diff --git a/config.json b/config.json new file mode 100644 index 0000000..ea9648f --- /dev/null +++ b/config.json @@ -0,0 +1,283 @@ +{ + "_commit_hash": null, + "architectures": [ + "Blip2ForConditionalGeneration" + ], + "initializer_factor": 1.0, + "initializer_range": 0.02, + "model_type": "blip-2", + "num_query_tokens": 32, + "qformer_config": { + "_name_or_path": "", + "add_cross_attention": false, + "architectures": null, + "attention_probs_dropout_prob": 0.1, + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": null, + "chunk_size_feed_forward": 0, + "classifier_dropout": null, + "cross_attention_frequency": 2, + "cross_attention_hidden_size": null, + "decoder_start_token_id": null, + "diversity_penalty": 0.0, + "do_sample": false, + "early_stopping": false, + "encoder_hidden_size": 1408, + "encoder_no_repeat_ngram_size": 0, + "eos_token_id": null, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "initializer_range": 0.02, + "intermediate_size": 3072, + "is_decoder": false, + "is_encoder_decoder": false, + "label2id": { + "LABEL_0": 0, + "LABEL_1": 1 + }, + "layer_norm_eps": 1e-12, + "length_penalty": 1.0, + "max_length": 20, + "max_position_embeddings": 512, + "min_length": 0, + "model_type": "blip_2_qformer", + "no_repeat_ngram_size": 0, + "num_attention_heads": 12, + "num_beam_groups": 1, + "num_beams": 1, + "num_hidden_layers": 12, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": 0, + "position_embedding_type": "absolute", + "prefix": null, + "problem_type": null, + "pruned_heads": {}, + "remove_invalid_values": false, + "repetition_penalty": 1.0, + "return_dict": true, + "return_dict_in_generate": false, + "sep_token_id": null, + "suppress_tokens": null, + "task_specific_params": null, + "temperature": 1.0, + "tf_legacy_loss": false, + "tie_encoder_decoder": false, + "tie_word_embeddings": true, + "tokenizer_class": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": null, + "torchscript": false, + "transformers_version": "4.27.0.dev0", + "typical_p": 1.0, + "use_bfloat16": false, + "vocab_size": 30522 + }, + "text_config": { + "_name_or_path": "", + "add_cross_attention": false, + "architectures": [ + "T5ForConditionalGeneration" + ], + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": null, + "chunk_size_feed_forward": 0, + "cross_attention_hidden_size": null, + "d_ff": 5120, + "d_kv": 64, + "d_model": 2048, + "decoder_start_token_id": 0, + "dense_act_fn": "gelu", + "diversity_penalty": 0.0, + "do_sample": false, + "dropout_rate": 0.1, + "early_stopping": false, + "encoder_no_repeat_ngram_size": 0, + "eos_token_id": 1, + "exponential_decay_length_penalty": null, + "feed_forward_proj": "gated-gelu", + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "initializer_factor": 1.0, + "is_decoder": false, + "is_encoder_decoder": true, + "is_gated_act": true, + "label2id": { + "LABEL_0": 0, + "LABEL_1": 1 + }, + "layer_norm_epsilon": 1e-06, + "length_penalty": 1.0, + "max_length": 20, + "min_length": 0, + "model_type": "t5", + "n_positions": 512, + "no_repeat_ngram_size": 0, + "num_beam_groups": 1, + "num_beams": 1, + "num_decoder_layers": 24, + "num_heads": 32, + "num_layers": 24, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_past": true, + "output_scores": false, + "pad_token_id": 0, + "prefix": null, + "problem_type": null, + "pruned_heads": {}, + "relative_attention_max_distance": 128, + "relative_attention_num_buckets": 32, + "remove_invalid_values": false, + "repetition_penalty": 1.0, + "return_dict": true, + "return_dict_in_generate": false, + "sep_token_id": null, + "suppress_tokens": null, + "task_specific_params": { + "summarization": { + "early_stopping": true, + "length_penalty": 2.0, + "max_length": 200, + "min_length": 30, + "no_repeat_ngram_size": 3, + "num_beams": 4, + "prefix": "summarize: " + }, + "translation_en_to_de": { + "early_stopping": true, + "max_length": 300, + "num_beams": 4, + "prefix": "translate English to German: " + }, + "translation_en_to_fr": { + "early_stopping": true, + "max_length": 300, + "num_beams": 4, + "prefix": "translate English to French: " + }, + "translation_en_to_ro": { + "early_stopping": true, + "max_length": 300, + "num_beams": 4, + "prefix": "translate English to Romanian: " + } + }, + "temperature": 1.0, + "tf_legacy_loss": false, + "tie_encoder_decoder": false, + "tie_word_embeddings": false, + "tokenizer_class": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": "float32", + "torchscript": false, + "transformers_version": "4.27.0.dev0", + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 32128 + }, + "torch_dtype": "float32", + "transformers_version": null, + "use_decoder_only_language_model": false, + "vision_config": { + "_name_or_path": "", + "add_cross_attention": false, + "architectures": null, + "attention_dropout": 0.0, + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": null, + "chunk_size_feed_forward": 0, + "cross_attention_hidden_size": null, + "decoder_start_token_id": null, + "diversity_penalty": 0.0, + "do_sample": false, + "dropout": 0.0, + "early_stopping": false, + "encoder_no_repeat_ngram_size": 0, + "eos_token_id": null, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu", + "hidden_size": 1408, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "image_size": 224, + "initializer_factor": 1.0, + "initializer_range": 1e-10, + "intermediate_size": 6144, + "is_decoder": false, + "is_encoder_decoder": false, + "label2id": { + "LABEL_0": 0, + "LABEL_1": 1 + }, + "layer_norm_eps": 1e-05, + "length_penalty": 1.0, + "max_length": 20, + "min_length": 0, + "model_type": "blip_2_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 16, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "num_hidden_layers": 39, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": null, + "patch_size": 14, + "prefix": null, + "problem_type": null, + "projection_dim": 512, + "pruned_heads": {}, + "qkv_bias": true, + "remove_invalid_values": false, + "repetition_penalty": 1.0, + "return_dict": true, + "return_dict_in_generate": false, + "sep_token_id": null, + "suppress_tokens": null, + "task_specific_params": null, + "temperature": 1.0, + "tf_legacy_loss": false, + "tie_encoder_decoder": false, + "tie_word_embeddings": true, + "tokenizer_class": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": null, + "torchscript": false, + "transformers_version": "4.27.0.dev0", + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/pytorch_model-00001-of-00002.bin b/pytorch_model-00001-of-00002.bin new file mode 100644 index 0000000..47300fb --- /dev/null +++ b/pytorch_model-00001-of-00002.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:537bb68668d2cc0e84297ee5c23a77e5a86fc28f528afc642155bf5b02dc7e7f +size 9441197415 diff --git a/pytorch_model-00002-of-00002.bin b/pytorch_model-00002-of-00002.bin new file mode 100644 index 0000000..08693f4 --- /dev/null +++ b/pytorch_model-00002-of-00002.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afef3d90827b19571700dc3cf3ce403b34ae35cbc2137d0b772660af4115d804 +size 6328861892 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..f19896c --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,1337 @@ +{ + "metadata": { + "total_size": 16295951872 + }, + "weight_map": { + "language_model.decoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", + "language_model.decoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", + "language_model.decoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", + "language_model.decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00002.bin", + "language_model.decoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", + "language_model.decoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.decoder.block.0.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin", + "language_model.decoder.block.0.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin", + "language_model.decoder.block.0.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin", + "language_model.decoder.block.0.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin", + "language_model.decoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", + "language_model.decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.0.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.0.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.1.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.1.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.1.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.1.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.1.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.1.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.10.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.10.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.10.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.10.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.10.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.10.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.11.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.11.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.11.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.11.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.11.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.11.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.12.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.12.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.12.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.12.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.12.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.12.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.12.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.12.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.13.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.13.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.13.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.13.