'Is this a *custom model*?' meme

config.json

@@ -0,0 +1,250 @@
+{
+  "auto_map": {
+    "AutoModelForCausalLM": "modeling_diva.DiVAModel"
+  },
+  "return_dict": true,
+  "output_hidden_states": false,
+  "output_attentions": false,
+  "torchscript": false,
+  "torch_dtype": null,
+  "use_bfloat16": false,
+  "tf_legacy_loss": false,
+  "pruned_heads": {},
+  "tie_word_embeddings": true,
+  "chunk_size_feed_forward": 0,
+  "is_encoder_decoder": false,
+  "is_decoder": false,
+  "cross_attention_hidden_size": null,
+  "add_cross_attention": false,
+  "tie_encoder_decoder": false,
+  "max_length": 20,
+  "min_length": 0,
+  "do_sample": false,
+  "early_stopping": false,
+  "num_beams": 1,
+  "num_beam_groups": 1,
+  "diversity_penalty": 0,
+  "temperature": 1,
+  "top_k": 50,
+  "top_p": 1,
+  "typical_p": 1,
+  "repetition_penalty": 1,
+  "length_penalty": 1,
+  "no_repeat_ngram_size": 0,
+  "encoder_no_repeat_ngram_size": 0,
+  "bad_words_ids": null,
+  "num_return_sequences": 1,
+  "output_scores": false,
+  "return_dict_in_generate": false,
+  "forced_bos_token_id": null,
+  "forced_eos_token_id": null,
+  "remove_invalid_values": false,
+  "exponential_decay_length_penalty": null,
+  "suppress_tokens": null,
+  "begin_suppress_tokens": [
+    128000,
+    128009,
+    128002
+  ],
+  "architectures": null,
+  "finetuning_task": null,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1"
+  },
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "tokenizer_class": null,
+  "prefix": null,
+  "bos_token_id": 128000,
+  "pad_token_id": 128002,
+  "eos_token_id": 128009,
+  "sep_token_id": null,
+  "decoder_start_token_id": 128000,
+  "task_specific_params": null,
+  "problem_type": null,
+  "_name_or_path": "",
+  "transformers_version": "4.41.2",
+  "encoder": {
+    "vocab_size": 51866,
+    "num_mel_bins": 128,
+    "d_model": 1280,
+    "encoder_layers": 32,
+    "encoder_attention_heads": 20,
+    "decoder_layers": 32,
+    "decoder_attention_heads": 20,
+    "decoder_ffn_dim": 5120,
+    "encoder_ffn_dim": 5120,
+    "dropout": 0,
+    "attention_dropout": 0,
+    "activation_dropout": 0,
+    "activation_function": "gelu",
+    "init_std": 0.02,
+    "encoder_layerdrop": 0,
+    "decoder_layerdrop": 0,
+    "use_cache": true,
+    "num_hidden_layers": 32,
+    "scale_embedding": false,
+    "max_source_positions": 1500,
+    "max_target_positions": 448,
+    "classifier_proj_size": 256,
+    "use_weighted_layer_sum": false,
+    "apply_spec_augment": false,
+    "mask_time_prob": 0.05,
+    "mask_time_length": 10,
+    "mask_time_min_masks": 2,
+    "mask_feature_prob": 0,
+    "mask_feature_length": 10,
+    "mask_feature_min_masks": 0,
+    "median_filter_width": 7,
+    "return_dict": true,
+    "output_hidden_states": false,
+    "output_attentions": false,
+    "torchscript": false,
+    "torch_dtype": null,
+    "use_bfloat16": false,
+    "tf_legacy_loss": false,
+    "pruned_heads": {},
+    "tie_word_embeddings": true,
+    "chunk_size_feed_forward": 0,
+    "is_encoder_decoder": true,
+    "is_decoder": false,
+    "cross_attention_hidden_size": null,
+    "add_cross_attention": false,
+    "tie_encoder_decoder": false,
+    "max_length": 20,
+    "min_length": 0,
+    "do_sample": false,
+    "early_stopping": false,
+    "num_beams": 1,
+    "num_beam_groups": 1,
+    "diversity_penalty": 0,
+    "temperature": 1,
+    "top_k": 50,
+    "top_p": 1,
+    "typical_p": 1,
+    "repetition_penalty": 1,
+    "length_penalty": 1,
+    "no_repeat_ngram_size": 0,
+    "encoder_no_repeat_ngram_size": 0,
+    "bad_words_ids": null,
+    "num_return_sequences": 1,
+    "output_scores": false,
+    "return_dict_in_generate": false,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "remove_invalid_values": false,
+    "exponential_decay_length_penalty": null,
+    "suppress_tokens": null,
+    "begin_suppress_tokens": [
+      220,
+      50256
+    ],
+    "architectures": null,
+    "finetuning_task": null,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "tokenizer_class": null,
+    "prefix": null,
+    "bos_token_id": 50256,
+    "pad_token_id": 50256,
+    "eos_token_id": 50256,
+    "sep_token_id": null,
+    "decoder_start_token_id": 50257,
+    "task_specific_params": null,
+    "problem_type": null,
+    "_name_or_path": "",
+    "transformers_version": "4.41.2",
+    "model_type": "whisper"
+  },
+  "decoder": {
+    "vocab_size": 128256,
+    "max_position_embeddings": 8192,
+    "hidden_size": 4096,
+    "intermediate_size": 14336,
+    "num_hidden_layers": 32,
+    "num_attention_heads": 32,
+    "num_key_value_heads": 8,
+    "hidden_act": "silu",
+    "initializer_range": 0.02,
+    "rms_norm_eps": 1e-05,
+    "pretraining_tp": 1,
+    "use_cache": true,
+    "rope_theta": 10000,
+    "rope_scaling": null,
+    "attention_bias": false,
+    "attention_dropout": 0,
+    "mlp_bias": false,
+    "return_dict": true,
+    "output_hidden_states": false,
+    "output_attentions": false,
+    "torchscript": false,
+    "torch_dtype": null,
+    "use_bfloat16": false,
+    "tf_legacy_loss": false,
+    "pruned_heads": {},
+    "tie_word_embeddings": false,
+    "chunk_size_feed_forward": 0,
+    "is_encoder_decoder": false,
+    "is_decoder": false,
+    "cross_attention_hidden_size": null,
+    "add_cross_attention": false,
+    "tie_encoder_decoder": false,
+    "max_length": 20,
+    "min_length": 0,
+    "do_sample": false,
+    "early_stopping": false,
+    "num_beams": 1,
+    "num_beam_groups": 1,
+    "diversity_penalty": 0,
+    "temperature": 1,
+    "top_k": 50,
+    "top_p": 1,
+    "typical_p": 1,
+    "repetition_penalty": 1,
+    "length_penalty": 1,
+    "no_repeat_ngram_size": 0,
+    "encoder_no_repeat_ngram_size": 0,
+    "bad_words_ids": null,
+    "num_return_sequences": 1,
+    "output_scores": false,
+    "return_dict_in_generate": false,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "remove_invalid_values": false,
+    "exponential_decay_length_penalty": null,
+    "suppress_tokens": null,
+    "begin_suppress_tokens": null,
+    "architectures": null,
+    "finetuning_task": null,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "tokenizer_class": null,
+    "prefix": null,
+    "bos_token_id": 1,
+    "pad_token_id": null,
+    "eos_token_id": 2,
+    "sep_token_id": null,
+    "decoder_start_token_id": null,
+    "task_specific_params": null,
+    "problem_type": null,
+    "_name_or_path": "",
+    "transformers_version": "4.41.2",
+    "model_type": "llama"
+  },
+  "model_type": ""
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3472edff09f44a6a05480c008db61c64736eb0cb6149288723492171cca4df5
+size 9947817720

model.safetensors.index.json

@@ -0,0 +1,782 @@
+{
+  "metadata": {
+    "total_size": 38310608896
+  },
+  "weight_map": {
+    "query_tokens": "model-00001-of-00004.safetensors",
+    "projection.weight": "model-00001-of-00004.safetensors",
+    "projection.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.13.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.14.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.15.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.16.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.17.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.18.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.19.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.20.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.21.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.22.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.23.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.24.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.25.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.26.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.27.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.28.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.29.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.30.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.31.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.12.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.13.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.14.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.15.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.16.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.17.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.18.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.19.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.20.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.21.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.22.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.23.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.24.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.25.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.26.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.27.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.28.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.29.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.30.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.31.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.0.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.1.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.2.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.3.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.4.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.5.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.6.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.7.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.8.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.9.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.10.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.11.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.12.