per_second": 2.302,
+      "step": 4200
+    },
+    {
+      "epoch": 13.31360946745562,
+      "grad_norm": 4.5625,
+      "learning_rate": 0.00018071090619916093,
+      "loss": 1.2505,
+      "step": 4500
+    },
+    {
+      "epoch": 13.31360946745562,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.8178,
+      "eval_samples_per_second": 36.667,
+      "eval_steps_per_second": 2.309,
+      "step": 4500
+    },
+    {
+      "epoch": 14.201183431952662,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.8898,
+      "eval_samples_per_second": 36.596,
+      "eval_steps_per_second": 2.304,
+      "step": 4800
+    },
+    {
+      "epoch": 14.792899408284024,
+      "grad_norm": 3.921875,
+      "learning_rate": 0.00017567128158176953,
+      "loss": 1.1568,
+      "step": 5000
+    },
+    {
+      "epoch": 15.088757396449704,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.6043,
+      "eval_samples_per_second": 36.881,
+      "eval_steps_per_second": 2.322,
+      "step": 5100
+    },
+    {
+      "epoch": 15.976331360946746,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.8561,
+      "eval_samples_per_second": 36.629,
+      "eval_steps_per_second": 2.306,
+      "step": 5400
+    },
+    {
+      "epoch": 16.272189349112427,
+      "grad_norm": 2.984375,
+      "learning_rate": 0.00017013583004418993,
+      "loss": 1.0789,
+      "step": 5500
+    },
+    {
+      "epoch": 16.86390532544379,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.913,
+      "eval_samples_per_second": 36.572,
+      "eval_steps_per_second": 2.303,
+      "step": 5700
+    },
+    {
+      "epoch": 17.75147928994083,
+      "grad_norm": 3.53125,
+      "learning_rate": 0.000164140821963114,
+      "loss": 0.9769,
+      "step": 6000
+    },
+    {
+      "epoch": 17.75147928994083,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.802,
+      "eval_samples_per_second": 36.683,
+      "eval_steps_per_second": 2.31,
+      "step": 6000
+    },
+    {
+      "epoch": 18.63905325443787,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.9543,
+      "eval_samples_per_second": 36.532,
+      "eval_steps_per_second": 2.3,
+      "step": 6300
+    },
+    {
+      "epoch": 19.23076923076923,
+      "grad_norm": 3.046875,
+      "learning_rate": 0.00015772553890390197,
+      "loss": 0.913,
+      "step": 6500
+    },
+    {
+      "epoch": 19.526627218934912,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 37.0561,
+      "eval_samples_per_second": 36.431,
+      "eval_steps_per_second": 2.294,
+      "step": 6600
+    },
+    {
+      "epoch": 20.414201183431953,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.9,
+      "eval_samples_per_second": 36.585,
+      "eval_steps_per_second": 2.304,
+      "step": 6900
+    },
+    {
+      "epoch": 20.71005917159763,
+      "grad_norm": 3.1875,
+      "learning_rate": 0.00015093201623287631,
+      "loss": 0.8395,
+      "step": 7000
+    },
+    {
+      "epoch": 21.301775147928993,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.8939,
+      "eval_samples_per_second": 36.591,
+      "eval_steps_per_second": 2.304,
+      "step": 7200
+    },
+    {
+      "epoch": 22.189349112426036,
+      "grad_norm": 2.765625,
+      "learning_rate": 0.00014380476768566824,
+      "loss": 0.7613,
+      "step": 7500
+    },
+    {
+      "epoch": 22.189349112426036,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 37.0429,
+      "eval_samples_per_second": 36.444,
+      "eval_steps_per_second": 2.295,
+      "step": 7500
+    },
+    {
+      "epoch": 23.076923076923077,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.8494,
+      "eval_samples_per_second": 36.636,
+      "eval_steps_per_second": 2.307,
+      "step": 7800
+    },
+    {
+      "epoch": 23.668639053254438,
+      "grad_norm": 3.359375,
+      "learning_rate": 0.00013639049369634876,
+      "loss": 0.7133,
+      "step": 8000
+    },
+    {
+      "epoch": 23.964497041420117,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.6719,
+      "eval_samples_per_second": 36.813,
+      "eval_steps_per_second": 2.318,
+      "step": 8100
+    },
+    {
+      "epoch": 24.85207100591716,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.8698,