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.13.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.13.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.13.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.13.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.14.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.14.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.14.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.14.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.14.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.14.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.14.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.14.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.15.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.15.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.15.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.15.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.15.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.15.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.15.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.15.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.16.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.16.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.16.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.16.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.16.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.16.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.16.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.16.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.17.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.17.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.17.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.17.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.17.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.17.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.17.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.17.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.18.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.18.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.18.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.18.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.18.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.18.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.18.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.18.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.19.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.19.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.19.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.19.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.19.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.19.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.19.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.19.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.2.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.2.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.2.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.2.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.2.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.2.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.20.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.20.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.20.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.20.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.20.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.20.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.20.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.20.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.21.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.21.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.21.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.21.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.21.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.21.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.21.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.21.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.22.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.22.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.22.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.22.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.22.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.22.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.22.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.22.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.23.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.23.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.23.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.23.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.23.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.23.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.23.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.23.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.3.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.3.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.3.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.3.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.3.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.3.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.4.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.4.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.4.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.4.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.4.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.4.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.5.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.5.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.5.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.5.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.5.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.5.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.6.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.6.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.6.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.6.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.6.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.6.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.7.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.7.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.7.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.7.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.7.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.7.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.8.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.8.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.8.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.8.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.8.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.8.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.9.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.9.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.9.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.9.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.9.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.block.9.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.decoder.embed_tokens.weight": "pytorch_model-00001-of-00002.bin", + "language_model.decoder.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin", + "language_model.encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.12.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.13.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.14.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.15.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.16.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.17.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.18.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.19.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.20.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.21.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.22.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.23.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.embed_tokens.weight": "pytorch_model-00001-of-00002.bin", + "language_model.encoder.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin", + "language_model.lm_head.weight": "pytorch_model-00002-of-00002.bin", + "language_model.shared.weight": "pytorch_model-00001-of-00002.bin", + "language_projection.bias": "pytorch_model-00001-of-00002.bin", + "language_projection.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.0.attention.attention.key.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.0.attention.attention.key.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.0.attention.attention.query.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.0.attention.attention.query.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.0.attention.attention.value.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.0.attention.attention.value.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.0.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.0.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.0.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.0.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.0.crossattention.attention.key.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.0.crossattention.attention.key.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.0.crossattention.attention.query.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.0.crossattention.attention.query.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.0.crossattention.attention.value.