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.13.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.14.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.15.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.16.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.17.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.18.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.19.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.20.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.21.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.22.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.23.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.24.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.25.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.26.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.27.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.28.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.29.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.30.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.31.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.0.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.1.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.2.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.3.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.4.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.5.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.6.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.7.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.8.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.9.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.10.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.11.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.12.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.13.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.14.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.15.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.16.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.17.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.18.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.19.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.20.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.21.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.22.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.23.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.24.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.25.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.26.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.27.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.28.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.29.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.30.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.31.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.0.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.1.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.2.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.3.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.4.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.5.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.6.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.7.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.8.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.9.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.10.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.11.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.12.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.13.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.14.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.15.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.16.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.17.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.18.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.19.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.20.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.21.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.22.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.23.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.24.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.25.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.26.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.27.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.28.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.29.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.30.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.31.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.0.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.1.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.2.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.3.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.4.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.5.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.6.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.7.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.8.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.9.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.10.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.11.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.12.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.13.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.14.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.15.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.16.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.17.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.18.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.19.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.20.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.21.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.22.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.23.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.24.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.25.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.26.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.27.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.28.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.29.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.30.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.31.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.0.encoder_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.1.encoder_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.2.encoder_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.3.encoder_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.4.encoder_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.5.encoder_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.6.encoder_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.7.encoder_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.8.encoder_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.9.encoder_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.10.encoder_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.11.encoder_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.12.encoder_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.13.encoder_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.14.encoder_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.15.encoder_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.16.encoder_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.17.encoder_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.18.encoder_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.19.encoder_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.20.encoder_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.21.encoder_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.22.encoder_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.23.encoder_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.24.encoder_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.25.encoder_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.26.encoder_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.27.encoder_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.28.encoder_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.29.encoder_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.30.encoder_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.31.encoder_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.0.encoder_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.1.encoder_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.2.encoder_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.3.encoder_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.4.encoder_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.5.encoder_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.6.encoder_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.7.encoder_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.8.encoder_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.9.encoder_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.10.encoder_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.11.encoder_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.12.encoder_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.13.encoder_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.14.encoder_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.15.encoder_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.16.encoder_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.17.encoder_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.18.encoder_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.19.encoder_