'Repeat After Me' Training

config.json

@@ -0,0 +1 @@
+{"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": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "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": [0, 1, 2], "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": 0, "eos_token_id": 2, "sep_token_id": null, "decoder_start_token_id": 1, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "transformers_version": "4.39.0", "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": 0.0, "attention_dropout": 0.0, "activation_dropout": 0.0, "activation_function": "gelu", "init_std": 0.02, "encoder_layerdrop": 0.0, "decoder_layerdrop": 0.0, "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": 0.0, "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": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "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": "4.39.0", "model_type": "whisper"}, "decoder": {"vocab_size": 32000, "max_position_embeddings": 1024, "hidden_size": 4096, "intermediate_size": 11008, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 32, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000.0, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "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": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "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": "4.39.0", "model_type": "llama"}, "time_dialation": 25, "model_type": ""}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c994d18d0ccc9c45f15cdce43c04647f66af0ec6a902c72cbc3b84004ef71462
+size 9967080096

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cc768400bf6656078acb3feedc5b7179cbfa655d5af4046c3958cd1255974c3
+size 5304244672

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"total_size": 15271233536}, "weight_map": {"encoder.conv1.weight": "model-00001-of-00002.safetensors", "encoder.conv1.bias": "model-00001-of-00002.safetensors", "encoder.conv2.weight": "model-00001-of-00002.safetensors", "encoder.conv2.bias": "model-00001-of-00002.safetensors", "encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.31.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.30.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.31.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.27.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.28.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.29.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.30.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.31.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", "encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.27.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.28.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.29.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.30.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.31.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", "encoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.1.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.3.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.4.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.5.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.6.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.7.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.8.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.9.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.10.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.11.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.12.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.13.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.14.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.15.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.16.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.17.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.18.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.19.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.20.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.21.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.22.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.23.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.24.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.25.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.26.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.27.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.28.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.29.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.30.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.31.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.1.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.3.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.4.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.5.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.6.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.7.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.8.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.9.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.10.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.11.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.12.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.13.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.14.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.15.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.16.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.17.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.18.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.19.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.20.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.21.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.22.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.23.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.24.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.25.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.26.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.27.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.28.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.29.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.30.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.31.