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.0.crossattention.attention.value.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.0.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.0.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.0.crossattention.output.dense.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.0.crossattention.output.dense.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.0.intermediate_query.dense.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.0.intermediate_query.dense.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.0.output_query.LayerNorm.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.0.output_query.LayerNorm.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.0.output_query.dense.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.0.output_query.dense.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.1.attention.attention.key.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.1.attention.attention.key.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.1.attention.attention.query.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.1.attention.attention.query.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.1.attention.attention.value.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.1.attention.attention.value.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.1.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.1.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.1.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.1.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.1.intermediate_query.dense.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.1.intermediate_query.dense.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.1.output_query.LayerNorm.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.1.output_query.LayerNorm.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.1.output_query.dense.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.1.output_query.dense.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.10.attention.attention.key.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.10.attention.attention.key.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.10.attention.attention.query.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.10.attention.attention.query.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.10.attention.attention.value.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.10.attention.attention.value.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.10.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.10.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.10.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.10.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.10.crossattention.attention.key.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.10.crossattention.attention.key.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.10.crossattention.attention.query.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.10.crossattention.attention.query.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.10.crossattention.attention.value.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.10.crossattention.attention.value.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.10.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.10.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.10.crossattention.output.dense.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.10.crossattention.output.dense.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.10.intermediate_query.dense.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.10.intermediate_query.dense.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.10.output_query.LayerNorm.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.10.output_query.LayerNorm.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.10.output_query.dense.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.10.output_query.dense.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.11.attention.attention.key.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.11.attention.attention.key.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.11.attention.attention.query.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.11.attention.attention.query.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.11.attention.attention.value.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.11.attention.attention.value.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.11.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.11.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.11.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.11.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.11.intermediate_query.dense.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.11.intermediate_query.dense.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.11.output_query.LayerNorm.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.11.output_query.LayerNorm.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.11.output_query.dense.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.11.output_query.dense.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.2.attention.attention.key.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.2.attention.attention.key.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.2.attention.attention.query.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.2.attention.attention.query.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.2.attention.attention.value.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.2.attention.attention.value.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.2.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.2.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.2.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.2.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.2.crossattention.attention.key.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.2.crossattention.attention.key.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.2.crossattention.attention.query.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.2.crossattention.attention.query.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.2.crossattention.attention.value.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.2.crossattention.attention.value.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.2.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.2.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.2.crossattention.output.dense.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.2.crossattention.output.dense.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.2.intermediate_query.dense.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.2.intermediate_query.dense.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.2.output_query.LayerNorm.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.2.output_query.LayerNorm.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.2.output_query.dense.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.2.output_query.dense.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.3.attention.attention.key.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.3.attention.attention.key.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.3.attention.attention.query.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.3.attention.attention.query.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.3.attention.attention.value.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.3.attention.attention.value.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.3.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.3.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.3.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.3.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.3.intermediate_query.dense.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.3.intermediate_query.dense.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.3.output_query.LayerNorm.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.3.output_query.LayerNorm.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.3.output_query.dense.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.3.output_query.dense.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.4.attention.attention.key.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.4.attention.attention.key.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.4.attention.attention.query.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.4.attention.attention.query.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.4.attention.attention.value.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.4.attention.attention.value.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.4.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.4.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.4.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.4.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.4.crossattention.attention.key.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.4.crossattention.attention.key.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.4.crossattention.attention.query.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.4.crossattention.attention.query.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.4.crossattention.attention.value.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.4.crossattention.attention.value.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.4.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.4.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.4.crossattention.output.dense.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.4.crossattention.output.dense.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.4.intermediate_query.dense.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.4.intermediate_query.dense.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.4.output_query.LayerNorm.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.4.output_query.LayerNorm.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.4.output_query.dense.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.4.output_query.dense.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.5.attention.attention.key.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.5.attention.attention.key.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.5.attention.attention.query.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.5.attention.attention.query.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.5.attention.attention.value.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.5.attention.attention.value.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.5.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.5.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.5.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.5.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.5.intermediate_query.dense.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.5.intermediate_query.dense.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.5.output_query.LayerNorm.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.5.output_query.LayerNorm.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.5.output_query.dense.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.5.output_query.dense.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.6.attention.attention.key.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.6.attention.attention.key.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.6.attention.attention.query.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.6.attention.attention.query.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.6.attention.attention.value.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.6.attention.attention.value.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.6.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.6.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.6.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.6.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.6.crossattention.attention.key.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.6.crossattention.attention.key.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.6.crossattention.attention.query.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.6.crossattention.attention.query.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.6.crossattention.attention.value.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.6.crossattention.attention.value.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.6.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.6.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.6.crossattention.output.dense.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.6.crossattention.output.dense.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.6.intermediate_query.dense.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.6.intermediate_query.dense.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.6.output_query.LayerNorm.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.6.output_query.LayerNorm.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.6.output_query.dense.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.6.output_query.dense.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.7.attention.attention.key.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.7.attention.attention.key.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.7.attention.attention.query.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.7.attention.attention.query.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.7.attention.attention.value.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.7.attention.attention.value.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.7.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.7.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.7.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.7.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.7.intermediate_query.dense.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.7.intermediate_query.dense.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.7.output_query.LayerNorm.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.7.output_query.LayerNorm.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.7.output_query.dense.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.7.output_query.dense.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.8.attention.attention.key.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.8.attention.attention.key.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.8.attention.attention.query.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.8.attention.attention.query.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.8.attention.attention.value.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.8.attention.attention.value.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.8.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.8.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.8.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.8.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.8.crossattention.attention.key.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.8.crossattention.attention.key.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.8.crossattention.attention.query.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.8.crossattention.attention.query.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.8.crossattention.attention.value.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.8.crossattention.attention.value.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.8.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.8.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.8.crossattention.output.dense.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.8.crossattention.output.dense.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.8.intermediate_query.dense.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.8.intermediate_query.dense.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.8.output_query.LayerNorm.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.8.output_query.LayerNorm.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.8.output_query.dense.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.8.output_query.dense.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.9.attention.attention.key.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.9.attention.attention.key.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.9.attention.attention.query.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.9.attention.attention.query.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.9.attention.attention.value.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.9.attention.attention.value.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.9.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.9.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.9.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.9.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.9.intermediate_query.dense.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.9.intermediate_query.dense.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.9.output_query.LayerNorm.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.9.output_query.LayerNorm.weight": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.9.output_query.dense.bias": "pytorch_model-00001-of-00002.bin", + "qformer.encoder.layer.9.output_query.dense.weight": "pytorch_model-00001-of-00002.bin", + "qformer.layernorm.bias": "pytorch_model-00001-of-00002.bin", + "qformer.layernorm.weight": "pytorch_model-00001-of-00002.bin", + "query_tokens": "pytorch_model-00001-of-00002.bin", + "vision_model.embeddings.class_embedding": "pytorch_model-00001-of-00002.bin", + "vision_model.embeddings.patch_embedding.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.embeddings.patch_embedding.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.embeddings.position_embedding": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.0.layer_norm1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.0.layer_norm1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.0.layer_norm2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.0.layer_norm2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.0.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.0.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.0.self_attn.q_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.0.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.0.self_attn.v_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.1.layer_norm2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.1.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.1.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.1.self_attn.q_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.1.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.1.self_attn.v_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.10.layer_norm2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.10.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.10.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.10.self_attn.q_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.10.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.10.self_attn.v_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.11.layer_norm2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.11.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.11.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.11.self_attn.q_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.11.