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.20.encoder_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.21.encoder_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.22.encoder_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.23.encoder_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.24.encoder_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.25.encoder_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.26.encoder_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.27.encoder_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.28.encoder_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.29.encoder_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.30.encoder_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.31.encoder_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.0.encoder_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.1.encoder_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.2.encoder_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.3.encoder_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.4.encoder_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.5.encoder_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.6.encoder_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.7.encoder_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.8.encoder_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.9.encoder_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.10.encoder_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.11.encoder_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.12.encoder_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.13.encoder_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.14.encoder_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.15.encoder_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.16.encoder_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.17.encoder_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.18.encoder_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.19.encoder_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.20.encoder_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.21.encoder_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.22.encoder_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.23.encoder_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.24.encoder_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.25.encoder_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.26.encoder_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.27.encoder_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.28.encoder_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.29.encoder_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.30.encoder_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.31.encoder_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.0.encoder_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.1.encoder_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.2.encoder_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.3.encoder_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.4.encoder_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.5.encoder_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.6.encoder_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.7.encoder_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.8.encoder_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.9.encoder_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.10.encoder_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.11.encoder_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.12.encoder_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.13.encoder_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.14.encoder_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.15.encoder_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.16.encoder_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.17.encoder_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.18.encoder_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.19.encoder_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.20.encoder_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.21.encoder_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.22.encoder_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.23.encoder_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.24.encoder_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.25.encoder_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.26.encoder_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.27.encoder_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.28.encoder_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.29.encoder_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.30.encoder_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.31.encoder_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.0.encoder_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.1.encoder_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.2.encoder_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.3.encoder_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.4.encoder_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.5.encoder_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.6.encoder_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.7.encoder_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.8.encoder_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.9.encoder_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.10.encoder_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.11.encoder_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.12.encoder_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.13.encoder_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.14.encoder_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.15.encoder_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.16.encoder_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.17.encoder_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.18.encoder_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.19.encoder_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.20.encoder_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.21.encoder_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.22.encoder_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.23.encoder_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.24.encoder_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.25.encoder_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.26.encoder_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.27.encoder_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.28.encoder_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.29.encoder_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.30.encoder_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.31.encoder_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.0.encoder_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.1.encoder_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.2.encoder_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.3.encoder_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.4.encoder_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.5.encoder_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.6.encoder_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.7.encoder_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.8.encoder_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.9.encoder_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.10.encoder_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.11.encoder_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.12.encoder_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.13.encoder_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.14.encoder_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.15.encoder_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.16.encoder_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.17.encoder_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.18.encoder_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.19.encoder_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.20.encoder_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.21.encoder_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.22.encoder_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.23.encoder_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.24.encoder_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.25.encoder_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.26.encoder_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.27.encoder_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.28.encoder_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.29.encoder_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.30.encoder_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.31.encoder_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.0.encoder_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.1.encoder_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.2.encoder_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.3.encoder_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.4.encoder_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.5.encoder_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.6.encoder_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.7.encoder_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.8.encoder_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.9.encoder_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.10.encoder_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.11.encoder_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.12.encoder_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.13.encoder_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.14.encoder_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.15.encoder_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.16.encoder_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.17.encoder_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.18.encoder_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.19.encoder_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.20.encoder_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.21.encoder_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.22.encoder_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.23.encoder_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.24.encoder_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.25.encoder_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.26.encoder_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.27.encoder_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.28.encoder_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.29.encoder_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.30.encoder_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.31.encoder_attn.out_proj.