+      "eval_samples_per_second": 36.615,
+      "eval_steps_per_second": 2.305,
+      "step": 8400
+    },
+    {
+      "epoch": 25.14792899408284,
+      "grad_norm": 4.1875,
+      "learning_rate": 0.00012873777539848283,
+      "loss": 0.6546,
+      "step": 8500
+    },
+    {
+      "epoch": 25.7396449704142,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.693,
+      "eval_samples_per_second": 36.792,
+      "eval_steps_per_second": 2.317,
+      "step": 8700
+    },
+    {
+      "epoch": 26.62721893491124,
+      "grad_norm": 2.40625,
+      "learning_rate": 0.00012089675630312754,
+      "loss": 0.5857,
+      "step": 9000
+    },
+    {
+      "epoch": 26.62721893491124,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.5163,
+      "eval_samples_per_second": 36.97,
+      "eval_steps_per_second": 2.328,
+      "step": 9000
+    },
+    {
+      "epoch": 27.514792899408285,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.9675,
+      "eval_samples_per_second": 36.519,
+      "eval_steps_per_second": 2.299,
+      "step": 9300
+    },
+    {
+      "epoch": 28.106508875739646,
+      "grad_norm": 2.265625,
+      "learning_rate": 0.00011291881373954065,
+      "loss": 0.5462,
+      "step": 9500
+    },
+    {
+      "epoch": 28.402366863905325,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.8575,
+      "eval_samples_per_second": 36.628,
+      "eval_steps_per_second": 2.306,
+      "step": 9600
+    },
+    {
+      "epoch": 29.28994082840237,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.7695,
+      "eval_samples_per_second": 36.715,
+      "eval_steps_per_second": 2.312,
+      "step": 9900
+    },
+    {
+      "epoch": 29.585798816568047,
+      "grad_norm": 1.921875,
+      "learning_rate": 0.00010485622221144484,
+      "loss": 0.4881,
+      "step": 10000
+    },
+    {
+      "epoch": 30.17751479289941,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.8382,
+      "eval_samples_per_second": 36.647,
+      "eval_steps_per_second": 2.307,
+      "step": 10200
+    },
+    {
+      "epoch": 31.06508875739645,
+      "grad_norm": 2.140625,
+      "learning_rate": 9.676181087466444e-05,
+      "loss": 0.4573,
+      "step": 10500
+    },
+    {
+      "epoch": 31.06508875739645,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.8178,
+      "eval_samples_per_second": 36.667,
+      "eval_steps_per_second": 2.309,
+      "step": 10500
+    },
+    {
+      "epoch": 31.952662721893493,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.8459,
+      "eval_samples_per_second": 36.639,
+      "eval_steps_per_second": 2.307,
+      "step": 10800
+    },
+    {
+      "epoch": 32.544378698224854,
+      "grad_norm": 1.953125,
+      "learning_rate": 8.868861738047158e-05,
+      "loss": 0.4072,
+      "step": 11000
+    },
+    {
+      "epoch": 32.84023668639053,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.9905,
+      "eval_samples_per_second": 36.496,
+      "eval_steps_per_second": 2.298,
+      "step": 11100
+    },
+    {
+      "epoch": 33.72781065088758,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 37.2072,
+      "eval_samples_per_second": 36.283,
+      "eval_steps_per_second": 2.285,
+      "step": 11400
+    },
+    {
+      "epoch": 34.023668639053255,
+      "grad_norm": 2.1875,
+      "learning_rate": 8.068954035279121e-05,
+      "loss": 0.3735,
+      "step": 11500
+    },
+    {
+      "epoch": 34.61538461538461,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.8893,
+      "eval_samples_per_second": 36.596,
+      "eval_steps_per_second": 2.304,
+      "step": 11700
+    },
+    {
+      "epoch": 35.50295857988166,
+      "grad_norm": 1.8046875,
+      "learning_rate": 7.281699277636572e-05,
+      "loss": 0.3356,
+      "step": 12000
+    },
+    {
+      "epoch": 35.50295857988166,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.8597,
+      "eval_samples_per_second": 36.625,
+      "eval_steps_per_second": 2.306,
+      "step": 12000
+    },
+    {
+      "epoch": 36.3905325443787,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 37.126,
+      "eval_samples_per_second": 36.363,