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.11.self_attn.v_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.12.layer_norm2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.12.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.12.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.12.self_attn.q_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.12.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.12.self_attn.v_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.13.layer_norm2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.13.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.13.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.13.self_attn.q_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.13.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.13.self_attn.v_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.14.layer_norm2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.14.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.14.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.14.self_attn.q_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.14.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.14.self_attn.v_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.15.layer_norm2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.15.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.15.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.15.self_attn.q_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.15.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.15.self_attn.v_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.16.layer_norm2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.16.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.16.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.16.self_attn.q_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.16.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.16.self_attn.v_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.17.layer_norm2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.17.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.17.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.17.self_attn.q_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.17.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.17.self_attn.v_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.18.layer_norm2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.18.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.18.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.18.self_attn.q_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.18.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.18.self_attn.v_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.19.layer_norm2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.19.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.19.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.19.self_attn.q_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.19.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.19.self_attn.v_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.2.layer_norm2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.2.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.2.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.2.self_attn.q_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.2.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.2.self_attn.v_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.20.layer_norm2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.20.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.20.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.20.self_attn.q_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.20.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.20.self_attn.v_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.21.layer_norm2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.21.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.21.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.21.self_attn.q_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.21.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.21.self_attn.v_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.22.layer_norm2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.22.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.22.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.22.self_attn.q_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.22.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.22.self_attn.v_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.23.layer_norm2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.23.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.23.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.23.self_attn.q_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.23.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.23.self_attn.v_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.24.layer_norm1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.24.layer_norm1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.24.layer_norm2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.24.layer_norm2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.24.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.24.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.24.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.24.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.24.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.24.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.24.self_attn.q_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.24.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.24.self_attn.v_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.25.layer_norm1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.25.layer_norm1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.25.layer_norm2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.25.layer_norm2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.25.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.25.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.25.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.25.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.25.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.25.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.25.self_attn.q_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.25.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.25.self_attn.v_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.26.layer_norm1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.26.layer_norm1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.26.layer_norm2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.26.layer_norm2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.26.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.26.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.26.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.26.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.26.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.26.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.26.self_attn.q_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.26.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.26.self_attn.v_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.27.layer_norm1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.27.layer_norm1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.27.layer_norm2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.27.layer_norm2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.27.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.27.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.27.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.27.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.27.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.27.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.27.self_attn.q_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.27.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.27.self_attn.v_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.28.layer_norm1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.28.layer_norm1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.28.layer_norm2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.28.layer_norm2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.28.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.28.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.28.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.28.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.28.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.28.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.28.self_attn.q_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.28.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.28.self_attn.v_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.29.layer_norm1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.29.layer_norm1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.29.layer_norm2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.29.layer_norm2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.29.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.29.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.29.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.29.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.29.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.29.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.29.self_attn.q_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.29.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.29.self_attn.v_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.3.layer_norm2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.3.