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.0.encoder_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.1.encoder_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.2.encoder_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.3.encoder_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.4.encoder_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.5.encoder_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.6.encoder_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.7.encoder_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.8.encoder_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.9.encoder_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.10.encoder_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.11.encoder_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.12.encoder_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.13.encoder_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.14.encoder_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.15.encoder_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.16.encoder_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.17.encoder_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.18.encoder_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.19.encoder_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.20.encoder_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.21.encoder_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.22.encoder_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.23.encoder_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.24.encoder_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.25.encoder_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.26.encoder_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.27.encoder_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.28.encoder_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.29.encoder_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.30.encoder_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.31.encoder_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.0.encoder_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.1.encoder_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.2.encoder_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.3.encoder_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.4.encoder_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.5.encoder_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.6.encoder_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.7.encoder_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.8.encoder_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.9.encoder_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.10.encoder_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.11.encoder_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.12.encoder_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.13.encoder_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.14.encoder_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.15.encoder_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.16.encoder_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.17.encoder_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.18.encoder_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.19.encoder_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.20.encoder_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.21.encoder_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.22.encoder_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.23.encoder_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.24.encoder_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.25.encoder_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.26.encoder_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.27.encoder_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.28.encoder_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.29.encoder_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.30.encoder_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.31.encoder_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.0.fc1.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.1.fc1.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.2.fc1.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.3.fc1.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.4.fc1.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.5.fc1.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.6.fc1.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.7.fc1.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.8.fc1.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.9.fc1.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.10.fc1.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.11.fc1.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.12.fc1.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.13.fc1.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.14.fc1.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.15.fc1.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.16.fc1.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.17.fc1.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.18.fc1.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.19.fc1.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.20.fc1.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.21.fc1.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.22.fc1.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.23.fc1.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.24.fc1.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.25.fc1.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.26.fc1.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.27.fc1.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.28.fc1.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.29.fc1.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.30.fc1.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.31.fc1.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.0.fc1.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.1.fc1.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.2.fc1.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.3.fc1.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.4.fc1.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.5.fc1.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.6.fc1.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.7.fc1.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.8.fc1.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.9.fc1.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.10.fc1.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.11.fc1.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.12.fc1.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.13.fc1.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.14.fc1.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.15.fc1.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.16.fc1.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.17.fc1.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.18.fc1.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.19.fc1.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.20.fc1.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.21.fc1.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.22.fc1.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.23.fc1.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.24.fc1.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.25.fc1.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.26.fc1.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.27.fc1.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.28.fc1.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.29.fc1.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.30.fc1.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.31.fc1.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.0.fc2.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.1.fc2.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.2.fc2.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.3.fc2.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.4.fc2.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.5.fc2.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.6.fc2.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.7.fc2.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.8.fc2.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.9.fc2.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.10.fc2.