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.0.fc1.weight": "model-00001-of-00002.safetensors", "encoder.layers.1.fc1.weight": "model-00001-of-00002.safetensors", "encoder.layers.2.fc1.weight": "model-00001-of-00002.safetensors", "encoder.layers.3.fc1.weight": "model-00001-of-00002.safetensors", "encoder.layers.4.fc1.weight": "model-00001-of-00002.safetensors", "encoder.layers.5.fc1.weight": "model-00001-of-00002.safetensors", "encoder.layers.6.fc1.weight": "model-00001-of-00002.safetensors", "encoder.layers.7.fc1.weight": "model-00001-of-00002.safetensors", "encoder.layers.8.fc1.weight": "model-00001-of-00002.safetensors", "encoder.layers.9.fc1.weight": "model-00001-of-00002.safetensors", "encoder.layers.10.fc1.weight": "model-00001-of-00002.safetensors", "encoder.layers.11.fc1.weight": "model-00001-of-00002.safetensors", "encoder.layers.12.fc1.weight": "model-00001-of-00002.safetensors", "encoder.layers.13.fc1.weight": "model-00001-of-00002.safetensors", "encoder.layers.14.fc1.weight": "model-00001-of-00002.safetensors", "encoder.layers.15.fc1.weight": "model-00001-of-00002.safetensors", "encoder.layers.16.fc1.weight": "model-00001-of-00002.safetensors", "encoder.layers.17.fc1.weight": "model-00001-of-00002.safetensors", "encoder.layers.18.fc1.weight": "model-00001-of-00002.safetensors", "encoder.layers.19.fc1.weight": "model-00001-of-00002.safetensors", "encoder.layers.20.fc1.weight": "model-00001-of-00002.safetensors", "encoder.layers.21.fc1.weight": "model-00001-of-00002.safetensors", "encoder.layers.22.fc1.weight": "model-00001-of-00002.safetensors", "encoder.layers.23.fc1.weight": "model-00001-of-00002.safetensors", "encoder.layers.24.fc1.weight": "model-00001-of-00002.safetensors", "encoder.layers.25.fc1.weight": "model-00001-of-00002.safetensors", "encoder.layers.26.fc1.weight": "model-00001-of-00002.safetensors", "encoder.layers.27.fc1.weight": "model-00001-of-00002.safetensors", "encoder.layers.28.fc1.weight": "model-00001-of-00002.safetensors", "encoder.layers.29.fc1.weight": "model-00001-of-00002.safetensors", "encoder.layers.30.fc1.weight": "model-00001-of-00002.safetensors", "encoder.layers.31.fc1.weight": "model-00001-of-00002.safetensors", "encoder.layers.0.fc1.bias": "model-00001-of-00002.safetensors", "encoder.layers.1.fc1.bias": "model-00001-of-00002.safetensors", "encoder.layers.2.fc1.bias": "model-00001-of-00002.safetensors", "encoder.layers.3.fc1.bias": "model-00001-of-00002.safetensors", "encoder.layers.4.fc1.bias": "model-00001-of-00002.safetensors", "encoder.layers.5.fc1.bias": "model-00001-of-00002.safetensors", "encoder.layers.6.fc1.bias": "model-00001-of-00002.safetensors", "encoder.layers.7.fc1.bias": "model-00001-of-00002.safetensors", "encoder.layers.8.fc1.bias": "model-00001-of-00002.safetensors", "encoder.layers.9.fc1.bias": "model-00001-of-00002.safetensors", "encoder.layers.10.fc1.bias": "model-00001-of-00002.safetensors", "encoder.layers.11.fc1.bias": "model-00001-of-00002.safetensors", "encoder.layers.12.fc1.bias": "model-00001-of-00002.safetensors", "encoder.layers.13.fc1.bias": "model-00001-of-00002.safetensors", "encoder.layers.14.fc1.bias": "model-00001-of-00002.safetensors", "encoder.layers.15.fc1.bias": "model-00001-of-00002.safetensors", "encoder.layers.16.fc1.bias": "model-00001-of-00002.safetensors", "encoder.layers.17.fc1.bias": "model-00001-of-00002.safetensors", "encoder.layers.18.fc1.bias": "model-00001-of-00002.safetensors", "encoder.layers.19.fc1.bias": "model-00001-of-00002.safetensors", "encoder.layers.20.fc1.bias": "model-00001-of-00002.safetensors", "encoder.layers.21.fc1.bias": "model-00001-of-00002.safetensors", "encoder.layers.22.fc1.bias": "model-00001-of-00002.safetensors", "encoder.layers.23.fc1.bias": "model-00001-of-00002.safetensors", "encoder.layers.24.fc1.bias": "model-00001-of-00002.safetensors", "encoder.layers.25.fc1.bias": "model-00001-of-00002.safetensors", "encoder.layers.26.fc1.bias": "model-00001-of-00002.safetensors", "encoder.layers.27.fc1.bias": "model-00001-of-00002.safetensors", "encoder.layers.28.fc1.bias": "model-00001-of-00002.safetensors", "encoder.layers.29.fc1.bias": "model-00001-of-00002.safetensors", "encoder.layers.30.fc1.bias": "model-00001-of-00002.safetensors", "encoder.layers.31.fc1.bias": "model-00001-of-00002.safetensors", "encoder.layers.0.fc2.weight": "model-00001-of-00002.safetensors", "encoder.layers.1.fc2.weight": "model-00001-of-00002.safetensors", "encoder.layers.2.fc2.weight": "model-00001-of-00002.safetensors", "encoder.layers.3.fc2.weight": "model-00001-of-00002.safetensors", "encoder.layers.4.fc2.weight": "model-00001-of-00002.safetensors", "encoder.layers.5.fc2.weight": "model-00001-of-00002.safetensors", "encoder.layers.6.fc2.weight": "model-00001-of-00002.safetensors", "encoder.layers.7.fc2.weight": "model-00001-of-00002.safetensors", "encoder.layers.8.fc2.weight": "model-00001-of-00002.safetensors", "encoder.layers.9.fc2.weight": "model-00001-of-00002.safetensors", "encoder.layers.10.fc2.weight": "model-00001-of-00002.safetensors", "encoder.layers.11.fc2.weight": "model-00001-of-00002.safetensors", "encoder.layers.12.fc2.weight": "model-00001-of-00002.safetensors", "encoder.layers.13.fc2.weight": "model-00001-of-00002.safetensors", "encoder.layers.14.fc2.weight": "model-00001-of-00002.safetensors", "encoder.layers.15.fc2.weight": "model-00001-of-00002.safetensors", "encoder.layers.16.fc2.weight": "model-00001-of-00002.safetensors", "encoder.layers.17.fc2.weight": "model-00001-of-00002.safetensors", "encoder.layers.18.fc2.weight": "model-00001-of-00002.safetensors", "encoder.layers.19.fc2.weight": "model-00001-of-00002.safetensors", "encoder.layers.20.fc2.weight": "model-00001-of-00002.safetensors", "encoder.layers.21.fc2.weight": "model-00001-of-00002.safetensors", "encoder.layers.22.fc2.weight": "model-00001-of-00002.safetensors", "encoder.layers.23.fc2.weight": "model-00001-of-00002.safetensors", "encoder.layers.24.fc2.weight": "model-00001-of-00002.safetensors", "encoder.layers.25.fc2.weight": "model-00001-of-00002.safetensors", "encoder.layers.26.fc2.weight": "model-00001-of-00002.safetensors", "encoder.layers.27.fc2.weight": "model-00001-of-00002.safetensors", "encoder.layers.28.fc2.weight": "model-00001-of-00002.safetensors", "encoder.layers.29.fc2.weight": "model-00001-of-00002.safetensors", "encoder.layers.30.fc2.weight": "model-00001-of-00002.safetensors", "encoder.layers.31.fc2.weight": "model-00001-of-00002.safetensors", "encoder.layers.0.fc2.bias": "model-00001-of-00002.safetensors", "encoder.layers.1.fc2.bias": "model-00001-of-00002.safetensors", "encoder.layers.2.fc2.bias": "model-00001-of-00002.safetensors", "encoder.layers.3.fc2.bias": "model-00001-of-00002.safetensors", "encoder.layers.4.fc2.bias": "model-00001-of-00002.safetensors", "encoder.layers.5.fc2.bias": "model-00001-of-00002.safetensors", "encoder.layers.6.fc2.bias": "model-00001-of-00002.safetensors", "encoder.layers.7.fc2.bias": "model-00001-of-00002.safetensors", "encoder.layers.8.fc2.bias": "model-00001-of-00002.safetensors", "encoder.layers.9.fc2.bias": "model-00001-of-00002.safetensors", "encoder.layers.10.fc2.bias": "model-00001-of-00002.safetensors", "encoder.layers.11.fc2.bias": "model-00001-of-00002.safetensors", "encoder.layers.12.fc2.bias": "model-00001-of-00002.safetensors", "encoder.layers.13.fc2.bias": "model-00001-of-00002.safetensors", "encoder.layers.14.fc2.bias": "model-00001-of-00002.safetensors", "encoder.layers.15.fc2.bias": "model-00001-of-00002.safetensors", "encoder.layers.16.fc2.bias": "model-00001-of-00002.safetensors", "encoder.layers.17.fc2.bias": "model-00001-of-00002.safetensors", "encoder.layers.18.fc2.bias": "model-00001-of-00002.safetensors", "encoder.layers.19.fc2.bias": "model-00001-of-00002.safetensors", "encoder.layers.20.fc2.bias": "model-00001-of-00002.safetensors", "encoder.layers.21.fc2.bias": "model-00001-of-00002.safetensors", "encoder.layers.22.fc2.bias": "model-00001-of-00002.safetensors", "encoder.layers.23.fc2.bias": "model-00001-of-00002.safetensors", "encoder.layers.24.fc2.bias": "model-00001-of-00002.safetensors", "encoder.layers.25.fc2.bias": "model-00001-of-00002.safetensors", "encoder.layers.26.fc2.bias": "model-00001-of-00002.safetensors", "encoder.layers.27.fc2.bias": "model-00001-of-00002.safetensors", "encoder.layers.28.fc2.bias": "model-00001-of-00002.safetensors", "encoder.layers.29.fc2.bias": "model-00001-of-00002.safetensors", "encoder.layers.30.fc2.bias": "model-00001-of-00002.safetensors", "encoder.layers.31.fc2.bias": "model-00001-of-00002.safetensors", "encoder.layers.0.final_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.1.final_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.2.final_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.3.final_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.4.final_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.5.final_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.6.final_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.7.final_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.8.final_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.9.final_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.10.final_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.11.final_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.12.final_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.13.final_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.14.final_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.15.final_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.16.final_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.17.final_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.18.final_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.19.final_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.20.final_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.21.final_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.22.final_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.23.final_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.24.final_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.25.final_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.26.final_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.27.final_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.28.final_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.29.final_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.30.final_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.31.final_layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layers.0.final_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.1.final_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.2.final_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.3.final_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.4.final_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.5.final_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.6.final_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.7.final_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.8.final_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.9.final_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.10.final_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.11.final_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.12.final_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.13.final_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.14.final_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.15.final_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.16.final_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.17.final_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.18.final_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.19.final_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.20.final_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.21.final_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.22.final_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.23.final_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.24.final_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.25.final_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.26.final_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.27.final_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.28.final_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.29.final_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.30.final_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layers.31.final_layer_norm.bias": "model-00001-of-00002.safetensors", "encoder.layer_norm.weight": "model-00001-of-00002.safetensors", "encoder.layer_norm.bias": "model-00001-of-00002.safetensors", "connector.dialator.weight": "model-00001-of-00002.safetensors", "connector.dialator.bias": "model-00001-of-00002.safetensors", "decoder.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "decoder.model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.12.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.0.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.1.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.2.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.3.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.5.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.12.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.0.input_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.1.input_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.2.input_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.0.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.1.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.2.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "decoder.model.norm.weight": "model-00002-of-00002.safetensors", "decoder.model.embed_tokens.weight": "model-00002-of-00002.safetensors", "decoder.lm_head.weight": "model-00002-of-00002.safetensors"}}

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 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}