+      "eval_steps_per_second": 2.289,
+      "step": 12300
+    },
+    {
+      "epoch": 36.98224852071006,
+      "grad_norm": 1.7578125,
+      "learning_rate": 6.512255856701177e-05,
+      "loss": 0.3124,
+      "step": 12500
+    },
+    {
+      "epoch": 37.27810650887574,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.7155,
+      "eval_samples_per_second": 36.769,
+      "eval_steps_per_second": 2.315,
+      "step": 12600
+    },
+    {
+      "epoch": 38.16568047337278,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 37.3255,
+      "eval_samples_per_second": 36.168,
+      "eval_steps_per_second": 2.277,
+      "step": 12900
+    },
+    {
+      "epoch": 38.46153846153846,
+      "grad_norm": 1.25,
+      "learning_rate": 5.765665457425102e-05,
+      "loss": 0.2847,
+      "step": 13000
+    },
+    {
+      "epoch": 39.053254437869825,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.8115,
+      "eval_samples_per_second": 36.673,
+      "eval_steps_per_second": 2.309,
+      "step": 13200
+    },
+    {
+      "epoch": 39.94082840236686,
+      "grad_norm": 1.90625,
+      "learning_rate": 5.0468200231001286e-05,
+      "loss": 0.2682,
+      "step": 13500
+    },
+    {
+      "epoch": 39.94082840236686,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.8329,
+      "eval_samples_per_second": 36.652,
+      "eval_steps_per_second": 2.308,
+      "step": 13500
+    },
+    {
+      "epoch": 40.828402366863905,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.9982,
+      "eval_samples_per_second": 36.488,
+      "eval_steps_per_second": 2.297,
+      "step": 13800
+    },
+    {
+      "epoch": 41.42011834319526,
+      "grad_norm": 0.79296875,
+      "learning_rate": 4.360429701490934e-05,
+      "loss": 0.2514,
+      "step": 14000
+    },
+    {
+      "epoch": 41.71597633136095,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.9527,
+      "eval_samples_per_second": 36.533,
+      "eval_steps_per_second": 2.3,
+      "step": 14100
+    },
+    {
+      "epoch": 42.603550295857985,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.8048,
+      "eval_samples_per_second": 36.68,
+      "eval_steps_per_second": 2.309,
+      "step": 14400
+    },
+    {
+      "epoch": 42.89940828402367,
+      "grad_norm": 0.9921875,
+      "learning_rate": 3.710991982161555e-05,
+      "loss": 0.2398,
+      "step": 14500
+    },
+    {
+      "epoch": 43.49112426035503,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.6719,
+      "eval_samples_per_second": 36.813,
+      "eval_steps_per_second": 2.318,
+      "step": 14700
+    },
+    {
+      "epoch": 44.37869822485207,
+      "grad_norm": 0.65234375,
+      "learning_rate": 3.102762227218957e-05,
+      "loss": 0.2324,
+      "step": 15000
+    },
+    {
+      "epoch": 44.37869822485207,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.9077,
+      "eval_samples_per_second": 36.578,
+      "eval_steps_per_second": 2.303,
+      "step": 15000
+    },
+    {
+      "epoch": 45.26627218934911,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.9609,
+      "eval_samples_per_second": 36.525,
+      "eval_steps_per_second": 2.3,
+      "step": 15300
+    },
+    {
+      "epoch": 45.857988165680474,
+      "grad_norm": 0.6796875,
+      "learning_rate": 2.5397257885675397e-05,
+      "loss": 0.2276,
+      "step": 15500
+    },
+    {
+      "epoch": 46.15384615384615,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.9434,
+      "eval_samples_per_second": 36.542,
+      "eval_steps_per_second": 2.301,
+      "step": 15600
+    },
+    {
+      "epoch": 47.0414201183432,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 37.1485,
+      "eval_samples_per_second": 36.341,
+      "eval_steps_per_second": 2.288,
+      "step": 15900
+    },
+    {
+      "epoch": 47.337278106508876,
+      "grad_norm": 0.73046875,
+      "learning_rate": 2.025571894372794e-05,
+      "loss": 0.2244,
+      "step": 16000
+    },
+    {
+      "epoch": 47.928994082840234,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 37.0304,
+      "eval_samples_per_second": 36.457,
+      "eval_steps_per_second": 2.295,
+      "step": 16200
+    },
+    {
+      "epoch": 48.81656804733728,