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.11.fc2.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.12.fc2.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.13.fc2.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.14.fc2.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.15.fc2.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.16.fc2.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.17.fc2.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.18.fc2.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.19.fc2.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.20.fc2.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.21.fc2.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.22.fc2.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.23.fc2.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.24.fc2.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.25.fc2.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.26.fc2.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.27.fc2.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.28.fc2.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.29.fc2.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.30.fc2.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.31.fc2.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.0.fc2.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.1.fc2.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.2.fc2.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.3.fc2.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.4.fc2.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.5.fc2.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.6.fc2.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.7.fc2.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.8.fc2.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.9.fc2.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.10.fc2.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.11.fc2.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.12.fc2.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.13.fc2.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.14.fc2.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.15.fc2.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.16.fc2.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.17.fc2.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.18.fc2.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.19.fc2.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.20.fc2.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.21.fc2.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.22.fc2.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.23.fc2.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.24.fc2.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.25.fc2.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.26.fc2.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.27.fc2.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.28.fc2.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.29.fc2.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.30.fc2.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.31.fc2.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.0.final_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.1.final_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.2.final_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.3.final_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.4.final_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.5.final_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.6.final_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.7.final_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.8.final_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.9.final_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.10.final_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.11.final_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.12.final_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.13.final_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.14.final_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.15.final_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.16.final_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.17.final_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.18.final_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.19.final_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.20.final_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.21.final_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.22.final_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.23.final_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.24.final_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.25.final_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.26.final_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.27.final_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.28.final_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.29.final_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.30.final_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.31.final_layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layers.0.final_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.1.final_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.2.final_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.3.final_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.4.final_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.5.final_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.6.final_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.7.final_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.8.final_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.9.final_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.10.final_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.11.final_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.12.final_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.13.final_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.14.final_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.15.final_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.16.final_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.17.final_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.18.final_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.19.final_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.20.final_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.21.final_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.22.final_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.23.final_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.24.final_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.25.final_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.26.final_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.27.final_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.28.final_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.29.final_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.30.final_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layers.31.final_layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "connector.layer_norm.bias": "model-00001-of-00004.safetensors",
+    "connector.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "connector.embed_positions.weight": "model-00001-of-00004.safetensors",
+  }
+}

modeling_diva.py

@@ -0,0 +1,237 @@
+import copy
+import json
+import os
+from typing import Optional, Union
+
+import gradio as gr
+import librosa
+import numpy as np
+import torch
+import torch.nn.functional as F
+from datasets import Audio
+from safetensors.torch import load, load_model
+from torch import nn
+from transformers import (
+    AutoProcessor,
+    AutoTokenizer,
+    LlamaForCausalLM,
+    PretrainedConfig,
+    PreTrainedModel,
+    WhisperForConditionalGeneration,
+)
+
+
+class WhisperConnector(nn.Module):
+    def __init__(
+        self,
+    ):
+        super().__init__()
+        self.decoder = None
+        self.projection = nn.Linear(1280, 4096)
+        self.query_tokens = nn.Parameter(torch.randn(448, 1280))
+
+    def forward(self, x, output_device="cuda:1"):
+        bsz = x.shape[0]
+        query_tokens = self.query_tokens[None, :, :].expand(bsz, -1, -1)
+        virt_whisper_tokens = self.decoder(
+            inputs_embeds=query_tokens, encoder_hidden_states=x
+        )
+        if self.projection.weight.shape[-1] == 5120:
+            virtual_tokens = self.projection(virt_whisper_tokens[0].reshape(112, 5120))
+        else:
+            virtual_tokens = self.projection(virt_whisper_tokens[0])
+        return virtual_tokens.to(output_device)
+
+
+class DiVAModel(PreTrainedModel):
+    def __init__(
+        self, via_path=None, config_dict={}, device_map=None, speech_encoder_device=None
+    ):
+        super().__init__(PretrainedConfig.from_dict(config_dict))
+        if speech_encoder_device is None:
+            speech_encoder_device = "cuda:0"
+        whisper = WhisperForConditionalGeneration.from_pretrained(
+            "openai/whisper-large-v3"
+        )
+        connector = WhisperConnector()
+        connector.decoder = copy.deepcopy(whisper.model.decoder)
+        if via_path is not None:
+            with open(via_path, "rb") as f:
+                sd = load(f.read())
+
+            with torch.no_grad():
+                connector.query_tokens = nn.Parameter(sd["query_tokens"])
+                connector.projection.weight = nn.Parameter(sd["projection.weight"].T)
+                connector.projection.bias = nn.Parameter(sd["projection.bias"])
+                wsd = {
+                    key.replace("connector.", ""): sd[key]
+                    for key in sd
+                    if key.startswith("connector.")