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.3.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.3.self_attn.q_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.3.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.3.self_attn.v_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.30.layer_norm1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.30.layer_norm1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.30.layer_norm2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.30.layer_norm2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.30.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.30.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.30.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.30.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.30.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.30.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.30.self_attn.q_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.30.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.30.self_attn.v_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.31.layer_norm1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.31.layer_norm1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.31.layer_norm2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.31.layer_norm2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.31.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.31.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.31.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.31.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.31.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.31.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.31.self_attn.q_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.31.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.31.self_attn.v_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.32.layer_norm1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.32.layer_norm1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.32.layer_norm2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.32.layer_norm2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.32.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.32.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.32.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.32.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.32.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.32.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.32.self_attn.q_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.32.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.32.self_attn.v_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.33.layer_norm1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.33.layer_norm1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.33.layer_norm2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.33.layer_norm2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.33.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.33.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.33.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.33.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.33.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.33.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.33.self_attn.q_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.33.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.33.self_attn.v_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.34.layer_norm1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.34.layer_norm1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.34.layer_norm2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.34.layer_norm2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.34.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.34.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.34.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.34.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.34.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.34.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.34.self_attn.q_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.34.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.34.self_attn.v_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.35.layer_norm1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.35.layer_norm1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.35.layer_norm2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.35.layer_norm2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.35.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.35.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.35.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.35.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.35.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.35.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.35.self_attn.q_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.35.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.35.self_attn.v_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.36.layer_norm1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.36.layer_norm1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.36.layer_norm2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.36.layer_norm2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.36.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.36.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.36.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.36.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.36.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.36.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.36.self_attn.q_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.36.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.36.self_attn.v_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.37.layer_norm1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.37.layer_norm1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.37.layer_norm2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.37.layer_norm2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.37.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.37.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.37.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.37.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.37.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.37.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.37.self_attn.q_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.37.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.37.self_attn.v_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.38.layer_norm1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.38.layer_norm1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.38.layer_norm2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.38.layer_norm2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.38.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.38.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.38.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.38.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.38.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.38.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.38.self_attn.q_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.38.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.38.self_attn.v_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.4.layer_norm2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.4.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.4.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.4.self_attn.q_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.4.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.4.self_attn.v_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.5.layer_norm2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.5.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.5.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.5.self_attn.q_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.5.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.5.self_attn.v_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.6.layer_norm2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.6.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.6.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.6.self_attn.q_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.6.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.6.self_attn.v_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.7.layer_norm2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.7.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.7.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.7.self_attn.q_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.7.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.7.self_attn.v_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.8.layer_norm2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.8.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.8.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.8.self_attn.q_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.8.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.8.self_attn.v_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.9.layer_norm2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.9.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.9.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.9.self_attn.q_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.9.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin", + "vision_model.encoder.layers.9.self_attn.v_bias": "pytorch_model-00001-of-00002.bin", + "vision_model.post_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "vision_model.post_layernorm.weight": "pytorch_model-00001-of-00002.bin" + } +}