+      "grad_norm": 0.66796875,
+      "learning_rate": 1.563669475839956e-05,
+      "loss": 0.2242,
+      "step": 16500
+    },
+    {
+      "epoch": 48.81656804733728,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.8527,
+      "eval_samples_per_second": 36.632,
+      "eval_steps_per_second": 2.306,
+      "step": 16500
+    },
+    {
+      "epoch": 49.70414201183432,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 37.017,
+      "eval_samples_per_second": 36.47,
+      "eval_steps_per_second": 2.296,
+      "step": 16800
+    },
+    {
+      "epoch": 50.29585798816568,
+      "grad_norm": 0.71875,
+      "learning_rate": 1.1570450926997655e-05,
+      "loss": 0.222,
+      "step": 17000
+    },
+    {
+      "epoch": 50.59171597633136,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 37.0005,
+      "eval_samples_per_second": 36.486,
+      "eval_steps_per_second": 2.297,
+      "step": 17100
+    },
+    {
+      "epoch": 51.4792899408284,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 37.0483,
+      "eval_samples_per_second": 36.439,
+      "eval_steps_per_second": 2.294,
+      "step": 17400
+    },
+    {
+      "epoch": 51.77514792899408,
+      "grad_norm": 0.73046875,
+      "learning_rate": 8.083631020418791e-06,
+      "loss": 0.2219,
+      "step": 17500
+    },
+    {
+      "epoch": 52.366863905325445,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.8489,
+      "eval_samples_per_second": 36.636,
+      "eval_steps_per_second": 2.307,
+      "step": 17700
+    },
+    {
+      "epoch": 53.25443786982248,
+      "grad_norm": 0.99609375,
+      "learning_rate": 5.199082004372957e-06,
+      "loss": 0.2215,
+      "step": 18000
+    },
+    {
+      "epoch": 53.25443786982248,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.8278,
+      "eval_samples_per_second": 36.657,
+      "eval_steps_per_second": 2.308,
+      "step": 18000
+    },
+    {
+      "epoch": 54.142011834319526,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.8191,
+      "eval_samples_per_second": 36.666,
+      "eval_steps_per_second": 2.309,
+      "step": 18300
+    },
+    {
+      "epoch": 54.73372781065089,
+      "grad_norm": 1.1328125,
+      "learning_rate": 2.9357045374040825e-06,
+      "loss": 0.2224,
+      "step": 18500
+    },
+    {
+      "epoch": 55.02958579881657,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.9293,
+      "eval_samples_per_second": 36.556,
+      "eval_steps_per_second": 2.302,
+      "step": 18600
+    },
+    {
+      "epoch": 55.917159763313606,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.8842,
+      "eval_samples_per_second": 36.601,
+      "eval_steps_per_second": 2.305,
+      "step": 18900
+    },
+    {
+      "epoch": 56.21301775147929,
+      "grad_norm": 0.7421875,
+      "learning_rate": 1.30832912661093e-06,
+      "loss": 0.2211,
+      "step": 19000
+    },
+    {
+      "epoch": 56.80473372781065,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.681,
+      "eval_samples_per_second": 36.804,
+      "eval_steps_per_second": 2.317,
+      "step": 19200
+    },
+    {
+      "epoch": 57.69230769230769,
+      "grad_norm": 1.0546875,
+      "learning_rate": 3.2761895254306287e-07,
+      "loss": 0.2212,
+      "step": 19500
+    },
+    {
+      "epoch": 57.69230769230769,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.6389,
+      "eval_samples_per_second": 36.846,
+      "eval_steps_per_second": 2.32,
+      "step": 19500
+    },
+    {
+      "epoch": 58.57988165680474,
+      "eval_loss": 0.5067562460899353,
+      "eval_runtime": 36.8606,
+      "eval_samples_per_second": 36.624,
+      "eval_steps_per_second": 2.306,
+      "step": 19800
+    },
+    {
+      "epoch": 59.171597633136095,
+      "grad_norm": 0.78515625,
+      "learning_rate": 0.0,
+      "loss": 0.2214,
+      "step": 20000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 20000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 60,
+  "save_steps": 300,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.745192353814282e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a73772e6e6a31279e54f711d37cd5b0982ed85861239164fbaeea11be12bd5bd
+size 5304