+                }
+                connector.decoder.load_state_dict(wsd)
+
+        if device_map == None:
+            num_layers = 32
+            num_gpus = 2
+            device_map = dict(
+                **{"model.embed_tokens": 1, "model.norm": 1, "lm_head": 2},
+                **{
+                    "model.layers." + str(i): 1 + (i // (num_layers // num_gpus))
+                    for i in range(num_layers)
+                },
+            )
+
+        self.connector = connector.to(speech_encoder_device)
+        self.whisper_encoder = whisper.model.encoder.to(speech_encoder_device)
+        self.llama_decoder = LlamaForCausalLM.from_pretrained(
+            "meta-llama/Meta-Llama-3-8B-Instruct",
+            device_map=device_map,
+            torch_dtype=torch.float16,
+        )
+        self.processor = AutoProcessor.from_pretrained("openai/whisper-large-v3")
+        self.tokenizer = AutoTokenizer.from_pretrained("WillHeld/via-llama")
+        self.prefix = torch.tensor([128000, 128006, 882, 128007, 271]).to(
+            self.llama_decoder.model.embed_tokens.weight.device
+        )
+
+        self.pre_user_suffix = torch.tensor(
+            self.tokenizer.encode(
+                "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n"
+            )
+        ).to(self.llama_decoder.model.embed_tokens.weight.device)
+        self.final_header = torch.tensor([128009, 128006, 78191, 128007, 271]).to(
+            self.llama_decoder.model.embed_tokens.weight.device
+        )
+        self.speech_encoder_device = speech_encoder_device
+
+    @classmethod
+    def from_pretrained(
+        cls,
+        pretrained_model_name_or_path: Optional[Union[str, os.PathLike]],
+        *model_args,
+        config=None,
+        cache_dir=None,
+        **kwargs,
+    ):
+        if os.path.isdir(pretrained_model_name_or_path):
+            via_path = (
+                pretrained_model_name_or_path + "/model-00001-of-00004.safetensors"
+            )
+            config_path = pretrained_model_name_or_path + "/config.json"
+        else:
+            # Loading from huggingface repo
+            from huggingface_hub import hf_hub_download
+
+            hf_hub_download(
+                repo_id=pretrained_model_name_or_path,
+                token=kwargs.get("token", None),
+                local_dir=os.path.dirname(__file__),
+            )
+            via_path = os.path.dirname(__file__) + "/model-00001-of-00004.safetensors"
+            config_path = os.path.dirname(__file__) + "/config.json"
+        with open(config_path, "r") as f:
+            config_dict = json.loads(f.read())
+        return cls(
+            via_path,
+            config_dict,
+            kwargs["device_map"] if "device_map" in kwargs else None,
+            (
+                kwargs["speech_encoder_device"]
+                if "speech_encoder_device" in kwargs
+                else None
+            ),
+        )
+
+    def forward(self, audio, prefix_text_tokens, suffix_text_tokens):
+        inputs = self.processor(audio, return_tensors="pt", sampling_rate=16_000)
+        input_features = inputs.input_features.to(self.speech_encoder_device)
+        hidden_states = self.whisper_encoder(input_features=input_features)[
+            "last_hidden_state"
+        ]
+        virt_tokens = self.connector(
+            hidden_states,
+            output_device=self.llama_decoder.model.embed_tokens.weight.device,
+        ).squeeze()
+
+        prefix_embed = self.llama_decoder.model.embed_tokens(prefix_text_tokens)
+        suffix_embed = self.llama_decoder.model.embed_tokens(suffix_text_tokens)
+        inputs_embeds = torch.cat(
+            [prefix_embed, virt_tokens, suffix_embed], axis=0
+        ).unsqueeze(0)
+
+        outputs = self.llama_decoder(
+            inputs_embeds=inputs_embeds.to(
+                self.llama_decoder.model.embed_tokens.weight.device
+            ).half(),
+            return_dict=True,
+            output_hidden_states=True,
+            past_key_values=past_key_values,
+        )
+
+        return outputs
+
+    def generate(
+        self, audio, prompt, do_sample=False, logits_processor=None, max_new_tokens=128
+    ):
+        inputs = self.processor(audio, return_tensors="pt", sampling_rate=16_000)
+        input_features = inputs.input_features.to(self.speech_encoder_device)
+        hidden_states = self.whisper_encoder(input_features=input_features)[
+            "last_hidden_state"
+        ]
+        virt_tokens = self.connector(
+            hidden_states,
+            output_device=self.llama_decoder.model.embed_tokens.weight.device,
+        ).squeeze()
+
+        if prompt != None and prompt != "":
+            user_prompt_text = torch.tensor(
+                self.tokenizer(prompt, add_special_tokens=False)["input_ids"],
+                device=self.pre_user_suffix.device,
+            )
+            prefix = torch.cat(
+                [self.pre_user_suffix, user_prompt_text, self.prefix], axis=0
+            )
+        else:
+            prefix = self.prefix
+        prefix_embed = self.llama_decoder.model.embed_tokens(prefix)
+        suffix = self.final_header
+        suffix_embed = self.llama_decoder.model.embed_tokens(suffix)
+        inputs_embeds = torch.cat(
+            [prefix_embed, virt_tokens, suffix_embed], axis=0
+        ).unsqueeze(0)
+        outs = []
+        outputs = None
+        greedy = 1
+        i = 0
+        while greedy != 128009 and len(outs) < max_new_tokens:
+            past_key_values = outputs.past_key_values if outputs else None
+            outputs = self.llama_decoder(
+                inputs_embeds=inputs_embeds.to(
+                    self.llama_decoder.model.embed_tokens.weight.device
+                ).half(),
+                return_dict=True,
+                output_hidden_states=True,
+                past_key_values=past_key_values,
+            )
+            next_token_logits = outputs.logits[-1, -1, :]
+
+            if logits_processor:
+                local_outs = torch.tensor(outs) if outs != [] else suffix
+                local_outs = local_outs.reshape(1, -1)
+                next_token_logits = logits_processor(
+                    local_outs,
+                    next_token_logits.reshape(1, -1),
+                )
+                next_token_logits = next_token_logits.flatten()
+            if do_sample:
+                logits = next_token_logits / temperature
+                probs = F.softmax(logits, dim=-1)
+                greedy = torch.multinomial(probs, num_samples=1)[0]
+            else:
+                greedy = next_token_logits.argmax()
+            outs.append(greedy)
+            next_embed = self.llama_decoder.model.embed_tokens(greedy.reshape(1, 1))
+            inputs_embeds = next_embed
+        return self.tokenizer.decode(outs, skip_special_tokens=True).replace(
+            "<|eot_id|>", ""
+        )

preprocessor_config.json

@@ -0,0 +1,14 @@
+{
+  "chunk_length": 30,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 128,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|reserved_special_token_0|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,2064 @@
+{
+  "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": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_3|>",
+      "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": "<|reserved_special_token_4|>",
+      "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": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_248|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_249|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_250|>",
+      "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": 1000000000000000019884624838656,
+  "pad_token": "<|reserved_special_token_0|>",
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}